Abstract: In this talk, I will first to provide a basic introduction of autonomous driving. Then I will present some research work on long range 3D sensing using monocular cameras. High-speed autonomous driving demands 3D perception beyond 200m, which is the typical maximum range for either Lidar or Radar. I will present a new method that combines traditional 3D vision with scene-parsing method to enable accurate vehicle range sensing at over 1000m. A ultra-long range 3D dataset will also be introduced.
Personal introduction: Dr. Yang Ruigang, tenured professor of the Department of Computer Science, University of Kentucky, PhD supervisor and senior member of IEEE. He is winner of the National Science Foundation (NSF) Talent Award. Serving as Deputy Editor-in-Chief of IEEE PAMI Journal, Special Editor and Editorial Board Member of IEE Computer Vision Journal, he is responsible for undertaking 35 scientific research projects of the United States NSF, Department of Homeland Security, Department of Defense, and the Navy (7 of which are NSF). He has been engaged in an aggregate scientific research funding tallying 18 million US dollars. He has published over 100 papers and has been cited by Google Scholar 10,000 times with an H factor reaching 58. With 12 US patents, Professor Yang Ruigang's main research direction is on computer graphics and computer vision, notably 3D reconstruction and 3D data analysis. He used to be chief scientist of 3D vision and director of robotics and autonomous driving laboratory of Baidu Research Institute. His incumbent title is CTO of Incept Technology.