Invited Talk: Yan Huang, Southeast University

Special session 12: Artificial Intelligence in Radar Signal Processing

Short Bio: 
Yan Huang received the B.S. degree in electrical engineering, and the Ph. D. degree in signal and information processing, both from Xidian University, Xi’an, China, in 2013 and 2018, respectively. He was studying as a visiting Ph.D. student in Electrical and Computer Engineering department at University of Florida from Sep. 2016 to July 2017, and in Electrical and Systems Engineering department at the Washington University in St. Louis from July 2017 to Aug. 2018. He is currently an assistant professor at the State Key Laboratory of Millimeter Waves, Southeast University. His research interests include machine learning, synthetic aperture radar, image processing, remote sensing.

Title:  Density-Based Vehicle Detection Approach for Automotive Millimeter-Wave Radar

Abstract:
Automotive radars, along with other sensors, generate the backbone of self-driving vehicles. Herein, automotive radars, especially the millimeter-wave (MMW) radar, have already reached a market penetration that leads to tens of million units being used. The MMW radar has been rapidly expanded and developed for the past a few years, and it has found its own way into nearly all car manufacturers’ plans in the world. In this paper, we focus on the classic signal processing problem, vehicle detection, based on the MMW radar. It is a new area for MMW radar signal processing and requires a both effective and efficient solution for practical applications, like the advanced driver assistant system (ADAS). We first generate high-resolution point cloud image based on radar signal processing steps and develop two kinds of density-based approaches for vehicle detection tasks on this point cloud image. The article outlines the processing steps and presents some experimental results.