Speaker: Yongchan Gao

Affiliation: Xidian University

Academic title: Professor

Honorary title: "Future Women Scientist Program" of China Association for Science and Technology

Abstract:

Constant false alarm (CFAR) target detection is one of the important tasks of radar operation. Typical constant false alarm target detection improves the data-dependent covariance matrix estimation, and the detection performance degrades sharply in non-homogeneous clutter environments. In view of the above problem, starting from the non-homogeneous training samples, combined with the idea of deep learning, this report designs a signal detection method driven by data model cooperation. A convolutional neural network based on residual network is constructed to determine the distribution of clutter and carry out CFAR target detection accordingly.  Numerical results with simulated and measured data verify the effectiveness of the proposed method, in order to provide theoretical and methodological guidance for intelligent radar signal processing.

Biography:

Yongchan Gao, received the B.S. degree in electronic engineering from Xidian University in 2009 and the Ph.D. degree in signal and information processing from the National Laboratory of Radar Signal Processing, Xidian University in 2015. She is currently an Professor of Xi'an University, mainly engaged in the research of adaptive detection of signals，clutter suppression for new radar systems and array signal processing. She published more than 30 papers, won the "Future Women Scientist Program" of China Association for Science and Technology, the excellent doctoral dissertation nomination award of the Chinese Society of Electronic Education.