Featured Papers
RRSIS: Referring Remote Sensing Image Segmentation
Localizing desired objects from remote sensing images is of great use in practical applications. Referring image segmentation, which aims at segmenting out the objects to which a given expression refers, has been extensively studied in natural images. However, almost no research attention is given to this task of remote sensing imagery. Considering its potential for real-world applications, in this paper, we introduce referring remote sensing image segmentation (RRSIS) to fill in this gap and make some insightful explorations. Specifically, we create a new dataset, called RefSegRS, for this task, enabling us to evaluate different methods. Afterward, we benchmark referring image segmentation methods of natural images on the RefSegRS dataset and find that these models show limited efficacy in detecting small and scattered objects. To alleviate this issue, we propose a language-guided cross-scale enhancement (LGCE) module that utilizes linguistic features to adaptively enhance multi-scale visual features by integrating both deep and shallow features. The proposed dataset, benchmarking results, and the designed LGCE module provide insights into the design of a better RRSIS model.
Reference: Zhenghang Yuan, Lichao Mou, Yuansheng Hua, Xiao Xiang Zhu (2024). RRSIS: Referring remote sensing image segmentation. IEEE Transactions Geoscience and Remote Sensing, in press.
A High-Resolution Calving Front Data Product for Marine-Terminating Glaciers in Svalbard
Glacier calving fronts are an important indicator of the processes in the Earth's large ice sheets in Greenland and Antarctica. Existing approaches for calving front detection generally work by first performing a pixel-wise segmentation or edge detection, and then extract the actual calving front in a post-processing step. Our goal in this study is to build a model that only needs a single step, and directly outputs the calving front as a polyline. Following the idea of explicit contour prediction, we have developed a new method called “Charting Outlines by Recurrent Adaptation” (COBRA). It works by combining the idea of Active Contour models with deep learning. First, a 2D CNN backbone derives feature maps from the input imagery. Then, a 1D CNN (Snake Head) iteratively deforms an initial contour until to match the true contour. Evaluations on several large-scale datasets of Greenland's glaciers show that this approach is indeed better at predicting glacier calving fronts than previous methods.
The model results can be seen here: https://khdlr.github.io/COBRA/map.html
Reference: Tian Li, Konrad Heidler, Lichao Mou, Ádám Ignéczi, Xiao Xiang Zhu, Jonathan L Bamber (2024). A High-Resolution Calving Front Data Product for Marine-Terminating Glaciers in Svalbard. Earth System Science Data, 16, pp. 919–939. (link)
Books
1. | Gustau Camps-Valls, Devis Tuia, Xiao Xiang Zhu, Markus Reichstein (Editors) (2021). Deep learning for the Earth Sciences: A comprehensive approach to remote sensing, climate science and geosciences, Wiley & Sons, 2021. (link) |
2. | Johannes Brinkmann, Mrinalini Kochupillai (2020). Law, Business, and Legitimacy, Springer International Publishing, 2020. (link) |
Journal Papers
|
Double-Blind Peer-Reviewed Conference Papers
1. | Sanja Scepanovic, Ivica Obadic, Sagar Joglekar, Laura Giustarini, Cristiano Nattero, Daniele Quercia, Xiao Xiang Zhu (2023). MedSat: A Public Health Dataset for England Featuring Medical Prescriptions and Satellite Imagery. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track. |
2. | Adam Stewart, Nils Lehmann, Isaac Corley, Yi Wang, Yi-Chia Chang, Nassim Ait Ali Braham, Shradha Sehgal, Caleb Robinson, Arindam Banerjee (2023). SSL4EO-L: Datasets and Foundation Models for Landsat Imagery. In NeurIPS Benchmark and Dataset Track. |
3. | Alexandre Lacoste, Nils Lehmann, Pau Rodriguez, Evan David Sherwin, Hannah Kerner, Björn Lütjens, Jeremy Andrew Irvin, David Dao, Hamed Alemohammad, Alexandre Drouin, Mehmet Gunturkun, Gabriel Huang, David Vazquez, Dava Newman, Yoshua Bengio, Stefano Ermon, Xiao Xiang Zhu (2023). GEO-Bench: Toward Foundation Models for Earth Monitoring. In NeurIPS Benchmark and Dataset Track. |
4. | Runming Dong, Lichao Mou, Mengxuan Chen, Weijia Li, Xin-Yi Tong, Shuai Yuan, Lixian Zhang, Juepeng Zheng, Xiao Xiang Zhu, Haohuan Fu (2023). Large-Scale Land Cover Mapping with Fine-Grained Classes via Class-Aware Semi-Supervised Semantic Segmentation. In Proceedings of ICCV 2023, Paris, France.. |
5. | Patrick Ebel, Vivien Sainte Fare Garnot, Michael Schmitt, Jan Wegner, Xiao Xiang Zhu (2023). UnCRtainTS: Uncertainty Quantification for Cloud Removal in Optical Satellite Time Series. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. (pdf) |
6. | Frank Nussbaum, Jakob Gawlikowski, Julia Niebling (2022). Structuring Uncertainty for Fine-Grained Sampling in Stochastic Segmentation Networks. In Advances in Neural Information Processing Systems. (pdf) |
7. | Sudipan Saha, Shan Zhao, Nasrullah Sheikh, Xiao Xiang Zhu (2022). Reiterative Domain Aware Multi-Target Adaptation. In German Conference on Pattern Recognition (GCPR). |
8. | Teo Beker, Homa Ansari, Sina Montazeri, Qiang Song, Xiao Xiang Zhu (2022). Fine-tuning CNNs for Decreased Sensitivity to Non-volcanic Deformation Velocity Signal. In XXIV ISPRS Congress - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
9. | Aysim Toker, Lukas Kondmann, Mark Weber, Marvin Eisenberger, Andrés Camero, Jingliang Hu, Ariadna Pregel Hoderlein, Caglar Cenaras, Timothy Davis, Daniel Cremers, Giovanni Marchisio, Xiao Xiang Zhu, Laura Leal-Taixé (2022). DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). |
10. | Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu (2022). HPO: We won't get fooled again. In First Conference on Automated Machine Learning (Late-Breaking Workshop). (link) |
11. | David Schinagl, Georg Krispel, Horst Possegger, Peter M Roth, Horst Bischof (2022). OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. (link) |
12. | Codruț-Andrei Diaconu, Sudipan Saha, Stephan Günnemann, Xiao Xiang Zhu (2022). Understanding the Role of Weather Data for Earth Surface Forecasting using a ConvLSTM-based Model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. |
13. | Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu (2022). Landscape of Neural Architecture Search across sensors: how much do they differ ?. In XXIV ISPRS Congress - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
14. | Shan Zhao, Sudipan Saha, Xiao Xiang Zhu (2022). Graph Neural Network Based Open-set Domain Adaptation. In XXIV ISPRS Congress - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
15. | Sudipan Saha, Jakob Gawlikowski, Xiao Xiang Zhu (2022). Fusing Multiple Untrained Networks for Hyperspectral Change Detection. In XXIV ISPRS Congress - The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
16. | Laura Cue La Rosa, Dario Augusto Borges Oliveira (2021). Learning from Label Proportions with Prototypical Contrastive Clustering. In Thirty-Sixth AAAI Conference on Artificial Intelligence, Main Track. |
17. | Gyri Reiersen, David Dao, Björn Lütjens, Konstantin Klemmer, Kenza Amara, Attila Steinegger, Ce Zhang, Xiao Xiang Zhu (2021). ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AI for Social Impact Track. |
18. | Muhammad G. Javed, Muhammad Raza, Muhammad Mohsin Ghaffar, Christian Weis, Norbert Wehn, Muhammad Shahzad, Faisal Shafait (2021). QuantYOLO: A High-Throughput and Power-Efficient Object Detection Network for Resource and Power Constrained UAVs. In International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2021. |
19. | Nosheen Abid, Muhammad Imran Malik, Muhammad Shahzad, Faisal Shafait, H Ali, Muhammad Mohsin Ghaffar, Christian Weis, Norbert Wehn, Marcus Liwicki (2021). Burnt Forest Estimation from Sentinel-2 Imagery of Australia using Unsupervised Deep Learning. In International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2021. |
20. | Nouman Ahmed, Sudipan Saha, Muhammad Shahzad, Muhammad Moazam Fraz, Xiao Xiang Zhu (2021). Progressive Unsupervised Deep Transfer Learning for Forest Mapping in Satellite Image. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops. |
21. | David Mandl, Peter Mohr, Stefanie Zollmann, Tobias Langlotz, Shohei Mori, Christoph Ebner, Peter M. Roth, Denis Kalkofen (2021). Learning Camera Characteristics for Coherent Mixed Reality Rendering. In IEEE International Symposium on Mixed and Augmented Reality. |
22. | Mina Basirat, Peter M. Roth (2021). S*ReLU: Learning Piecewise Linear Activation Functions via ParticleSwarm Optimization. In International Conference on Computer Vision Theory and Applications. |
23. | Patrick Ebel, Sudipan Saha, Xiao Xiang Zhu (2021). Fusing Multi-modal Data for Supervised Change Detection. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
24. | Sudipan Saha, Lukas Kondmann, Xiao Xiang Zhu (2021). Deep No Learning Approach for Unsupervised Change Detection in Hyperspectral Images. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
25. | Chunping Qiu, Paolo Gamba, Michael Schmitt, Xiao Xiang Zhu (2020). Learning from Noisy Samples for Man-made Impervious Surface Mapping. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
26. | Danfeng Hong, Jing Yao, Xin Wu, Chanussot Jocelyn, Xiao Xiang Zhu (2020). Spatial-Spectral Manifold Embedding of Hyperspectral Data. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
27. | Di Hu, Xuhong Li, Lichao Mou, Pu Jin, Dong Chen, Liping Jing, Xiao Xiang Zhu, Dejing Dou (2020). Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition. In European Conference on Computer Vision 2020. |
28. | Jing Yao, Danfeng Hong, Jocelyn Chanussot, Deyu Meng, Xiao Xiang Zhu, Zongben Xu (2020). Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution. In European Conference on Computer Vision. |
29. | Jingliang Hu, Lichao Mou, Xiao Xiang Zhu (2020). Unsupervised Domain Adaptation using a Teacher-student Network for Cross-city Classification of Sentinel-2 Images. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
30. | Lichao Mou, Yuansheng Hua, Jin Pu, Xiao Xiang Zhu (2020). Global Message Passing in Networks via Task-driven Random Walks for Semantic Segmentation of Remote Sensing Images. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2020. |
31. | Michael Schmitt, Jonathan Prexl, Parick Ebel, Lukas Liebel, Xiao Xiang Zhu (2020). Weakly Supervised Semantic Segmentation of Satellite Images for Land Cover Mapping - Challenges and Opportunities. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
32. | Qingyu Li, Yilei Shi, Stefan Auer, Xiao Xiang Zhu (2020). Detection of Undocumented Buildings using Convolutional Neural Network and Official Geodata. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2020. |
33. | Rong Liu, Xiao Xiang Zhu (2020). Improved Endmember Bundle Extraction based on Multi-Objective Particle Swarm Optimization. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2020. |
34. | Saqib Ali Khan, Yilei Shi, Muhammad Shahzad, Xiao Xiang Zhu (2020). FGCN: Deep Feature-Based Graph Convolutional Network for Semantic Segmentation of Urban 3D Point Clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. |
35. | Sina Montazeri, Xiao Xiang Zhu (2020). Geodetic InSAR: Detailed Urban Area Mapping with Absolute Coordinates. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2020. |
36. | Xiao Xiang Zhu (2020). AI4EO: Reasoning, Uncertainty, Ethics and Beyond. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
37. | Xiao Xiang Zhu (2020). Deep Learning for Mapping Global Urban Morphology from Space. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
38. | Yuxing Xie, Jiaojiao Tian, Xiao Xiang Zhu (2020). Feature Relevance Point Cloud Classification with Imperfect Training Data. In ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
39. | Lloyd Haydn Hughes, Michael Schmitt (2019). A Semi-Supervised Approach to SAR-Optical Image Matching. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
40. | Lichao Mou, Yuansheng Hua, Xiao Xiang Zhu (2019). A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes. In IEEE Conference on Computer Vision and Pattern Recognition. (link) |
41. | Michael Schmitt, Lloyd Hadn Hughes, Chunping Qiu, Xiao Xiang Zhu (2019). Aggregating Cloud-free Sentinel-2 Images With Google Earth Engine. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
42. | Michael Schmitt, Lloyd Haydn Hughes, Chunping Qiu, Xiao Xiang Zhu (2019). SEN12MS - A Curated Dataset of Georeferenced Multi-spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
43. | Rong Huang, Zhen Ye, Danfeng Hong, Yusheng Xu, Uwe Stilla (2019). Semantic Labeling and Refinment of Lidar Point Clouds Using Deep Neural Networkin Urban Areas. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 4. |
44. | Lloyd Haydn Hughes, Stefan Auer, Michael Schmitt (2018). Investigation of Joint Visibility Between SAR and Optical Images of Urban Environments. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
45. | Chunping Qiu, Michael Schmitt, Pedram Ghamisi, Xiao Xiang Zhu (2018). Effect of the Training Set Configuration on Sentinel-2-based Urban Local Climate Zone Classification.. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
46. | Danfeng Hong, Naoto Yokoya, Jian Xu, Xiao Xiang Zhu (2018). Joint & Progressive Learning From High-dimensional Data for Multi-label Classification. In Proceedings of the European Conference on Computer Vision (ECCV). |
47. | Michael Schmitt, Lloyd Haydn Hughes, Xiao Xiang Zhu (2018). The SEN1-2 Dataset for Deep Learning in SAR-optical Data Fusion. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
48. | Chunping Qiu, Michael Schmitt, Xiao Xiang Zhu (2017). A Tie Point Matching Strategy for Very High Resolution SAR-Optical Stereogrammety Over Urban Areas. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
49. | Yuanyuan Wang, Xiao Xiang Zhu (2017). Earth Observation Using SAR and Social Media Images. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. |
50. | Jingliang Hu, Rui Guo, Xiao Xiang Zhu, Gerald Baier, Yuanyuan Wang (2015). Non-local Means Filter for Polarimetric SAR Speckle Reduction-experiments Using TerraSAR-x Data. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Single-Blind Peer-Reviewed Conference Papers
1. | Yao Sun, Stefan Auer, Liqiu Meng, Xiao Xiang Zhu (2023). Artificial Intelligence based Building Attributes Enrichment in OpenStreetMap using Street-view Images. In International Cartographic Conference 2023. |
2. | Korbinian Staudacher, Tobias Guggemos, Wolfgang Gehrke, Sophia Grundner-Culemann (2022). Reducing 2-Qubit Gate Count for ZX-Calculus Based Quantum Circuit Optimization. In Quantum Processing and Languages (QPL 22). (pdf) |
3. | Qingsong Xu, Yilei Shi, Xiao Xiang Zhu (2022). Universal Domain Adaptation without Source Data for Remote Sensing Image Scene Classification. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
4. | Conrad M Albrecht, Chenying Liu, Yi Wang, Levente J Klein, Xiao Xiang Zhu (2022). Monitoring Urban Forests from Auto-Generated Segmentation Maps. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
5. | Yi Wang, Conrad M Albrecht, Xiao Xiang Zhu (2022). Self-supervised Vision Transformers for Joint SAR-optical Representation Learning. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
6. | Nikolai Skuppin, Eike Hoffmann, Yilei Shi, Xiao Xiang Zhu (2022). Building Type Classification with Incomplete Labels. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
7. | Zhenghang Yuan, Lichao Mou, Xiao Xiang Zhu (2022). Change-aware Visual Question Answering. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
8. | Zhitong Xiong, Xiao Xiang Zhu (2022). Knowledge Transfer for Label-efficient Monocular Height Estimation. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
9. | Fahong Zhang, Yilei Shi, Xiao Xiang Zhu (2022). Domain-agnostic Domain Adaption for Building Footprint Extraction. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
10. | Teo Beker, Homa Ansari, Sina Montazeri, Qiang Song, Xiao Xiang Zhu (2022). Explainability Analysis of CNN in Detection of Volcanic Deformation Signal. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
11. | Jakob Gawlikowski, Sudipan Saha, Julia Niebling, Xiao Xiang Zhu (2022). Robust Distribution-Shift Aware SAR-Optical Data Fusion for Multi-Label Scene Classification. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
12. | Sudipan Saha, Jakob Gawlikowski, Jay Nandy, Xiao Xiang Zhu (2022). Compact Feature Representation for Unsupervised OOD Detection. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
13. | Sudipan Saha, Shao Zhan, Muhammad Shahzad, Xiao Xiang Zhu (2022). Mitigating Distribution Shift for Multi-sensor Classification. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
14. | Qian Song, Conrad M. Albrecht, Zhitong Xiong, Xiao Xiang Zhu (2022). Towards Global Forest Biomass Estimators From Tree Height Data. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
15. | Jonas Gütter, Julia Niebling, Xiao Xiang Zhu (2022). Analysing the Interactions Between Training Dataset Size, Label Noise and Model Performance in Remote Sensing Data. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
16. | Konrad Heidler, Lichao Mou, Erik Loebel, Mirko Scheinert, Sébastien" Lef\`evre, Xiao Xiang Zhu (2022). Deep Active Contour Models for Delineating Glacier Calving Fronts. In IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium. |
17. | Patrick Ebel, Yajin Xu, Michael Schmitt, Xiao Xiang Zhu (2022). Multi-Sensor Time Series Cloud Removal Fusing Optical and SAR Satellite Information. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
18. | Sol Cummings, Lukas Kondmann, Xiao Xiang Zhu (2022). Siamese Attention U-Net for Multi-Class Change Detection. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
19. | Wei Yao, Gottfried Schwarz, Mihai Datcu (2022). A Pattern Analysis Image Validation Tool for the Generation of Reliable Earth Observation Image Benchmarks. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. |
20. | Patrick Damme, Marius Birkenbach, Constantinos Bitsakos, Matthias Boehm, Philippe Bonnet, Florina Ciorba, Mark Dokter, Pawel Dowgiallo, Ahmed Eleliemy, Christian Faerber, Georgios Goumas, Dirk Habich, Niclas Hedam, Marlies Hofer, Wenjun Huang, Kevin Innerebner, Vasileios Karakostas, Roman Kern, Tomaž Kosar, Alexander Krause, Daniel Krems, Andreas Laber, Wolfgang Lehner, Eric Mier, Marcus Paradies, Bernhard Peischl, Gabrielle Poerwawinata, Stratos Psomadakis, Tilmann Rabl, Piotr Ratuszniak, Pedro Silva, Nikolai Skuppin, Andreas Starzacher, Benjamin Steinwender, Ilin Tolovski, Pınar Tözün, Wojciech Ulatowski, Yuanyuan Wang, Izajasz Wrosz, Aleš Zamuda, Ce Zhang, Xiao Xiang Zhu (2022). DAPHNE: An Open and Extensible System Infrastructure for Integrated Data Analysis Pipelines. In 12th Annual Conference on Innovative Data Systems Research (CIDR ’22). |
21. | Yilei Shi, Richard Bamler, Yuanyuan Wang, Xiao Xiang Zhu (2020). Generation of Large-Scale High Quality 3-D Urban Models. In 2020 IEEE Radar Conference (RadarConf20). |
22. | Yilei Shi, Richard Bamler, Yuanyuan Wang, Xiao Xiang Zhu (2021). Generation of Large Scale 3-D City Models Using Insar and Optical Data. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. |
23. | Yuanyuan Wang, Kun Qian, Xiao Xiang Zhu (2021). Efficient SAR Tomographic Inversion via Sparse Bayesian Learning. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. |
24. | Konrad Heidler, Lichao Mou, Celia Baumhoer, Andreas Dietz, Xiao Xiang Zhu (2021). HED-UNet: A Multi-Scale Framework for Simultaneous Segmentation and Edge Detection. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. |
25. | Konrad Heidler, Lichao Mou, Xiao Xiang Zhu (2021). Seeing the Bigger Picture: Enabling Large Context Windows in Neural Networks by Combining Multiple Zoom Levels. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. |
26. | Patrick Ebel, Michael Schmitt, Xiao Xiang Zhu (2021). Internal Learning for Sequence-to-Sequence Cloud Removal via Synthetic Aperture Radar Prior Information. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. |
27. | Jonas Gütter, Anna Kruspe, Xiao Xiang Zhu (2021). An OpenStreetMap-Based Dataset of Building Footprints for Analysing Different Types of Label Noise. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. |
28. | Yao Sun, Yuansheng Hua, Lichao Mou, Xiao Xiang Zhu (2021). Conditional GIS-Aware Network for Individual Building Segmentation in a VHR SAR Image. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. |
29. | Lukas Kondmann, Aysim Toker, Marc Rußwurm, Andrés Camero, Devis Peressuti, Grega Milcinski, Pierre-Philippe Mathieu, Nicolas Longépé, Timothy Davis, Giovanni Marchisio, Laura Leal-Taixé, Xiao Xiang Zhu (2021). DENETHOR: The DynamicEarthNET dataset for Harmonized, inter-Operable, analysis-Ready, daily crop monitoring from space. In Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track (Round 2). (link) |
30. | Eike Jens Hoffmann, Mohsin Ali, Xiao Xiang Zhu (2021). Zooming into Uncertainties: Towards Fusing Multi Zoom Level Imagery for Urban Land Use Segmentation. In International Geoscience and Remote Sensing Symposium (IGARSS). |
31. | Antonius Scherer, Tobias Guggemos, Sophia Grundner-Culemann, Nikolas Pomplun, Sven Prüfer, Andreas Spörl (2021). OnCall Operator Scheduling for Satellites with Grover's Algorithm. In International Conference on Computational Science. (link) |
32. | Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu (2021). Compact Neural Architecture Search for Local Climate Zones Classification. In ESANN 2021, 29th European Symposium on Artificial Neural Networks, Bruges, Belgium, 2021, Proceedings. |
33. | Nils Mäurer, Thomas Gräupl, Christop Gentsch, Tobias Guggemos, Marcel Tiepelt, Corinna Schmitt, Gabi Dreo Rodosek (2021). The Secure Cell Attachment Procedure of LDACS. In IEEE European Symposium on Security and Privacy, Safety vs Security in the Air and on the Ground. |
34. | Homa Ansari, Marc Russwurm, Syed Mohsin Ali, Sina Montazeri, Alessandro Parizzi, Xiao Xiang Zhu (2021). InSAR Displacement Time Series Mining: A Machine Learning Approach. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
35. | Jakob Gawlikowski, Sudipan Saha, Anna Kruspe, Xiao Xiang Zhu (2021). Towards Out-of-distribution Detection for Remote Sensing. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
36. | Jonathan Prexl, Sudipan Saha, Xiao Xiang Zhu (2021). Mitigating Spatial and Spectral Differences for Change Detection Using Super-resolution and Unsupervised Learning. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
37. | Kun Qian, Yuanyuan Wang, Xiao Xiang Zhu (2021). Towards SAR Tomographic Inversion via Sparse Bayesian Learning. In EUSAR 2021; 13th European Conference on Synthetic Aperture Radar. |
38. | Lukas Kondmann, Hannes Taubenböck, Xiao Xiang Zhu (2021). Blinded by the Light: Monitoring Local Economic Development Over Time With Nightlight Emissions. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
39. | Mrinalini Kochupillai (2021). Outline of a Novel Approach for Indentifying Ethical Issues in Early Stages of Research. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
40. | Roland Perko, Mario Theuermann, Manfred Klopschitz, Thomas Schnabel, Peter M. Roth (2021). Protocol Design Issues for Object Density Estimation and Counting in Remote Sensing. In International Geoscience and Remote Sensing Symposium (IGARSS). |
41. | Sudipan Saha, Biplab Banerjee, Xiao Xiang Zhu (2021). Trusting Small Training Dataset for Supervised Change Detection. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
42. | Ruchika Chavhan, Biplab Banerjee, Xiao Xiang Zhu, Subhasis Chaudhuri (2021). Novel Actor Dual-Critic Model for Remote Sensing Image Captioning. In International conference on pattern recognition. |
43. | Danfeng Hong, Yao Jing, Jocelyn Chanussot, Xiao Xiang Zhu (2020). Unsupervised Hyperspectral Embedding by Learning A Deep Regression Network. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
44. | Gustau Camps-Valls, Markus Reichstein, Xiao Xiang Zhu (2020). Advancing Deep Learning for Earth Sciences: From Hybrid Modeling to Interpretability. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
45. | Homa Ansari, Francesco De Zan, Alessandro Parizzi (2020). Systematic Interferometric Phase Biases and their Impact on Earth Surface Deformation Monitoring. In 13th European Conference on Synthetic Aperture Radar - postponed to 2021. |
46. | Jakob Gawlikowski, Michael Schmitt, Anna Kruspe, Xiao Xiang Zhu (2020). On the Fusion Strategies OF Sentinel-1 and Sentinel-2 Data For Local Climate Zone Classification. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
47. | Lichao Mou, Yuansheng Hua, Pu Jin, Yilei Shi, Xiao Xiang Zhu (2020). Event and Activity Recognition in Aerial Videos using Deep Neural Networks and a New Dataset. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
48. | Patrick Ebel, Andrea Meraner, Michael Schmitt, Xiao Xiang Zhu (2020). Cloud Removal in Unpaired Sentinel-2 Imagery Using Cycle-Consistent GAN and SAR-Optical Data Fusion. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2020. |
49. | Philipp Sibler, Yuanyuan Wang, Stefan Auer, Mohsin Ali, Xiao Xiang Zhu (2020). Generative Adversarial Networks for Synthesizing InSAR Patches. In European Conference on Synthetic Aperture Radar. |
50. | Qingyu Li, Lichao Mou, Yuansheng Hua, Yao Sun, Pu Jin, Yilei Shi, Xiao Xiang Zhu (2020). Instance Segmentation of Buildings Using Keypoints. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
51. | Sudipan Saha, Lichao Mou, Chunping Qiu, Xiao Xiang Zhu (2020). A Novel Approach to Unsupervised Segmentation of Multitemporal VHR Images Based on Deep Learning. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
52. | Yilei Shi, Qingyu Li, Xiao Xiang Zhu (2020). Building Extraction by Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
53. | Ying Zhang, Lichao Mou, Xiao Xiang Zhu (2020). Vision-Based Scattering Key-Frame Extraction for VideoSAR Summarization. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
54. | Yuansheng Hua, Devis Tuia, Lichao Mou, Xiao Xiang Zhu (2020). Learning Multi-label Aerial Image Classification Under Label Noise: A Regularization Approach Using Word Embeddings. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
55. | Yilei Shi, Yuanyuan Wang, Xiao Xiang Zhu, Richard Bamler (2019). Non-Local SAR Tomography for Large-Scale Urban Mapping. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019, Yokohama, Japan. (link) |
56. | Yuanyuan Wang, Xiao Xiang Zhu (2019). The Challenge of Creating the Sarptical Dataset. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
57. | Chunping Qiu, Michael Schmitt, Hannes Taubenböck, Xiao Xiang Zhu (2019). Mapping Human Settlements with Multi-seasonal Sentinel-2 Imagery and Attention-based ResNeXt. In Joint Urban Remote Sensing Event. |
58. | Chunping Qiu, Michael Schmitt, Xiao Xiang Zhu (2019). Fusing Multi-Seasonal Sentinel-2 Images with Residual Convolutional Neural Networks for Local Climate Zone-Derived Urban Land Cover Classification. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
59. | Chunping Qiu, Michael Schmitt, Xiao Xiang Zhu (2019). Mapping Impervious Surfaces with Multi-seasonal Sentinel-2 Imagery and Deep Neural Networks. In 2019 Joint Urban Remote Sensing Event (JURSE). |
60. | Danfeng Hong, Jocelyn Chanussot, Naoto Yokoya, Uta Heiden, Wieke Heldens, Xiao Xiang Zhu (2019). WU-Net: A Weakly-Supervised Unmixing Network for Remotely Sensed Hyperspectral Imagery. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
61. | Eike Jens Hoffmann, Martin Werner, Xiao Xiang Zhu (2019). Building Instance Classification using Social Media Images. In 2019 Joint Urban Remote Sensing Event (JURSE). |
62. | Eike Jens Hoffmann, Martin Werner, Xiao Xiang Zhu (2019). Mutual Information Analysis of Social Media Images and Building Functions. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
63. | Hossein Bagheri, Michael Schmitt, Xiao Xiang Zhu (2019). Towards the Reconstruction of Prismatic Building Models by SAR-Optical Stereogrammetry. In Joint Urban Remote Sensing Event. |
64. | Jingliang Hu, Danfeng Hong, Yuanyuan Wang, Xiao Xiang Zhu (2019). A Topological Data Analysis Guided Fusion Algorithm: Mapper-Regularized Manifold Alignment. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
65. | Lichao Mou, Yuansheng Hua, Xiao Xiang Zhu (2019). Spatial Relational Reasoning in Networks for Improving Semantic Segmentation of Aerial Images. In IEEE International Geoscience and Remote Sensing Symposium. |
66. | Lloyd Haydn Hughes, Nina Merkle, Tatjana Burgmann, Stefan Auer, Michael Schmitt (2019). Deep Learning for SAR-optical Image Matching. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
67. | Matthias Häberle, Martin Werner, Xiao Xiang Zhu (2019). Building Type Classification from Social Media Texts via Geo-spatial Textmining. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
68. | Qingyu Li, Yilei Shi, Xiao Xiang Zhu (2019). BFGAN–Building Footprint Extraction from Satellite Images. In 2019 Joint Urban Remote Sensing Event (JURSE). |
69. | Qingyu Li, Yilei Shi, Xiao Xiang Zhu (2019). Building Footprint Extraction with Graph Convolutional Network. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
70. | Scott Hensley, Brain Hawkins, Thierry Michel, Ron Muellerschoen, Xiao Xiang Zhu, Andres Reigber, Gustavo Martín del Campo (2019). Uavsar Tomography of Munich. In IEEE International Geoscience and Remote Sensing Symposium. |
71. | Sina Montazeri, Fernando Rodriguez Gonzalez, Xiao Xiang Zhu (2019). Mitigation of Positioning Bias in PSI Point Clouds. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
72. | Thomas Stark, Michael Wurm, Hannes Taubenböck, Xiao Xiang Zhu (2019). Slum Mapping in Imbalanced Remote Sensing Datasets Using Transfer Learned Deep Features. In 2019 Joint Urban Remote Sensing Event (JURSE). |
73. | Thomas Stark, Michael Wurm, Hannes Taubenböck, Xiao Xiang Zhu (2019). Slum Mapping in Imbalanced Remote Sensing Datasets Using Transfer Learned Deep Features. In 2019 Joint Urban Remote Sensing Event (JURSE). |
74. | Xin Wu, Danfeng Hong, Jiaojiao Tian, Ralph Kiefl, Ran Tao (2019). A Weakly-Supervised Deep Network for DSM-Aided Vehicle Detection. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
75. | Xin Wu, Danfeng Hong, Pedram Ghamisi, Wei Li, Ran Tao (2019). LW-ODF: A Light-Weight Object Detection Framework for Optical Remote Sensing Imagery. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
76. | Yao Sun, Yuansheng Hua, Lichao Mou, Xiao Xiang Zhu (2019). Large-scale Building Height Estimation from Single VHR SAR image Using Fully Convolutional Network and GIS building footprints. In Joint Urban Remote Sensing Event (JURSE). |
77. | Yao Sun, Yuanyuan Wang, Xiao Xiang Zhu (2019). Automatic Registration of SAR Image and GIS Building Footprints Data in Dense Urban Area. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
78. | Yilei Shi, Yuanyuan Wang, Xiao Xiang Zhu, Richard Bamler (2019). Large-Scale Urban Mapping using Small Stack Multi-baseline TanDEM-X Interferograms. In Joint Urban Remote Sensing Event (JURSE). |
79. | Yuansheng Hua, Lichao Mou, Xiao Xiang Zhu (2019). Label Relation Inference for Multi-Label Aerial Image Classification. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2019. |
80. | Yuansheng Hua, Lichao Mou, Xiao Xiang Zhu (2019). Multi-label Aerial Image Classification using A Bidirectional Class-wise Attention Network. In Joint Urban Remote Sensing Event. |
81. | Yilei Shi, Yuanyuan Wang, Richard Bamler, Xiao Xiang Zhu (2018). Towards High-resolution Global Urban 3D Model From TanDEM-X Data. In EARSeL 5th Joint Workshop “Urban Remote Sensing – Challenges & Solutions”, Bochum, Germany. (link) |
82. | Jian Kang, Yuanyuan Wang, Xiao Xiang Zhu (2018). Multi-pass SAR Interferometry for 3D Reconstruction of Complex Mountainous Areas Based on Robust Low Rank Tensor Decomposition. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018, Valencia, Spain. (link) |
83. | Yilei Shi, Yuanyuan Wang, Jian Kang, Marie Lachaise, Xiao Xiang Zhu, Richard Bamler (2018). 3D Reconstruction From Very Small TanDEM-X Stacks. In 12th European Conference on Synthetic Aperture Radar 2018. (link) |
84. | Yuanyuan Wang, Xiao Xiang Zhu (2018). Robust Nonlinear Blind SAR Tomography in Urban Areas. In 12th European Conference on Synthetic Aperture Radar 2018. |
85. | Chunping Qiu, Michael Schmitt, Pedram Ghamisi, Lichao Mou, Xiao Xiang Zhu (2018). Feature Importance Analysis of Sentinel-2 Imagery for Large-scale Urban Local Climate Zone Classification. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
86. | Claas Grohnfeldt, Michael Schmitt, Xiao Xiang Zhu (2018). A Conditional Generative Adversarial Network to Fuse SAR and Multispectral Optical Data for Cloud Removal From Sentinel-2 Images. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
87. | Claas Grohnfeldt, Xiao Xiang Zhu (2018). An Image Super-Resolulution Algorithm for the EnMAP Mission Using Sentinel-2 Data as Free Auxiliary Input. In Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. |
88. | Danfeng Hong, Naoto Yokoya, Xiao Xiang Zhu, Jocelyn Chanussot (2018). Learning A Common Subspace from Hyperspectral-Multispectral Correspondences. In Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
89. | Hossein Bagheri, Michael Schmitt, Xiao Xiang Zhu (2018). Urban TanDEM-X Raw DEM Fusion Based on TV-L1 and Huber Models. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
90. | Jian Kang, Yuanyuan Wang, Xiao Xiang Zhu (2018). Low Rank Modeling Based Multi-pass InSAR Technique. In 12th European Conference on Synthetic Aperture Radar 2018, Aachen, Germany. |
91. | Jingliang Hu, Xiao Xiang Zhu (2018). Exploring Sentinel-L Data for Local Climate Zone Classification. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
92. | Lichao Mou, Xiao Xiang Zhu (2018). A Recurrent Convolutional Neural Network for Land Cover Change Detection in Multispectral Images. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
93. | Lloyd H Hughes, Michael Schmitt, Xiao Xiang Zhu (2018). Generative Adversarial Networks for Hard Negative Mining in CNN-based SAR-Optical Image Matching. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
94. | Qingpeng Li, Lichao Mou, Kaiyu Jiang, Qingjie Liu, Yunhong Wang, Xiao Xiang Zhu (2018). Hierarchical Region Based Convolution Neural Network for Multiscale Object Detection in Remote Sensing Images. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
95. | Qingpeng Li, Lichao Mou, Kaiyu Jiang, Qingjie Liu, Yunhong Wang, Xiao Xiang Zhu (2018). Hierarchical Region Based Convolution Neural Network for Multiscale Object Detection in Remote Sensing Images. In IEEE International Geoscience and Remote Sensing Symposium. |
96. | Rong Huang, Hannes Taubenböck, Lichao Mou, Xiao Xiang Zhu (2018). Classification of Settlement Types From Tweets Using LDA and LSTM. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
97. | Xiao Xiang Zhu, Yao Sun, Yilei Shi, Yuanyuan Wang, Nan Ge (2018). Towards Global 3D/4D Urban Modeling Using TanDEM-X Data. In 12th European Conference on Synthetic Aperture Radar. |
98. | Yilei Shi, Xiao Xiang Zhu, Richard Bamler (2018). SAR Tomography using Non-local Sparse Reconstruction. In IEEE International Geoscience and Remote Sensing Symposium. |
99. | Yilei Shi, Xiao Xiang Zhu, Wang Yin, Richard Bamler (2018). An Efficient Algorithm for Compressive Sensing Based SAR Tomography. In European Conference on Synthetic Aperture Radar. |
100. | Yuansheng Hua, Lichao Mou, Xiao Xiang Zhu (2018). LAHNet: A Convolutional Neural Network Fusing Low-and High-Level Features for Aerial Scene Classification. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
101. | Yuanyuan Wang, Xiao Xiang Zhu (2018). The SARptical Dataset for Joint Analysis of SAR and Optical Image in Dense Urban Area. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2018. |
102. | Alexandre Tiard, Laurent Condat, Lucas Drumetz, Jocelyn Chanussot, Wang Yin, Xiao Xiang Zhu (2017). Robust Linear Unmixing With Enhanced Sparsity. In IEEE International Conference on Image Processing (ICIP). |
103. | Chunping Qiu, Michael Schmitt, Xiao Xiang Zhu (2017). Comparative Evaluation of Signal-Based and Descriptor-based Similarity Measures for SAR-optical Image Matching. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
104. | Cristian Rossi, Gerald Baier, Paola Rizzoli, José L Bueso Bello (2017). Topographical Changes Caused by the 2016 Central Italy Earthquake Series. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
105. | Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot, Xiao Xiang Zhu (2017). Learning a Low-coherence Dictionary to Address Spectral Variability for Hyperspectral Unmixing. In 2017 IEEE International Conference on Image Processing (ICIP). |
106. | Gerald Baier, Cristian Rossi, Marie Lachaise, Xiao Xiang Zhu, Richard Bamler (2017). A Nonlocal InSAR Filter for High Resolution DEM Generation From TanDEM-X Interferograms. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
107. | Gerald Baier, Cristian Rossi, Marie Lachaise, Xiao Xiang Zhu, Richard Bamler (2017). High-Resolution DEM Generation by Nonlocal Filtering of TanDEM-X Interferograms. In 10th International Workshop on Advances in the Science and Applications of SAR Interferometry and Sentinel-1 In SAR. |
108. | Hossein Bagheri, Michael Schmitt, Xiao Xiang Zhu (2017). Fusion of TanDEM-X and Cartosat-1 DEMs Using TV-norm Regularization and ANN-predicted Weights. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
109. | Hossein Bagheri, Michael Schmitt, Xiao Xiang Zhu (2017). Fusion of TanDEM-X and Cartosat-1 DEMs using TV-norm Regularization and ANN-predicted Weights. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
110. | Jian Kang, Yuanyuan Wang, Marco Körner, Xiao Xiang Zhu (2017). Improve Multi-baseline InSAR Parameter Retrieval by Semantic Information from Optical Images. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
111. | Jingliang Hu, Lichao Mou, Andreas Schmitt, Xiao Xiang Zhu (2017). FusioNet: A Two-stream Convolutional Neural Network for Urban Scene Classification Using PolSAR and Hyperspectral Data. In 2017 Joint Urban Remote Sensing Event. |
112. | Jingliang Hu, Yuanyuan Wang, Pedram Ghamisi, Xiao Xiang Zhu (2017). Evaluation of Polsar Similarity Measures With Spectral Clustering. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
113. | Jingliang Hu, Yuanyuan Wang, Pedram Ghamisi, Xiao Xiang Zhu (2017). Evaluation of Polsar Similarity Measures With Spectral Clustering. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
114. | Lichao Mou, Michael Schmitt, Yuanyuan Wang, Xiao Xiang Zhu (2017). A CNN for the Identification of Corresponding Patches in SAR and Optical Imagery of Urban Scenes. In 2017 Joint Urban Remote Sensing Event (JURSE). |
115. | Lichao Mou, Michael Schmitt, Yuanyuan Wang, Xiao Xiang Zhu (2017). Identifying Corresponding Patches in SAR and Optical Imagery With a Convolutional Neural Network. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
116. | Lichao Mou, Pedram Ghamisi, Xiao Xiang Zhu (2017). Fully Conv-Deconv Network for Unsupervised Spectral-Spatial Feature Extraction of Hyperspectral Imagery via Residual Learning. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
117. | Marion Heublein, Fadwa Alshawaf, Xiao Xiang Zhu, Stefan Hinz (2017). Robust GNSS and InSAR Tomography of Neutrospheric Refractivity Using a Compressive Sensing Approach. In European Geosciences Union General Assembly. |
118. | Martin Klotz, Michael Wurm, Xiao Xiang Zhu, Hannes Taubenböck (2017). Digital Deserts on the Ground and From Space. In Joint Urban Remote Sensing Event (JURSE). |
119. | Michael Schmitt, Florence Tupin, Xiao Xiang Zhu (2017). Fusion of SAR and Optical Remote Sensing Data - Challenges and Recent Trends. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
120. | Muhammad Shahzad, Michael Maurer, Friedrich Fraundorfer, Yuanyuan Wang, Xiao Xiang Zhu (2017). Buildings Extraction in SAR Images Using Intuitive Deep Learning Approach. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
121. | Pedram Ghamisi, Behnood Rasti, Xiao Xiang Zhu (2017). Feature fusion of hyperspectral and lidar data using extinction profiles and total variation. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
122. | Sina Montazeri, Christoph Gisinger, Xiao Xiang Zhu, Michael Eineder, Richard Bamler (2017). Automatic Positioning of SAR Ground Control Points From Multi-aspect TerraSAR-X Acquisitions. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
123. | Stefan Auer, Michael Schmitt, Peter Reinartz (2017). Automatic Alignment of High Resolution Optical and SAR Images for Urban Areas. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017. |
124. | Yao Sun, Muhammad Shahzad, Xiao Xiang Zhu (2017). Building Height Estimation in Single SAR Image Using OSM Building Footprints. In Joint Urban Remote Sensing Event (JURSE). |
125. | Yuanyuan Wang, Xiao Xiang Zhu (2017). Earth Observation Using SAR and Social Media Images. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. |
126. | Yuanyuan Wang, Xiao Xiang Zhu (2017). Robust blind scatterer separation in multibaseline InSAR. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017, Fort Worth, USA. (link) |
127. | Benjamin Fürsich, Richard Bamler, Sven Augustin, Heinz-Wilhelm Hübers, Xiao Xiang Zhu (2016). Towards Single-pixel FMCW Radar Reconstruction. In 2016 4th International Workshop on Compressed Sensing Theory and its Applications to Radar, Sonar and Remote Sensing (CoSeRa). |
128. | Danfeng Hong, Naoto Yokoya, Xiao Xiang Zhu (2016). Local Manifold Learning With Robust Neighbors Selection for Hyperspectral Dimensionality Reduction. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2016. |
129. | Danfeng Hong, Naoto Yokoya, Xiao Xiang Zhu (2016). The K-LLE Algorithm for Nonlinear Dimensionality Reduction of Large-scale Hyperspectral Data. In 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
130. | Gerald Baier, Xiao Xiang Zhu, Marie Lachaise, Helko Breit, Richard Bamler (2016). Nonlocal InSAR Filtering for DEM Generation and Addressing the Staircasing Effect. In Proceedings of EUSAR 2016: 11th European Conference on Synthetic Aperture Radar. |
131. | Jing Hu, Andreas Schmitt, Xiao Xiang Zhu (2016). Dual-Channel PolSAR Speckle Reduction Using Non-Local Means Filter. In European Conference on Synthetic Aperture Radar. |
132. | Jonathan Cheung-Wai Chan, Naoto Yokoya (2016). Mapping Land Covers of Brussels Capital Region Using Spatially Enhanced Hyperspectral Images. In 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
133. | Lichao Mou, Xiao Xiang Zhu (2016). Spatiotemporal Scene Interpretation of Space Videos Via Deep Neural Network and Tracklet Analysis. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS). |
134. | Naoto Yokoya, Pedram Ghamisi (2016). Land-cover Monitoring Using Time-series Hyperspectral Data via Fractional-order Darwinian Particle Swarm Optimization Segmentation. In 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
135. | Naoto Yokoya, Xiao Xiang Zhu, Antonio Plaza (2016). Graph-regularized Coupled Spectral Unmixing for Multisensor Time-series Analysis. In 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
136. | Pedram Ghamisi, Roberto Souza, Jon A Benediktsson, Xiao Xiang Zhu, Leticia Rittner, Roberto Lotufo (2016). Extended Extinction Profile for the Classification of Hyperspectral Images. In 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
137. | Xiangyin Quan, Bingchen Zhang, Xiao Xiang Zhu, Wen Hong, Yirong Wu (2016). DPCA Imaging from Nonuniform Sampling: an Lq Regularization Based Approach. In European Conference on Synthetic Aperture Radar. |
138. | Claas Grohnfeldt, Tristan Michael Burns, Xiao Xiang Zhu (2015). Dynamic Dictionary Learning Strategies for Sparse Representation Based Hyperspectral Image Enhancement. In 2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
139. | Claas Grohnfeldt, Xiao Xiang Zhu, Richard Bamler (2015). Splitting the Hyperspectral-multispectral Image Fusion Problem Autonomously Into Weighted Pan-sharpening Tasks—The Spectral Grouping Concept. In 2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
140. | Jakub Bieniarz, Daniele Cerra, Xiao Xiang Zhu, Rupert Müller, Peter Reinartz (2015). Hyperspectral Resolution Enhancement Using Multisensor Image Data. In 2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
141. | Jakub Bieniarz, Daniele Cerra, Xiao Xiang Zhu, Rupert Müller, Peter Reinartz (2015). Hyperspectral Resolution Enhancement – Application To Real Image Pair. In Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. |
142. | Michael Schmitt (2015). Three-dimensional Reconstruction of Urban Areas by Multi-aspect TomoSAR Data Fusion. In Joint Urban Remote Sensing Event. |
143. | Muhammad Shahzad, Xiao Xiang Zhu (2015). Detection of Buildings in Spaceborne Tomosar Point Clouds via Hybrid Region Growing and Energy Minimization Technique. In 2015 Joint Urban Remote Sensing Event (JURSE). |
144. | Muhammad Shahzad, Xiao Xiang Zhu (2015). Reconstruction of Building Footprints Using Spaceborne Tomosar Point Clouds. In Proceedings of CMRT15-City Models, Roads and Traffic 2015. |
145. | Nan Ge, Xiao Xiang Zhu (2015). Sparse Reconstruction Automaton for Synthetic Aperture Radar Tomography. In 2015 European Radar Conference (EuRAD). |
146. | Naoto Yokoya, Xiao Xiang Zhu (2015). Graph Regularized Coupled Spectral Unmixing for Change Detection. In 2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
147. | Xiao Xiang Zhu, Nan Ge, Muhammad Shahzad (2015). Exploiting Group Sparsity in SAR Tomography. In 2015 3rd International Workshop on Compressed Sensing Theory and its Applications to Radar, Sonar and Remote Sensing (CoSeRa). |
148. | Xiao Xiang Zhu, Nan Ge, Muhammad Shahzad (2015). Group Sparsity in SAR Tomography-experiments on TanDEM-X Data Stacks. In 2015 16th International Radar Symposium (IRS). |
149. | Yuanyuan Wang, Xiao Xiang Zhu (2015). The Robust InSAR Optimization Framework with Application to Monitoring Cities on Volcanoes. In Joint Urban Remote Sensing Event (JURSE) 2015, Lausanne, Switzerland. (link) |
150. | Xiao Xiang Zhu, Yuanyuan Wang, Muhammad Shahzad, Richard Bamler (2014). Spaceborne TomoSAR and Beyond: From SAR Image Stacks to Objects. In 10th European Conference on Synthetic Aperture Radar 2014. |
151. | Yuanyuan Wang, Xiao Xiang Zhu, Richard Bamler (2014). Robust Covariance Matrix Estimation with Application to Volcano Monitoring using SAR Image Stacks. In 10th European Conference on Synthetic Aperture Radar 2014. |
152. | Claas Grohnfeldt, Xiao Xiang Zhu, Richard Bamler (2014). The J-SparseFI-HM Hyperspectral Resolution Enhancement Method—Now Fully Automated. In 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
153. | Jakub Bieniarz, Esteban Aguilera, Xiao Xiang Zhu, Rupert Müller, Uta Heiden, Peter Reinartz (2014). Spectral-spatial Joint Sparsity Unmixing of Hyperspectral Data Using Overcomplete Dictionaries. In 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
154. | Rui Guo, Xiao Xiang Zhu (2014). High-rise Building Feature Extraction Using High Resolution Spotlight TanDEM-X Data. In EUSAR 2014; 10th European Conference on Synthetic Aperture Radar. |
155. | Xiao Xiang Zhu, Richard Bamler, Marie Lachaise, Fathalrahman Adam, Yilei Shi, Michael Eineder (2014). Improving TanDEM-X DEMs by Non-local InSAR Filtering. In EUSAR 2014; 10th European Conference on Synthetic Aperture Radar. |
156. | Xiao Xiang Zhu, Xiao-Ming Li, Rui Guo (2014). Compressive Sensing for Super-resolving SAR Imaging to Support Target Detection in Coastal Zone. In EUSAR 2014; 10th European Conference on Synthetic Aperture Radar. |
157. | Yuanyuan Wang, Xiao Xiang Zhu, Richard Bamler, Stefan Gernhardt (2013). Towards TerraSAR-X Street View: Creating City Point Cloud from Multi-Aspect Data Stacks. In Joint Urban Remote Sensing Event 2013. |
158. | Jakub Bieniarz, Xiao Xiang Zhu, Rupert Müller, Peter Reinartz (2013). Sparse Spectral Unmixing With Endmember Groups Pre-selection. In 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
159. | Muhammad Shahzad, Xiao Xiang Zhu (2013). Building Facades Reconstruction Using Multi-view Tomosar Point Clouds. In Joint Urban Remote Sensing Event 2013. |
160. | Xiao Xiang Zhu, Claas Grohnfeldt, Richard Bamler (2013). Collabrative Sparse Image Fusion with Application to Pan-sharpening. In 2013 18th International Conference on Digital Signal Processing (DSP). |
161. | Xiao Xiang Zhu, Richard Bamler (2013). Sparse Reconstruction Techniques in Tomographic SAR Inversion. In 21st European Signal Processing Conference (EUSIPCO 2013). |
162. | Xiao Xiang Zhu, Yuanyuan Wang, Stefan Gernhardt, Richard Bamler (2013). Tomo-GENESIS: DLR's Tomographic SAR Processing System. In Joint Urban Remote Sensing Event 2013. |
163. | Xiao Xiang Zhu, Yuanyuan Wang, Richard Bamler (2012). Integration of Tomographic SAR Inversion and PSI for Operational Use. In 9th European Conference on Synthetic Aperture Radar, 2012. |
164. | Jakub Bieniarz, Rupert Müller, Xiao Xiang Zhu, Peter Reinartz (2012). On the Use of Overcomplete Dictionaries for Spectral Unmixing. In 2012 4th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). |
165. | Xiao Xiang Zhu, Muhammad Shahzad, Richard Bamler (2012). From TomoSAR Point Clouds to Objects: Facade Reconstruction. In 2012 Tyrrhenian Workshop on Advances in Radar and Remote Sensing (TyWRRS). |
166. | Xiao Xiang Zhu, Richard Bamler (2012). Super-resolution of Sparse Reconstruction for Tomographic SAR Imaging-demonstration With Real Data. In EUSAR 2012; 9th European Conference on Synthetic Aperture Radar. |
167. | Xiao Xiang Zhu, Sofya Spiridonova, Richard Bamler (2012). A Pan-sharpening Algorithm Based on Joint Sparsity. In 2012 Tyrrhenian Workshop on Advances in Radar and Remote Sensing (TyWRRS). |
168. | Yuanyuan Wang, Xiao Xiang Zhu, Richard Bamler (2011). Advanced Coherence Stacking Technique Using High Resolution TerraSAR-X Spotlight Data. In Joint Urban Remote Sensing Event 2011. |
169. | Gianfranco Fornaro, Antonio Pauciullo, Diego Reale, Xiao Xiang Zhu, Richard Bamler (2011). Peculiarities of Urban Area Analysis With Very High Resolution Interferometric SAR Data. In 2011 Joint Urban Remote Sensing Event. |
170. | Gianfranco Fornaro, Diego Reale, Antonio Pauciullo, Xiao Xiang Zhu, Richard Bamler, Francesco Soldovieri (2011). Monitoring of Individual Ground Structures with Very High-Resolution Satellite Synthetic Aperture Radar: Results with the TerraSAR-X System. In European Geosciences Union General Assembly 2011. |
171. | Xiao Xiang Zhu, Richard Bamler (2011). A Fundamental Bound for Super-resolution - With Application to 3D SAR Imaging. In 2011 Joint Urban Remote Sensing Event. |
172. | Xiao Xiang Zhu, Richard Bamler (2011). Sparse Reconstrcution Techniques for SAR Tomography. In 2011 17th International Conference on Digital Signal Processing (DSP). |
173. | Xiao Xiang Zhu, Richard Bamler (2010). Super-resolution for 4-D SAR Tomography via Compressive Sensing. In 8th European Conference on Synthetic Aperture Radar. |
174. | Nico Adam, Xiao Xiang Zhu, Richard Bamler (2009). Coherent Stacking with TerraSAR-X Imagery in Urban Areas. In 2009 Joint Urban Remote Sensing Event. |
175. | Stefan Auer, Xiao Xiang Zhu, Stefan Hinz, Richard Bamler (2009). Ray Tracing and SAR-tomography for 3D Analysis of Microwave Scattering at Man-made Objects. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 38(Part 3), pp. W4. |
176. | Xiao Xiang Zhu, Nico Adam, Ramon Brcic, Richard Bamler (2009). Space-borne High Resolution SAR Tomography: Experiments in Urban Environment Using TS-X Data. In 2009 Joint Urban Remote Sensing Event. |
Other Conference Papers
1. | Zhongyang Hu, Yao Sun, Peter Kuipers Munneke, Stef Lhermitte, Xiao Xiang Zhu (To Appear). Towards a spatially transferable super resolution model for downscaling Antarctic surface melt. In NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning. (link) |
2. | Samyo Rode-Hasinger, Anna Kruspe, Xiao Xiang Zhu (2022). True or False? Detecting False Information on Social Media Using Graph Neural Networks. In Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022). |
3. | Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu (2021). Towards the design of calibrated AutoML algorithms for Classification in Earth Observation. In Space and Artificial Intelligence. |
4. | Conrad M Albrecht, Chenying Liu, Yi Wang, Levente J Klein, Xiao Xiang Zhu (2022). Rule-Based, Noisy Labels for Overhead Imagery Segmentation. In 2022 ESA Living Planet Symposium. (link) |
5. | Levente J Klein, Conrad M Albrecht, Fernando Marianno (2022). Carbon Sequestration and Urban Heat Island Mitigation by Urban Forests. In 2022 ESA Living Planet Symposium. (link) |
6. | Yi Wang, Nassim Ait Ali Braham, Conrad M Albrecht, Lichao Mou, Xiao Xiang Zhu (2022). From Natural Images to Spaceborne Imagery: An Empirical Study of Self-supervised Learning for Earth Observation. In 2022 ESA Living Planet Symposium. (link) |
7. | Ziqi Gu, Patrick Ebel, Qiangqiang Yuan, Michael Schmitt, Xiao Xiang Zhu (2022). Explicit Haze & Cloud Removal for Global Land Cover Classification. In MultiEarth 2022 – Multimodal Learning for Earth and Environment Workshop and Challenge. |
8. | Teo Beker, Homa Ansari, Sina Montazeri, Qiang Song (2022). Detection of Volcanic Deformations in InSAR Velocity Maps - a contribution to TecVolSA project. In EGU General Assembly 2022. (link) |
9. | Martin Hermann, Sudipan Saha, Xiao Xiang Zhu (2022). Few-Shot Filtering for the Detection of Specialized Change in Remote Sensing. In ICLR 2022 Workshop on Practical ML for Developing Countries. |
10. | Conrad Albrecht, Jonas Eberle, Max Schwinger (2022). Open Source Science for Large-Scale data Mining in Earth Observation. In NASA workshop #2: State-of-the-Art in Mission Data Processing Systems. (link) |
11. | Lukas Kondmann, Sebastian Boeck, Rogerio Bonifacio, Xiao Xiang Zhu (2022). Early Crop Type Classification with Satellite Imagery - An Empirical Analysis. In ICLR Practical ML for Developing Countries Workshop 2022. |
12. | Andrés Camero, Jamal Toutouh, Enrique Alba (2021). Reliable and Fast Recurrent Neural Network Architecture Optimization. In XIX Conferencia de la Asociación Española para la Inteligencia Aritificial (CAEPIA 20/21). (pdf) |
13. | Gyri Reiersen, David Dao, Björn Lütjens, Konstantin Klemmer, Xiao Xiang Zhu, Ce Zhang (2021). Tackling the Overestimation of Forest Carbon with Deep Learning and Aerial Imagery. In ICML 2021 Workshop on Tackling Climate Change with Machine Learning. (link) |
14. | Sven Prüfer, Antonius Scherer, Andreas Spörl, Tobias Guggemos, Nikolas Pomplun, Christoph Lenzen (2021). Quantum Shift Scheduling - A Comparison to Classical Approaches. In 12th International Workshop on Planning and Scheduling for Space (IWPSS). (link) |
15. | Anna Kruspe, Matthias Häberle, Eike Jens Hoffmann, Samyo Rode-Hasinger, Karam Abdulahhad, Xiao Xiang Zhu (2021). Changes in Twitter geolocations: Insights and suggestions for future usage. In Workshop on Noisy User-generated Text (W-NUT), Empirical Methods in Natural Language Processing (EMNLP). |
16. | Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu (2021). Lessons from the Clustering Analysis of a Search Space: A Centroid-based Approach to Initializing NAS. In Workshop on Data Science meets Optimization, International Joint Conferences on Artificial Intelligence IJCAI. |
17. | Nouman Ahmed, Sudipan Saha, Maaz Mohsin, Muhammad Shahzad, Xiao Xiang Zhu (2021). Progressive Unsupervised Deep Transfer Learning for Forest Mapping in Satellite Image. In ICCV 2021 workshop on Learning to Understand Aerial Images (LUAI). |
18. | Sudipan Saha, Lichao Mou, Muhammad Shahzad, Xiao Xiang Zhu (2021). Segmentation of VHR EO Images Using Unsupervised Learning. In ECML PKDD 2021 workshop Machine Learning for Earth Observation (MACLEAN). |
19. | Levente Klein, Wang Zhou, Conrad Albrecht (2021). Quantification of Carbon Sequestration in Urban Forests. Tackling Climate Change with Machine Learning Workshop at ICML 2021 (pdf) |
20. | Lukas Kondmann, Xiao Xiang Zhu (2021). Under the Radar–Auditing Fairness in ML for Humanitarian Mapping. In 2nd Data-driven Humanitarian Mapping Workshop at KDD. |
21. | Qian Song, Feng Xu, Xiao Xiang Zhu (2021). Physical-aware Radar Image Synthesis with Projective Network. In 34th General Assembly and Scientific Symposium of the International Union of Radio Science, URSI GASS 2021. |
22. | Andrés Camero, Jamal Toutouh, Hao Wang, Enrique Alba, Thomas Bäck (2021). Neural architecture search using a training-free performance metric. In 2nd AutoAI Workshop, Trustworthy AI - Integrating Learning, Optimisation and Reasoning (TAILOR). (pdf) |
23. | Jakob Gawlikowski, Sudipan Saha, Anna Kruspe, Xiao Xiang Zhu (2021). Out-of-distribution Detection in Satellite Image Classification. In RobustML Workshop, ICLR 2021. (link) |
24. | Jay Nandy, Sudipan Saha, Wynne Hsu, Mong Li Lee, Xiao Xiang Zhu (2021). Covariate Shift Adaptation for Adversarially Robust Classifier. In Workshop on Security and Safety in Machine Learning Systems, ICLR 2021. |
25. | Konstantin Klemmer, Sudipan Saha, Matthias Kahl, Tianlin Xu, Xiao Xiang Zhu (2021). Generative Modeling of Spatio-temporal Weather Patterns With Extreme Event Conditioning. In AI: Modeling Oceans and Climate Change (AIMOCC 2021) Workshop, ICLR 2021. (link) |
26. | Sina Montazeri, Homa Ansari, Francesco De Zan, René Mania, Robert Shau, Teo Beker, Alessandro Parizzi, Mahmud Haghshenas Haghighi, Peter Niemz, Simone Cesca, others (2021). TecVolSA: InSAR and Machine Learning for Surface Displacement Monitoring in South America. In EGU General Assembly Conference Abstracts. |
27. | Mrinalini Kochupillai (2021). Creating a Digital Marketplace for Agrobiodiversity and Plant Genetic Sequence Data: Legal and Ethical Considerations of an AI and Blockchain Based Solution. In Towards Responsible Plant Data Linkage: Global Challenges for Food Security and Governance, Alan Turing Instutute and University of Exceter. |
28. | Lukas Kondmann, Matthias Haeberle, Xiao Xiang Zhu (2020). Combining Twitter and Earth Observation Data for Local Poverty Mapping. In NeuRIPS Machine Learning for the Developing World Workshop. |
29. | Anna Kruspe, Matthias Häberle, Iona Kuhn, Xiao Xiang Zhu (2020). Cross-language Sentiment Analysis of European Twitter Messages During the COVID-19 Pandemic. In Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020. (link) |
30. | Jianzhe Lin, Lichao Mou, Tianze Yu, Xiao Xiang Zhu, Z. Jane Wang (2020). Dual Adversarial Network for Unsupervised Ground/Satellite-to-Aerial Scene Adaptation. In ACM International Conference on Multimedia. |
31. | Lukas Kondmann, Xiao Xiang Zhu (2020). Measuring Changes in Poverty with Deep Learning and Satellite Images. In 1st Practical ML for Developing Countries Workshop at ICLR. |
32. | Danfeng Hong, Xiao Xiang Zhu (2019). Learning to Align Multi-modal Remotely Sensed Data with a Joint Graph Structure. In ESA Living Planet Symposium. |
33. | Eike Jens Hoffmann, Martin Werner, Xiao Xiang Zhu (2019). Quality Assessment of Semantic Tags in OpenStreetMap. In 11th International Symposium on Digital Earth. |
34. | Xiao Xiang Zhu, Chunping Qiu, Jingliang Hu, Yilei Shi, Lichao Mou, Michael Schmitt, Yuanyuan Wang (2019). Deep Learning for Global Local Climate Zones Classification. In ESA Living Planet Symposium. |
35. | Yuxing Xie, Jing Yao, Xiao Xiang Zhu, Peter Reinartz (2019). Deep Learning-based Point Cloud Classification on Multiple Airborne LiDAR Dataset. In International Workshop Point Cloud Processing. |
36. | Yuanyuan Wang, Jian Kang, Xiao Xiang Zhu (2018). Fusing Spaceborne SAR Interferometry and Street View Images for 4D Urban Modeling. In 21st International Conference on Information Fusion 2018. |
37. | Chunping Qiu, Michael Schmitt, Lichao Mou, Xiao Xiang Zhu (2018). Urban Local Climate Zone Classification with a Residual Convolutional Neural Network and Multi-Seasonal Sentinel-2 Images. In 10th IAPR Workshop on Pattern Recognition in Remote Sensing. |
38. | Hossein Bagheri, Michael Schmitt, Xiao Xiang Zhu (2018). Exploring the Applicability of Semi-global Matching for SAR-optical Stereogrammetry of Urban Scenes. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
39. | Jingliang Hu, Danfeng Hong, Xiao Xiang Zhu (2018). MAPPER Regularized Semi-supervised Manifold Alignment for the Fusion of Simulated EnMAP Image and Sentinel-1 Dual-Pol Data. In 10th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. |
40. | Michael Schmitt, Lloyd Haydn Hughes, Marco Körner, Xiao Xiang Zhu (2018). Colorizing Sentinel-1 SAR images using a variational autoencoder conditioned on Sentinel-2 imagery. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
41. | Stefan Auer, Michael Schmitt, Peter Reinartz (2018). Object-related Alignment of High-Resolution Optical and SAR Images. In 21st International Conference on Information Fusion. |
42. | Xiao Xiang Zhu (2018). AI4EO – Successful Stories and Open Issues. In ESA Phi Week. |
43. | Xiao Xiang Zhu (2018). Data Science in Earth Observation. In ESA Phi Week. |
44. | Hossein Bagheri, Michael Schmitt, Xiao Xiang Zhu (2017). Uncertainty Assessment and Weight Map Generation for Efficient Fusion of TanDEM-X and Cartosat-1 DEMs. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
45. | Michael Eineder, Christoph Gisinger, Ulrich Balss, Xiao Ying Cong, Sina Montazeri, Stefan Hackel, Fernando Rodriguez Gonzalez, Hartmut Runge (2017). SAR Imaging Geodesy – Recent Results for TerraSAR-X and for Sentinel-1. In FRINGE 2017. |
46. | Sina Montazeri, Xiao Xiang Zhu, Christoph Gisinger, Fernando Rodriguez Gonzalez, Michael Eineder, Richard Bamler (2017). Towards Absolute Positioning of InSAR Point Clouds. In FRINGE 2017. |
47. | Sina Montazeri, Xiao Xiang Zhu, Christoph Gisinger, Michael Eineder, Richard Bamler (2017). Towards the Integration of Automatically Generated SAR Ground Control Points into InSAR Stacking Techniques. In Fringe workshop. |
48. | Yuanyuan Wang, Xiao Xiang Zhu, Sina Montazeri, Jian Kang, Lichao Mou, Michael Schmitt (2017). Potential of the “SARptical” System. In FRINGE 2017, Helsinki, Finland. (link) |
49. | Christoph Gisinger, Sina Montazeri, Ulrich Balss, Xiao Ying Cong, Stefan Hackel, Xiao Xiang Zhu, Roland Pail, Michael Eineder (2016). Applying Geodetic SAR with TerraSAR-X and TanDEM-X. In TerraSAR-X/TanDEM-X Science Team Meeting 2016. |
50. | Gerald Baier, Xiao Xiang Zhu (2016). GPU-based Nonlocal Filtering for Large Scale SAR Processing. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2016. |
51. | Hui Bi, Bingchen Zhang, Xiao Xiang Zhu, Wen Hong, Yirong Wu (2016). CFAR Detection for the Complex Approximated Message Passing Reconstructed SAR Image. In International Workshop on Compressed Sensing Theory and its Applications to Radar, Sonar and Remote Sensing (CoSeRa). |
52. | Jian Kang, Yuanyuan Wang, Marco Köner, Xiao Xiang Zhu (2016). Object-based InSAR Deformation Reconstruction with Application to Bridge Monitoring. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2016, Beijing, China. |
53. | Jingliang Hu, Pedram Ghamisi, Andreas Schmitt, Xiao Xiang Zhu (2016). Object Based Fusion of Polarimetric SAR and Hyperspectral Imaging for Land Use Classification. In 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. |
54. | Marion Heublein, Stefan Hinz, Xiao Xiang Zhu (2016). Compressive Sensing for Tomographic Reconstruction of Wet Refractivity Using GNSS and InSAR Observations. In ESA Living Planet Symposium. |
55. | Michael Schmitt, Muhammad Shahzad, Xiao Xiang Zhu (2016). Forest Remote Sensing on the Individual Tree Level by Airborne Millimeter Wave SAR. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2016. |
56. | Michael Schmitt, Xiao Xiang Zhu (2016). On the Challenges in Stereogrammetric Fusion of SAR and Optical Imagery for Urban Areas. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
57. | Sina Montazeri, Xiao Xiang Zhu, Ulrich Balss, Christoph Gisinger, Yuanyuan Wang, Michael Eineder, Richard Bamler (2016). SAR Ground Control Point Identification with the Aid of High Resolution Optical Data. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2016. |
58. | Yuanyuan Wang, Xiao Xiang Zhu (2016). Robust Multibaseline InSAR Optimization. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2016. |
59. | Yuanyuan Wang, Xiao Xiang Zhu (2015). Semantic Interpretation of InSAR Point Cloud. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015, Milan, Italy. (link) |
60. | Claas Grohnfeldt, Xiao Xiang Zhu (2015). Towards a Combined Sparse Representation and Unmixing Based Hybrid Hyperspectral Resolution Enhancement Method. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015. |
61. | Gerald Baier, Xiao Xiang Zhu (2015). Region Growing Based Nonlocal Filtering for InSAR. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015. |
62. | Jakub Bieniarz, Rupert Müller, Xiao Xiang Zhu, Peter Reinartz (2015). Sparse Pixel-wise Spectral Unmixing—Which Algorithm to Use and How to Improve the Results. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015. |
63. | Marion Heublein, Xiao Xiang Zhu, Fadwa Alshawaf, Michael Mayer, Richard Bamler, Stefan Hinz (2015). Compressive Sensing for Neutrospheric Water Vapor Tomography Using GNSS and InSAR Observations. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015. |
64. | Michael Schmitt, Lingyun Wei, Xiao Xiang Zhu (2015). Automatic Coastline Detection in Non-locally Filtered TanDEM-X Data. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015. |
65. | Muhammad Shahzad, Michael Schmitt, Xiao Xiang Zhu (2015). Segmentation and Crown Parameter Extraction of Individual Trees in an Airborne TomoSAR Point Cloud. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. |
66. | Nan Ge, Xiao Xiang Zhu (2015). SAR Tomography Using Staring and High-resolution Spotlight Data From the TanDEM-X Pursuit Monostatic Mode. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015. |
67. | Sina Montazeri, Xiao Xiang Zhu, Michael Eineder, Ramon Hanssen, Richard Bamler (2015). Deformation Monitoring of Urban Infrastructure by Tomographic SAR Using Multi-view TerraSAR-X Data Stacks. In FRINGE 2015. |
68. | Xiao Xiang Zhu, Richard Bamler (2015). Exploiting Sparsity in Remote Sensing and Earth Observation: Theory, Applications and Future Trends. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015. |
69. | Yuanyuan Wang, Xiao Xiang Zhu (2015). InSAR Forensics: Tracing InSAR Scatterers in High Resolution Optical Image. In FRINGE 2015. |
70. | Yuanyuan Wang, Xiao Xiang Zhu (2015). Semantic Interpretation of InSAR Estimates Using Optical Images with Application to Urban Infrastructure Monitoring. In ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, La Grande Motte, France. |
71. | Claas Grohnfeldt, Xiao Xiang Zhu, Richard Bamler (2014). Performance Assessment of the State-of-the-art Hyperspectra Image Enhancement Methods. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2014. |
72. | Jakub Bieniarz, Rupert Müller, Xiao Xiang Zhu, Peter Reinartz (2014). Hyperspectral image resolution enhancement based on joint sparsity spectral unmixing. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2014. |
73. | Muhammad Shahzad, Xiao Xiang Zhu (2014). Automatic Large Area Reconstruction of Building Facades From Spaceborne TomoSAR Point Clouds. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2014. |
74. | Muhammad Shahzad, Xiao Xiang Zhu (2014). Reconstructing 2-D/3-D Building Shapes From Spaceborne Tomographic SAR Point Clouds. In 3rd ISPRS Commission Symposium on Photogrammetric Computer Vision. |
75. | Xiao Xiang Zhu, Marie Lachaise, Fathalrahman Adam, Yilei Shi, Michael Eineder, Richard Bamler (2014). Beyond the 12m TanDEM-X DEM. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2014. |
76. | Xiao Xiang Zhu, Richard Bamler (2014). Exploiting Sparsity in Remote Sensing for Earth Observation. In SIAM conference on Image Science (IS14). |
77. | Xiao Xiang Zhu, Sina Montazeri, Christoph Gisinger, Ramon Hanssen, Richard Bamler (2014). Geodetic TomoSAR - Fusion of SAR Imaging Geodesy and TomoSAR for 3D Absolute Scatterer Positioning. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2014. |
78. | Xiao Xiang Zhu, Richard Bamler, Yuanyuan Wang, Muhammad Shahzad (2013). Tomographic Urban Imaging Using TerraSAR-X High Resolution Spotlight Data Stacks. In ESA Living Planet Symposium 2013, Edinburgh, United Kingdom. (link) |
79. | Yuanyuan Wang, Xiao Xiang Zhu (2013). Feature-Based Fusion of TomoSAR Point Clouds from Multiview TerraSAR-X Data Stacks. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2013. |
80. | Claas Grohnfeldt, Xiao Xiang Zhu, Richard Bamler (2013). Jointly Sparse Fusion of Hyperspectral and Multispectral Imagery. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2013. |
81. | Jakub Bieniarz, Esteban Aguilera, Rupert Müller, X Zhu, Peter Reinartz (2013). Application of Distributed Compressive Sensing in Hyperspectral Image Unmixing. In Proceedings of the 8th EARSeL Imaging Spectrometry Workshop, Nantes, France. |
82. | L Ding, Xiao Xiang Zhu, L Meng (2013). Scientific Visualization for 4-D Building Deformation Data Analysis. In Proceedings of the 26th International Cartographic Conference, Dresden, Germany. |
83. | Muhammad Shahzad, Xiao Xiang Zhu (2013). Reconstruction of Building Facades Using Spaceborne Multiview TomoSAR Point Clouds. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2013. |
84. | Xiao Xiang Zhu (2013). Exploiting Sparsity in Remote Sensing for Earth Observation. In International Conference Signal Processing, Optimization and Compressed Sensing (SPOC) 2013. |
85. | Xiao Xiang Zhu, Claas Grohnfeldt, Richard Bamler (2013). Collaborative Sparse Reconstruction for Pan-sharpening. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2013. |
86. | Xiao Xiang Zhu, Marie Lachaise, Fathalrahman Adam, Richard Bamler (2013). Towards 6 m TanDEM-X DEM: Non-local Methods for InSAR Filtering. In 4th TanDEM-X Scientific Meeting Final Program and Abstracts. |
87. | Xiao Xiang Zhu, Muhammad Shahzad, Yuanyuan Wang, Richard Bamler (2013). Tomographic Urban Mapping and Object Reconstruction Using TerraSAR-X Spotlight Data Stacks. In 5th TerraSAR-X Scientific Meeting, Oberpfaffenhofen, Germany. (link) |
88. | Yuanyuan Wang, Xiao Xiang Zhu, Yilei Shi, Richard Bamler (2012). Operational TomoSAR Processing Using TerraSAR-X High Resolution Spotlight Stacks From Multiple View Angles. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2012. (link) |
89. | Cristian Rossi, Thomas Fritz, Michael Eineder, Esra Erten, Xiao Xiang Zhu, Stefan Gernhardt (2012). Towards an Urban DEM Generation With Satellite SAR Interferometry. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXiX International Society for Photogrammetry and Remote Sensing Congress, 39(B7), pp. 73–78. |
90. | Jakub Bieniarz, Rupert Müller, Xiao Xiang Zhu, Peter Reinartz (2012). Sparse Approximation, Coherence and Use of Derivatives in Hyperspectral Unmixing. In Third Annual Hyperspectral Imaging Conference. |
91. | Muhammad Shahzad, Xiao Xiang Zhu, Richard Bamler (2012). Facade Structure Reconstruction Using Spaceborne TomoSAR Point Clouds. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2012. |
92. | Xiao Xiang Zhu, Richard Bamler (2012). Sparse Reconstruction Applied to Tomographic SAR Inversion. In SIAM Conference on Image Science (IS12). |
93. | Xiao Xiang Zhu, Richard Bamler (2012). Sparse Tomographic SAR Reconstruction From Mixed TerraSAR-X/TanDEM-X Data Stacks. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2012. |
94. | Xiao Xiang Zhu, Richard Bamler (2012). Tomographic SAR Inversion from Mixed Repeat-and- Single-pass Data Stacks – The TerraSAR-X/Tandem-X Case. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXII International Society for Photogrammetry and Remote Sensing Congress, 39(B7). |
95. | Yuanyuan Wang, Xiao Xiang Zhu, Richard Bamler (2011). Optimal Estimation of Distributed Scatterer Phase History Parameters from Meter-resolution SAR Data. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2011. |
96. | Richard Bamler, Xiao Xiang Zhu (2011). A Bound for Super-Resolution Power of Compressive Sensing Imaging Systems. In SIAM conference on optimization. |
97. | Xiao Xiang Zhu, Richard Bamler (2011). 3-D and 4-D Tomographic Urban Mapping using TerraSAR-X Spotlight Data. In 4th TerraSAR-X Scientific Meeting. |
98. | Xiao Xiang Zhu, Richard Bamler (2011). Multi-component Nonlinear Motion Estimation in Differential SAR Tomography - The Time-warp Method. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2011. |
99. | Xiao Xiang Zhu, Richard Bamler (2011). The SL 1MMER Algorithm for Spectral Estimation —with Application to Tomographic SAR Inversion. SIAM conference on optimization 2011 |
100. | Xiao Xiang Zhu, Richard Bamler (2011). Tomographic SAR Inversion Via Sparse Reconstruction. In Signal Processing with Adaptive Sparse Structured Representations SPARS 11. |
101. | Xiao Xiang Zhu, Richard Bamler (2011). Within the Resolution Cell: Super-resolution in Tomographic SAR Imaging. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2011. |
102. | Xiao Xiang Zhu, Xuan Wang, Richard Bamler (2011). Compressive Sensing for Image Fusion - With Application to Pan-sharpening. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2011. |
103. | Xuan Wang, Xiao Xiang Zhu, Richard Bamler, Aliaksei Makarau (2011). Compressive Sensing for PAN-Sharpening. In International Symposium on Image and Data Fusion (ISIDF), IEEE Xplore, Tengchong, China. |
104. | Diego Reale, Gianfranco Fornaro, Antonio Pauciullo, Xiao Xiang Zhu, Nico Adam, Richard Bamler (2010). Advanced Techniques and New High Resolution SAR Sensors for Monitoring Urban Areas. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2010. |
105. | Xiao Xiang Zhu, Richard Bamler (2010). Compressive Sensing for High Resolution Differential SAR Tomography - The SL1MMER Algorithm. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2010. |
106. | Xiao Xiang Zhu, Richard Bamler (2010). Space-Time Tomographic Infrastructure Reconstruction via Compressive Sensing Using TerraSAR-X High Resolution Spotlight Data. In Proceedings of International Workshop Spatial Information Technologies for Monitoring the Deformation of Large-Scale Man-made Linear Features. |
107. | Nico Adam, Xiao Xiang Zhu, Christian Minet, Werner Liebhart, Michael Eineder, Richard Bamler (2009). Techniques and Examples for the 3D Reconstruction of Complex Scattering Situations Using TerraSAR-X. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2009. |
108. | Stefan Auer, Xiao Xiang Zhu, Stefan Hinz, Richard Bamler (2009). 3D Analysis of Scattering Effects Based on Ray Tracing Techniques. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2009. |
109. | Xiao Xiang Zhu, Nico Adam, Richard Bamler (2009). First Demonstration of Space-borne High Resolution SAR Tomography in Urban Environment Using TerraSAR-X Data. In CEOS SAR Workshop on Calibration and Validation 2008. |
110. | Xiao Xiang Zhu, Nico Adam, Richard Bamler (2009). Space-borne High Resolution Tomographic Interferometry. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2009. |
111. | Xiao Xiang Zhu, Richard Bamler (2009). Very High Resolution SAR Tomography via Compressive Sensing. In FRINGE 2009. |
Thesis and Patents
1. | Chunping Qiu (2020). Deep Learning for Multi-Scale Mapping of Urban Land Cover from Space. Doctoral Thesis. Technical University of Munich. (link) |
2. | Lloyd H Hughes (2020). Deep Learning for Matching High-Resolution SAR and Optical Imagery. Doctoral Thesis. Technical University of Munich. (link) |
3. | Nan Ge (2020). Sparse Recovery in Spaceborne SAR Tomography. Doctoral Thesis. Technical University of Munich. (link) |
4. | Danfeng Hong (2019). Regression-Induced Representation Learning and Its Optimizer: A Novel Paradigm to Revisit Hyperspectral Imagery Analysis. Doctoral Thesis. Technical University of Munich. (link) |
5. | Jian Kang (2019). Object-based Multibaseline SAR Interferometry. Doctoral Thesis. Technical University of Munich. (link) |
6. | Michael Schmitt (2019). Data Fusion for SAR and Optical Remote Sensing. Habilitation. Technical University of Munich. |
7. | Sina Montazeri (2019). Geodetic Synthetic Aperture Radar Interferometry. Doctoral Thesis. Technical University of Munich. (link) |
8. | Gerald Baier (2018). Nonlocal Filtering for Single- and Multibaseline SAR Interferometry. Doctoral Thesis. Technical University of Munich. (pdf) |
9. | Claas Hendrik Grohnfeldt (2017). Multi-sensor Data Fusion for Multi- and Hyperspectral Resolution Enhancement Based on Sparse Representations. Doctoral Thesis. Technical University of Munich. (link) |
10. | Muhammad Shahzad (2016). From TomoSAR Point Cloud to Objects. Doctoral Thesis. Technical University of Munich. (link) |
11. | Yuanyuan Wang (2015). Advances in Meter-resolution Multipass Synthetic Aperture Radar Interferometry. Doctoral Thesis. Technical University of Munich. (link) |
12. | Xiao Xiang Zhu (2013). Modern Signal Processing in Remote Sensing. Habilitation. Technical University of Munich. |
13. | Xiao Xiang Zhu, Richard Bamler, Xuan Wang (2012). Verfahren zur Rechnergestuetzten Verarbeitung Digitalisierter Bilder (Compressive Sensing for Image Pan Sharpening). |
14. | Xiao Xiang Zhu (2011). Very High Resolution Tomographic SAR Inversion for Urban Infrastructure Monitoring - A Sparse and Nonlinear Tour, Deutsche Geodätische Kommission, 2011. (pdf) |
Past Featured Papers
Assessing the Macro-scale Patterns of Urban Tree Canopy Cover in Brazil Using High-resolution Remote Sensing Images
Urban trees typically provide many environmental, social, and economic urban ecosystem services to people living in urban areas. Along streets, they mitigate air and noise pollution and urban forests provide a habitat for wildlife, such as insects, birds, and serrated animals, while also providing a cool living environment by mitigating urban heat. Therefore, studying patterns of UTC cover is important to promote environmental justice and support urban sustainable development in Brazil. To better understand the UTC cover patterns in Brazil, this study creates UTC products for 472 cities in Brazil based on high-resolution satellite images and an advanced CNN segmentation model and then conducts a comprehensive assessment of macro-scale patterns of UTC cover in Brazil by taking tree canopy coverage, human exposure, and determines into account. The results revealed that the UTC cover of Brazilian cities is spatially heterogeneous, ranging from 5% to 34%. There was a difference in UTC coverage between the old and new urban areas, with the average largest difference near 5%. More than 76% urban population exposure to UTC coverage of 0~0.2. Most cities have a relatively high inequality in human exposure to urban tree-covered spaces, especially in northeastern and southeastern Brazil. Results from the geographical detector models show climatic factors play a major role in determining the UTC cover patterns in Brazilian cities, followed by socioeconomic, geographical, soil, and urbanization factors. This study suggests the Brazilian government pay more attention to greening renovation projects in old urban areas and formulate effective urban tree irrigation policies for cities with limited autumn and winter rainfall. The study also suggests follow-up research on UTC cover patterns that consider the effects of race, urban history, city structure, land use, and local government policy factors to further support the goals of sustainable development in Brazilian cities.
Reference: Jianhua Guo, Zhiheng Liu, Xiao Xiang Zhu (2023). Assessing the Macro-scale Patterns of Urban Tree Canopy Cover in Brazil Using High-resolution Remote Sensing Images. Sustainable Cities and Society, 100, 105003.(link)
HTC-DC Net: Monocular Height Estimation from Single Remote Sensing Images
Three-dimensional geoinformation is of great significance for understanding the living environment; however, 3-D perception from remote sensing data, especially on a large scale, is restricted, mainly due to the high costs of 3-D sensors such as light detection and ranging (LiDAR). To tackle this problem, we propose a method for monocular height estimation from optical imagery, which is currently one of the richest sources of remote sensing data. As an ill-posed problem, monocular height estimation requires well-designed networks for enhanced representations to improve the performance. Moreover, the distribution of height values is long-tailed with the low-height pixels, e.g., the background (BG), as the head, and thus, trained networks are usually biased and tend to underestimate building heights. To solve the problems, instead of formalizing the problem as a regression task, we propose HTC-DC Net following the classification–regression paradigm, with the head-tail cut (HTC) and the distribution-based constraints (DCs) as the main contributions. HTC-DC Net is composed of the backbone network as the feature extractor, the HTC-AdaBins module, and the hybrid regression process. The HTC-AdaBins module serves as the classification phase to determine bins adaptive to each input image. It is equipped with a vision transformer (ViT) encoder to incorporate local context with holistic information and involves an HTC to address the long-tailed problem in monocular height estimation for balancing the performances of foreground (FG) and BG pixels. The hybrid regression process does the regression via the smoothing of bins from the classification phase, which is trained via DCs. The proposed network is tested on three datasets of different resolutions, namely ISPRS Vaihingen (0.09 m), Data Fusion Contest 19 (DFC19) (1.3 m), and Global Building Height (GBH) (3 m). The experimental results show the superiority of the proposed network over existing methods by large margins. Extensive ablation studies demonstrate the effectiveness of each design component
Reference: Sining Chen, Yilei Shi, Zhitong Xiong, Xiao Xiang Zhu (2023). HTC-DC Net: Monocular Height Estimation from Single Remote Sensing Images. IEEE Transactions Geoscience and Remote Sensing, 61 (2023): 1-18. (link)
From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data.
Visual question answering (VQA) for remote sensing scene has great potential in intelligent human-computer interaction system. Although VQA in computer vision has been widely researched, VQA for remote sensing data (RSVQA) is still in its infancy. There are two characteristics that need to be specially considered for the RSVQA task. 1) No object annotations are available in RSVQA datasets, which makes it difficult for models to exploit informative region representation; 2) There are questions with clearly different difficulty levels for each image in the RSVQA task. Directly training a model with questions in a random order may confuse the model and limit the performance. To address these two problems, in this paper, a multi-level visual feature learning method is proposed to jointly extract language-guided holistic and regional image features. Besides, a self-paced curriculum learning (SPCL)-based VQA model is developed to train networks with samples in an easy-to-hard way. To be more specific, a language-guided SPCL method with a soft weighting strategy is explored in this work. The proposed model is evaluated on three public datasets, and extensive experimental results show that the proposed RSVQA framework can achieve promising performance.
Reference: Zhenghang Yuan, Lichao Mou, Qi Wang, Xiao Xiang Zhu (2022). From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data. IEEE Transactions on Geoscience and Remote Sensing, 60 (2022): 1-11. (link)
γ-Net: Superresolving SAR Tomographic Inversion via Deep Learning
Synthetic aperture radar tomography (TomoSAR) has been extensively employed in 3-D reconstruction in dense urban areas using high-resolution SAR acquisitions. Compressive sensing (CS)-based algorithms are generally considered as the state-of-the art in super-resolving TomoSAR, in particular in the single look case. This superior performance comes at the cost of extra computational burdens, because of the sparse reconstruction, which cannot be solved analytically, and we need to employ computationally expensive iterative solvers. In this article, we propose a novel deep learning-based superresolving TomoSAR inversion approach, γ -Net, to tackle this challenge. γ -Net adopts advanced complex-valued learned iterative shrinkage thresholding algorithm (CV-LISTA) to mimic the iterative optimization step in sparse reconstruction. Simulations show the height estimate from a well-trained γ -Net approaches the Cramér-Rao lower bound (CRLB) while improving the computational efficiency by one to two orders of magnitude comparing to the first-order CS-based methods. It also shows no degradation in the super-resolution power comparing to the state-of-the-art second-order TomoSAR solvers, which are much more computationally expensive than the first-order methods. Specifically, γ -Net reaches more than 90% detection rate in moderate super-resolving cases at 25 measurements at 6 dB SNR. Moreover, simulation at limited baselines demonstrates that the proposed algorithm outperforms the second-order CS-based method by a fair margin. Test on real TanDEM-X data with just
six interferograms also shows high-quality 3-D reconstruction with high-density detected double scatterers.
Reference: Kun Qian, Yuanyuan Wang, Yilei Shi, Xiao Xiang Zhu (2022). γ-Net: Superresolving SAR Tomographic Inversion via Deep Learning. IEEE Transactions on Geoscience and Remote Sensing, 60, pp. 1–16. (link)
The urban morphology on our planet – Global perspectives from space
Urbanization is the second-largest megatrend, right after climate change. Accurate measurements of urban morphological and demographic figures are at the core of many international endeavours to address issues of urbanization, such as the United Nations’ call for “Sustainable Cities and Communities”. In many countries – particularly developing countries –, however, this database does not yet exist. Here, we demonstrate a novel deep learning and big data analytics approach to fuse freely available global radar and multi-spectral satellite data, acquired by the Sentinel-1 and Sentinel-2 satellites. Via this approach, we created the first-ever global and quality controlled urban local climate zones classification covering all cities across the globe with a population greater than 300,000 and made it available to the community. Statistical analysis of the data quantifies a global inequality problem: approximately 40% of the area defined as compact or light/large low-rise accommodates about 60% of the total population, whereas approximately 30% of the area defined as sparsely built accommodates only about 10% of the total population. Beyond, patterns of urban morphology were discovered from the global classification map, confirming a morphologic relationship to the geographical region and related cultural heritage. We expect the open access of our dataset to encourage research on the global change process of urbanization, as a multidisciplinary crowd of researchers will use this baseline for spatial perspective in their work. In addition, it can serve as a unique dataset for stakeholders such as the United Nations to improve their spatial assessments of urbanization.
Reference: Xiao Xiang Zhu, Chunping Qiu, Jingliang Hu, Yilei Shi, Yuanyuan Wang, Michael Schmitt, Hannes Taubenböck (2021). The Urban Morphology on Our Planet - Global Perspectives from Space. Remote Sensing of Environment, 269, p.112794. [code] [paper]
DENETHOR: The DynamicEarthNET dataset for Harmonized, inter-Operable, analysis-Ready, daily crop monitoring from space
Recent advances in remote sensing products allow near-real time monitoring of the Earth’s surface. Despite increasing availability of near-daily time-series of satellite imagery, there has been little exploration of deep learning methods to utilize the unprecedented temporal density of observations. This is particularly interesting in crop monitoring where time-series remote sensing data has been used frequently to exploit phenological differences of crops in the growing cycle over time. In this work, we present DENETHOR: The DynamicEarthNET dataset for Harmonized, inter-Operabel, analysis-Ready, daily crop monitoring from space. Our dataset contains daily, analysis-ready Planet Fusion data together with Sentinel-1 radar and Sentinel-2 optical time-series for crop type classification in Northern Germany. Our baseline experiments underline that incorporating the available spatial and temporal information fully may not be straightforward and could require the design of tailored architectures. The dataset presents two main challenges to the community: Exploit the temporal dimension for improved crop classification and ensure that models can handle a domain shift to a different year. Finally, the dataset is being used in the #AI4FoodSecurity challenge, organized by Planet, DLR, TUM and Radiant Earth, and hosted by ESA. Participate until December 19!
Reference: Lukas Kondmann, Aysim Toker, Marc Rußwurm, Andrés Camero, Devis Peressuti, Grega Milcinski, Pierre-Philippe Mathieu, Nicolas Longépé, Timothy Davis, Giovanni Marchisio, Laura Leal-Taixé, Xiao Xiang Zhu (2021). DENETHOR: The DynamicEarthNET dataset for Harmonized, inter-Operable, analysis-Ready, daily crop monitoring from space. In Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track. [code][paper]
HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline.
Deep learning-based coastline detection algorithms have begun to outperform traditional statistical methods. However, these models are usually trained for as single-purpose: segment land and water, or delineate the coastline. On the other hand, a human annotator usually perform both tasks simultaneously. Considering this task duality, and inspired by the main building blocks of a semantic segmentation framework (UNet), and the edge detection framework (HED), we devised a new model that naturally combines both tasks: the HED-UNet. Training is made efficient by employing deep supervision on side predictions at multiple resolutions, and a hierarchical attention mechanism is introduced to adaptively merge these multiscale predictions into the final model output. The advantages of this approach are shown on a dataset of Sentinel-1 imagery covering parts of the Antarctic coast, where coastline detection is notoriously difficult.
Reference: Konrad Heidler, Lichao Mou, Celia Amélie Baumhoer, Andreas Dietz, Xiao Xiang Zhu (2021). HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline. IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2021.3064606. [code] [paper]
MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images
Aerial scene recognition is a fundamental research problem in interpreting high-resolution aerial imagery. Over the past few years, most studies focus on classifying an image into one scene category, while in real-world scenarios, it is more often that a single image contains multiple scenes. Therefore, in this paper, we investigate a more practical yet underexplored task---multi-scene recognition in single images. To this end, we create a large-scale dataset, called MultiScene, composed of 100,000 unconstrained high-resolution aerial images. Considering that manually labeling such images is extremely arduous, we resort to low-cost annotations from crowdsourcing platforms, e.g., OpenStreetMap (OSM). However, OSM data might suffer from incompleteness and incorrectness, which introduce noise into image labels. To address this issue, we visually inspect 14,000 images and correct their scene labels, yielding a subset of cleanly-annotated images, named MultiScene-Clean. With it, we can develop and evaluate deep networks for multi-scene recognition using clean data. Moreover, we provide crowdsourced annotations of all images for the purpose of studying network learning with noisy labels. We conduct experiments with extensive baseline models on both MultiScene-Clean and MultiScene to offer benchmarks for multi-scene recognition in single images and learning from noisy labels for this task, respectively. To facilitate progress, we make our dataset and trained models available online.
Reference: Yuansheng Hua, Lichao Mou, Pu Jin, Xiao Xiang Zhu (2021). MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images. IEEE Transactions on Geoscience and Remote Sensing, in press. [code] [paper]
Deep Learning Meets SAR: Concepts, Models, Pitfalls, and Perspectives
Deep learning in remote sensing has become an international hype, but it is mostly limited to the evaluation of optical data. Although deep learning has been introduced in Synthetic Aperture Radar (SAR) data processing, despite successful first attempts, its huge potential remains locked. Here, we provide an introduction to the most relevant deep learning models and concepts, point out possible pitfalls by analyzing special characteristics of SAR data, review the state-of-the-art of deep learning applied to SAR in depth, summarize available benchmarks, and recommend some important future research directions. With this effort, we hope to stimulate more research in this interesting yet under-exploited research field and to pave the way for use of deep learning in big SAR data processing workflows.
Reference: Xiao Xiang Zhu, Sina Montazeri, Mohsin Ali, Yuansheng Hua, Yuanyuan Wang, Lichao Mou, Yilei Shi, Feng Xu, Richard Bamler (2021). Deep Learning Meets SAR: Concepts, Models, Pitfalls, and Perspectives. IEEE Geoscience and Remote Sensing Magazine, doi: 10.1109/MGRS.2020.3046356. [paper]