14 April 2011
Research Seminar: Multiview Video Segmentation and Tracking
Platform Technologies Research Institute hosted a research seminar presented by Professor King Ngi Ngan, Chair Professor, Department of Electronic Engineering, The Chinese University of Hong Kong on Multiview Video Segmentation and Tracking
Event details
|
Title: |
Research Seminar: Multiview Video Segmentation and Tracking |
|---|---|
|
Person: |
Platform Technologies Research Institute |
|
Date: |
2011-04-19 |
|
Time: |
10:00 – 11:30am |
|
Location: |
RMIT City Campus, Research Lounge, Bld 28, entry via Bld 8, Level 5, opposite RMIT Swanston Library) |
Download the presentation (pdf 1.26) or contact platformtechnologies@rmit.edu.au for the presenter’s contact details.
About the seminar
The presentation will focus on an automatic algorithm to segment multiple objects from multiview video. The Initial Interested Objects (IIOs) are automatically extracted in the key view of the initial frame based on the saliency model. Multiple objects segmentation is decomposed into several sub-segmentation problems, and solved by minimizing the energy function using binary label graph cut. In the proposed novel energy function, the color and depth cues are integrated with the data term, which is then modified with background penalty with occlusion reasoning. In the smoothness term, foreground contrast enhancement is developed to strengthen the moving object’s boundary, and at the same time attenuates the background contrast. To segment the multiview video, the coarse predictions of the other views and the successive frames are projected by pixel-based disparity and motion compensation respectively, which exploit the inherent spatiotemporal consistency. Uncertain band along the object boundary is formed based on activity measure and refined with graph cut, resulting in a more accurate Interested Objects (IOs) layer across all views of the frames. The experiments are implemented on a number of multiview videos with real and complex scenes. Excellent subjective results have demonstrated the robustness and efficiency of the proposed algorithm.
About the presenter
King N. Ngan received the Ph.D. degree in Electrical Engineering from the Loughborough University in U.K. He is currently a chair professor, concurrently serving as Department Head at the Department of Electronic Engineering, Chinese University of Hong Kong. He was previously a full professor at the Nanyang Technological University, Singapore, and the University of Western Australia, Australia. He holds honorary and visiting professorships of numerous universities in China, Australia and South East Asia.
Professor Ngan is an associate editor of the Journal on Visual Communications and Image Representation, as well as an area editor of EURASIP Journal of Signal Processing: Image Communication, and served as an associate editor of IEEE Transactions on Circuits and Systems for Video Technology and Journal of Applied Signal Processing. He chaired a number of prestigious international conferences on video signal processing and communications, and served on the advisory and technical committees of numerous professional organizations. Professor Ngan co-chaired the IEEE International Conference on Image Processing (ICIP) in Hong Kong in September 2010. He has published extensively including 3 authored books, 5 edited volumes, over 300 refereed technical papers, and edited 9 special issues in journals. In addition, he holds 10 patents in the areas of image/video coding and communications.
Professor Ngan is a Fellow of IEEE (U.S.A.), IET (U.K.), and IEAust (Australia), and an IEEE Distinguished Lecturer in 2006-2007.
