Speaker: Zongxu Pan

Affiliation: Aerospace Information Research Institute, Chinese Academy of Sciences

Academic title: Associate Professor

Honorary title: IEEE senior member

Abstract:

Benefiting from the ability of working all day and all weather, synthetic aperture radar (SAR) has been widely used in many fields. As one of the most important applications of SAR, ship detection in SAR images always attracts a lot of attentions, and with the developing of deep learning techniques, advanced SAR ship detector can achieve satisfactory results under common cases. However, SAR ship detection still faces the challenges of detecting densely arranged ships in port area and defocusing ships in high seas. What’s more, it is difficult to distinguish false targets from the defocusing ships in multi-channel SAR systems, since they have similar appearances in the amplitude image. Aiming to mitigate the above-mentioned issues, the detector with rotatable bounding boxes, the detector with visual and Doppler features, and the detector based on the sub-aperture feature extraction proposed by our research group will be introduced in this talk.

Biography:

Zongxu Pan received the B.E. degree from Harbin Institute of Technology in 2010, and the Ph.D. degree from Tsinghua University in 2015. He is now an Associate Professor in Aeraspace Information Research Institute, Chinese Academy of Sciences. His research interest is remote sensing target detection and recognition. He has published over 80 papers in journals and conference proceedings. He severs as a Guest Editor of Remote Sensing and a Review Editor of Frontiers in Remote Sensing. He was selected as the Best Reviewer of IEEE GEOSCIENCE AND REMOTE SENSING LETTERS in 2022.