Segmentation: We focus on a sub-class of problem in semantic/instance/panoptic segmentation, with specific focus on remote sensing images such as airborne and satellite images. It takes images and an input, and output for each pixel, its land or functional categories.
Change detection: Taking bitemporal or multitemporal images or 3D data as input, we aim to detect pixel-level or object-level differences of significance, such as manmade or those due to natural disasters.
Radiometric Calibration: Relative and absolute radiometric calibration between multi-sensor and multi-seasonal remote sensing images.
Domain Adaptation (DA): We focus on developing domain adaptation method to tackle generalization problems in deep learning / machine learning on remote sensing images due to the diverse geographical location and different sensor responses.
Super Resolution: We focus on developing methods to super-resolve low resolution remote sensing images to obtain high resolution high frequency images.
Applications
- Land use land cover mapping
- National level mapping and updating
- Change detection
- Land/forest/earth surface monitoring
Key problems / Challenges
- Weak and lack of high-quality labels
- Lack of high-resolution and high temporal data.
- Large domain differences of 1) different sensors, 2) geographical regions; 3) seasons
- Multi-modality data such as microwave, optical
- Data registration and alignment
Publications
Review
Hessah Albanwan^, Rongjun Qin, Jung-Kuan Liu (2024). Remote Sensing-Based 3D Assessment of Landslides: A Review of the Data, Methods, and Applications. Remote Sensing . https://doi.org/10.3390/rs16030455. (link)
Review
Shengxi Gui^, Shuang Song^, Rongjun Qin, Yang Tang^ (2024). Remote Sensing Object Detection in the Deep Learning Era – A Review. Remote Sensing . https://doi.org/10.3390/rs16020327. (link).
Classification
Rongjun Qin, Tao Liu (2022). A Review of Landcover Classification with Very-high Resolution Remotely Sensed Optical Images – Analysis Unit, Model Scalability and Transferability. Remote Sensing, 14(3), 646. (link, arxiv)(Invited paper)
Classification
Ying Zuo, C.K. Shum, Rongjun Qin, Yuanyuan Jia, Guixiang Zhang^ and Shengxi Gui^. Pan-India Land Use Land Cover Deep Learning Aided Classification Using NICFI Products. American Geophysical Union Fall Meeting, Chicago, USA, December 16, 2022. (link)
Classification
Caleb Robinson, Kolya Malkin, Nebojsa Jojic, Huijun Chen^, Rongjun Qin, Changlin Xiao^, Michael Schmitt, Pedram Ghamisi, Ronny Hänsch, Naoto Yokoya (2021). Global Land Cover Mapping with Weak Supervision: Outcome of the 2020 IEEE GRSS Data Fusion Contest. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 3185-3199.(link).
Line segment matching
Min Chen, Shaohua Yan, Rongjun Qin, Xi Zhao, Tong Fang, Qing Zhu, Xuming Ge. Hierarchical Line Segment Matching for Wide-baseline Images via Exploiting Viewpoint Robust Local Structure and Geometric Constraints. ISPRS Journal of Photogrammetry and Remote Sensing, 181 (2021): 48-66. (link).
Urban modeling
Shengxi, Gui^, Rongjun Qin. Automated LoD-2 Model Reconstruction from Very-High-Resolution Satellite-derived Digital Surface Model and Orthophoto. ISPRS Journal of Photogrammetry and Remote Sensing. 181 (2021): 1-19. (arxiv, link, Github,video) – (Featured Article of the month, Editor’s Choice Article)
Classification
Liu, Wei, Fulin Su, Xinfei Jin, Hongxu Li, and Rongjun Qin. “Bispace Domain Adaptation Network for Remotely Sensed Semantic Segmentation.” IEEE Transactions on Geoscience and Remote Sensing (2020), vol. 60, pp. 1-11. (link, Github)
Classification
Xiao, Changlin^, Rongjun Qin, and Xiao Ling^ (2020). Urban Land-cover Classification Using Side-View Information from Oblique Images. Remote Sensing 12(3): 390.(link)
Classification
Wei Liu^, Rongjun Qin (2020). A multi-kernel domain adaptation method for unsupervised transfer learning on cross-source and cross-region remote sensing data classification. IEEE Transactions on Geosciences and Remote Sensing. PP(99):1-11 (pdf, link, Github)
Classification
Hessah Albanwan^, Rongjun Qin, Xiaohu Lu^, Mao Li^, Desheng Liu, Jean-Michel Guldmann (2020). 3D Iterative spatiotemporal Filtering for Classification of Multi-temporal Satellite Dataset. Photogrammetric Engineering and Remote Sensing. 2020, 86(1): 23-31.(link, pdf)
Classification
Changlin Xiao^, Rongjun Qin, Xiao Ling^ and Hanning Yuan (2019), Urban Land-Cover Classification with Facade Feature from Oblique Images. 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, July 28- August 2.(pp. 5944-5947). (link)
Classification
Wei Liu^ and Rongjun Qin (2019), Unsupervised transfer learning using for multi-model remote sensing data classification. 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, July 28- August 2. (pp. 636-639) (link)
Classification
Wei Liu^, Rongjun Qin, Fulin Su (2019) Weakly supervised classification of time-series of very high resolution remote sensing images by transfer learning. Remote Sensing Letters. 2019, 10(7): 689-698. (link)
Classification
Wei Liu^, Rongjun Qin , Fulin Su and Kun Hu^ (2018). An Unsupervised Domain Adaptation Method for Multi-Modal Remote Sensing Image Classification. CPGIS 2018. Kunming, China, June 28-30, 2018. (pp. 1-5) (Best student paper 3rd place) (link)
Classification
Qian Zhang, Rongjun Qin, X. Huang, Yong Fang and Liang Liu (2015). Classification of Ultra-High Resolution Orthophotos Combined with DSM Using a Dual Morphological Top Hat Profile. Remote Sensing 7 (12), 16422-16440. (pdf, link)
Classification
Rongjun Qin (2015). A Mean Shift Vector based Shape Feature for Classification of High Spatial Resolution Remotely Sensed Imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 5 (8), 1974-1985. (pdf, link)