时间: 2015年12月14日（周一）上午9:30

地点: 校本部东区翔英大楼808室

讲座: 基于改进的RGB-D场景流估计的遮挡和大尺度位移处理

演讲者: Associate Prof. Jian Zhang，悉尼科技大学（UTS）

讲座摘要：

The accuracy of scene flow is restricted by several challenges such as occlusion and large displacement motion. When occlusion happens, the positions inside the occluded regions lose their corresponding counterparts in preceding and succeeding frames. Large displacement motion will increase the complexity of motion modelling and computation. Moreover, occlusion and large displacement motion are highly related problems in scene flow estimation, e.g. large displacement motion often leads to considerably occluded regions in the scene. An improved dense scene flow method based on RGB-D data is proposed in this paper. To handle occlusion, we model the occlusion status for each point in our problem formulation, and jointly estimate the scene flow and occluded regions. To deal with large displacement motion, we employ an over-parameterized scene flow representation to model both the rotation and translation components of the scene flow, since large displacement motion cannot be well approximated using translational motion only. Furthermore, we employ a two-stage optimization procedure for this over-parameterized scene flow representation. In the first stage, we propose a new RGB-D PatchMatch method, which is mainly applied in the RGB-D image space to reduce the computational complexity introduced by the large displacement motion. According to the quantitative evaluation based on the Middlebury dataset, our method outperforms other published methods. The improved performance is also comprehensively confirmed on the real data acquired by Kinect sensor.

演讲者简介：

Jian Zhang received the B.Sc. degree from East Normal University, China in 1982; the M.Sc. degree in Computer Science from Flinders University, Australia in 1994; and the Ph.D. degree in Electrical Engineering from the University of New South Wales, Australia in 1999. From 1997 to 2003, A/Prof. Zhang was with the Visual Information Processing Laboratory, Motorola Labs, Sydney, as a Senior Research Engineer, and later became a Principal Research Engineer and a Foundation Manager with the Visual Communications Research Team. From 2004 to July 2011, he was a Principal Researcher and a Project Leader with National ICT Australia, Sydney, and a Conjoint Associate Professor with the School of Computer Science and Engineering, UNSW. He is currently an Associate Professor with the Advanced Analytics Institute, School of software, Faculty of Engineering and Information Technology, University of Technology, Sydney. A/Prof Zhang’s research interests include multimedia signal processing, computer vision, pattern recognition, visual information mining, human-computer interaction and intelligent video surveillance systems. Apart from more than 100 paper publications, book chapters, patents and technical reports from his research output, he was co-author of more than ten patents filed in US, UK, Japan and Australia including six issued US patents. Dr. Zhang is an IEEE Senior Member, Associated Editors for IEEE Transactions on Circuits and Systems for Video Technology and EURASIP Journal on Image and Video Processing. As a general co-chair, he has hosted the 2012 IEEE International Conference on Multimedia and Expo in Melbourne, Australia. As a Technical Program Co-chair, he chaired the IEEE International Workshop on Multimedia Signal Processing (MMSP) 2008 and IEEE Visual Communications and Image Processing (VCIP), 2014.