訊息公告

【網工所論文研討SEMINAR】2018/06/06 _15:30~17:30@ED117,Topic: Deep Visual Learning for Robust Object Detection

Deep Visual Learning for Robust Object Detection

Time2018/06/06  15:30~17:30

PlaceED117

SpeakerProfessor Shang-Hong Lai

Abstract

Object detection is a fundamental problem in computer vision and it is strongly demanded for a number of applications, such as robot or autonomous driving. Deep learning has emerged as a versatile machine learning approach that has been proved to be quite successful for numerous computer vision tasks. In this talk, I will present some of our recent researches on intelligent robot vision based on deep learning techniques. I will focus on the research on robust object detection from images. I will present our recent research to improve the robustness of object detection from the three perspectives: partial occlusion, image distortion, and night-time scenario. We have developed different solution approaches based on deep learning to overcome the above problems for different application scenarios. Some experimental results will be shown to demonstrate the effectiveness of the proposed object detection system.

Speaker Bio

Shang-Hong Lai received the B.S. and M.S. degrees in electrical engineering from National Tsing Hua University, Hsinchu, Taiwan, and the Ph.D. degree from University of Florida, Gainesville. He joined Siemens Corporate Research in Princeton, New Jersey, USA, as a member of technical staff in 1995. Since 1999, he became a faculty member in the Department of Computer Science, National Tsing Hua University, Taiwan, where he is currently a professor and the Chairman in the same department. From 2011 to 2015, Dr. Lai served as the Director of the Computer and Communication Center of National Tsing Hua University.

 

Dr. Lai’s research interests mainly focus on computer vision, image processing, machine learning, and medical image analysis. He has authored more than 200 papers published in refereed international journals and conferences in these areas. In addition, he has been awarded around 30 patents on his researches on computer vision and medical imaging. He has been an area chair or a program committee member for a number of international conferences. He served as the program chair for several conferences, including ACCV’16. Furthermore, Dr. Lai has been an associate editor for several international journals.