时间:7月1日 10:00-11:00    

地点:教十八 304室

Dr. Jonathan Wu

Professor and Canada Research Chair (Tier 1)
Department of Electrical and Computer Engineering
University of Windsor, Canada

3D Object Reconstruction using

Multi-View Calibrated Images

There are many applications such as obstacle avoidance in robotics, 3D modeling in inverse engineering, assisted living, security and surveillance which need to localize, recognize, reconstruct and track the 3D objects. The desired quality of the resulted 3D shape of the object and the acceptable time performance of the reconstruction process depends only on the applications. Some applications need to reconstruct a coarse shape of the object in acceptable time. Multi-view based vision network is one of the solutions for all of these applications. Two models are proposed in this work, one is a visual hull model and another one is a 3D object reconstruction model. The main contribution of the proposed visual hull model is to provide bounding surfaces over the bounding edges, which results a complete triangular surface mesh. Moreover, the proposed visual hull model can be computed over the camera networks distributedly. The second model is a depth map based 3D object reconstruction model which results a watertight triangular surface mesh. The proposed model produces the result with acceptable accuracy as well as high completeness, only using stereo matching and triangulation.

Brief Biography:   Dr.  Jonathan Wu

Dr. Jonathan Wu is a Professor in the Department of Electrical and Computer Engineering at the University of Windsor, Canada. He is also the founding director of the Computer Vision and Sensing Systems Laboratory at the University of Windsor. Prior to joining the University in 2005, Dr. Wu was leading the Computer Vision and Sensors Research Division at the National Research Council of Canada (NRC). Dr. Wu holds the Tier 1 Canada Research Chair (CRC) in Automotive Sensors and Sensing Systems. He has published one book in the area of 3D vision and more than 200 peer-reviewed papers (including 70 journal publications) in areas of computer vision, image processing, multimedia information processing, and intelligent systems. Dr. Wu is an Associate Editor for IEEE Transaction on Systems, Man, and Cybernetics (part A). Dr. Wu has served on the Technical Program Committees and International Advisory Committees for many prestigious conferences including IEEE Conference on Computer Vision and Pattern Recognition (CVPR).