Graph decomposition for multi-person tracking, pose estimation and motion segmentation
发表日期：2016-12-14 点击击数: 27
Understanding people in images and videos is a problem studied intensively in computer vision. While continuous progress has been made, occlusions, cluttered background, complex poses and large variety of appearance remain challenging, especially for crowded scenes. In this talk, I will explore the algorithms and tools that enable computer to interpret people’s position, motion and articulated poses in the real-world challenging images and videos. More specifically, I will discuss an optimization problem whose feasible solutions define a decomposition of a given graph. I will highlight the applications of this problem in computer vision, which range from multi-person tracking to motion segmentation. I will also cover an extended optimization problem whose feasible solutions define a decomposition of a given graph and a labeling of its nodes with the application on multi-person pose estimation.
Siyu Tang is a PhD student at Max Planck Institute for Informatics in Saarbruecken,
Germany, under the supervision of Prof. Bernt Schiele. From January 2017, she
will join Max Planck Institute for Intelligence Systems as a postdoctoral researcher, under the supervision of Prof. Michael Black. She received a master degree in RWTH Aachen University and a bachelor degree in Zhejiang University, both in computer science. She was a research intern at National Institute of Informatics. She received a best paper award at BMVC’12 for her work: Detection and Tracking of Occluded People. She is the winner of the Multi-Object Tracking Challenge in ECCV’16.