Speaker: Daiyin Zhu

Affiliation: Nanjing University of Aeronautics and Astronautics

Academic title: Professor

Abstract:

The Radar Detection and Imaging Techniques Research Group at NUAA employs the unmanned aerial vehicle (UAV) borne MiniSAR system to carry out full aspect echo collection and image processing for multiple types of representative ground targets. A proprietary SAR database for complex targets is constructed, based on which research on approaches to target recognition based on artificial intelligence is investigated. The SAR images obtained by the UAV-borne NUAA MiniSAR system operating at a high bandwidth of 1.8GHz is advantageous in resolution. Experimental results show that although the classic neural networks such as ResNet-18, AConvNet, DenseNet and VGG offer a near-100% accuracy for the MSTAR 10-target classification problem, the 9-class target classification accuracies provided by these networks for the MiniSAR dataset are all much lower than 90%. Therefore modified network to improve the target recognition results are presented. Since the experiment method employed in this work closely resemble the practical application scenario, the proposed database will be of great reference value to the development of SAR target recognition algorithms for engineering applications.

Biography:

Daiyin Zhu received the B.S. degree from the Southeast University, Nanjing, China, in 1996 and the M.S. and Ph.D. degrees from the Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, China, in 1998 and 2002, respectively, all in electronic engineering. 

From 1998 to 1999, he was a Guest Scientist in the Institute of Radio Frequency Technology, German Aerospace Center (DLR), Oberphaffenhofen, Germany, working in the field of synthetic aperture radar (SAR) interferometry. In 1998, he joined the Department of Electronic Engineering, NUAA, where he has been a Professor since 2008. His current research interests include radar imaging algorithms, SAR/ISAR autofocus techniques, SAR/GMTI, and SAR interferometry. Dr. Zhu has developed algorithms for several operational airborne SAR systems. In 2018, he received the Award of Defense Science & Technology, concerning airborne SAR system design and signal processing.