【電機系書報討論演講訊息】

書報討論網址：http://www.ee.nthu.edu.tw/~ee591000/

演講公告網址：/p/403-1175-2629-1.php

題   目：2D and 3D Models for Object and Scene Understanding

講   員：孫民 博士

時       間：2012年12月28日(星期五) 上午10時至11時

地       點：台達館215教室
 

Abstract:

In this talk, we introduce novel 2D and 3D models for object and scene understanding from images. This is an extremely challenging problem in computer vision. Objects change their appearance because of intra-class variability, view point transformations and their inherent deformable nature. Understanding scenes is also challenging. Scenes may comprise large number of objects whose relationships are class specific and depend on the view point and 3D scene geometry. First, we propose object models that are capable of detecting generic rigid objects and simultaneously extracting their viewpoints and 3D shape. The ability of these models to jointly capture appearance and shape in a truly 3D sense makes them robust to intra-class variability, view point changes and occlusions. Second, we have focused on designing models that can effectively capture the appearance and shape variability of deformable objects such as humans or animals. Most importantly, we propose algorithmic solutions that are capable of “taming” the intrinsic complexity of the pose estimation problem while guaranteeing the optimality of the solution. Finally, we have proposed models that can effectively capture the interplay among objects and scene elements so as to simultaneously recognize the scene, detect objects and segment regions accurately and efficiently. At the end of the talk, we briefly mention our future plans on i) enabling visual algorithms to utilize large-scale and rich sensory data, and ii) exploring novel computational paradigms that are capable of mimicking a human’s ability to understand images at different levels of granularity.

Bio: 

Min Sun graduated from National Chiao Tung University, Taiwan in 2003 with an B.Sc. degree in Electrical Engineering. He received his M.Sc. degree from Stanford University in Electrical Engineering in 2007 and graduated with a Ph.D. degree from the University of Michigan at Ann Arbor in 2012. His research interests include 3D object recognition, human pose estimation, scene understanding, and machine learning. He has won the best paper award in 3DRR'09 and is a recipient of W. Michael Blumenthal Family Fund Fellowship and Taiwan Merit Scholarship.

歡  迎  聽  講