Biograph: Lan Du received the B.S., M.S. and Ph. D. degrees in electronic engineering from Xidian University, Xi’an, China, in 2001, 2004, and 2007 respectively. From Sep. 2007 to Sep. 2009, she did research work as a Postdoctoral Research Associate in the Department of Electrical and Computer Engineering, Duke University, Durham, NC 27708 USA. She is currently a Professor at National Laboratory of Radar Signal Processing, Xidian University. Her main research interests are in the ﬁelds of statistical signal processing and machine learning with application to radar target recognition. Her doctoral dissertation was granted National Excellent Doctoral Dissertation of PR China in 2009. Her research work is supported by NSFC for Excellent Young Scholars and Chang Jiang Scholars Program for Young Scholars.
Title: SAR Target Detection and Discrimination in Complex Scenes
Abstract: Synthetic aperture radar (SAR) has been widely used in both commercial and military areas, such as urban planning, natural resources monitoring, and military surveillance, due to its ability to form high resolution images with relative invariance to weather and lighting conditions. With these advantages, SAR automatic target recognition (ATR) has also attracted much more attention during the past decades. A typical SAR ATR system often consists of three stages: detection, discrimination, and classification or recognition. This talk will introduce our recent work on SAR target detection and discrimination in complex scenes, mainly with unsupervised, weakly supervised and semi-supervised learning algorithms.