25 September 2003 Identification of occlusion regions based on background rebuilding for automatic video object segmentation
Author Affiliations +
Proceedings Volume 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition; (2003) https://doi.org/10.1117/12.539913
Event: Third International Symposium on Multispectral Image Processing and Pattern Recognition, 2003, Beijing, China
Abstract
In video sequences, object movement causes regions occlusion (to-be-covered or uncovered), which seriously decreases the accuracy of object segmentation. This paper presents a novel video object segmentation algorithm that can identify the occlusion regions. The background rebuilding technique is used to construct a reliable background image from the accumulated frame difference information. THe intial moving object segmentation is finished by the difference between the background image and the current frame, and the occlusion regions are detected. Then, the initial result is spatially segmented into homogeneous regions, and a method based on region labeling distinguishes between moving object and background regions. Experimental results for several MPEG-4 test sequences demonstrate the effectiveness of the proposed approach.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hongqiang Bao, Hongqiang Bao, Zhaoyang Zhang, Zhaoyang Zhang, } "Identification of occlusion regions based on background rebuilding for automatic video object segmentation", Proc. SPIE 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition, (25 September 2003); doi: 10.1117/12.539913; https://doi.org/10.1117/12.539913
PROCEEDINGS
4 PAGES


SHARE
RELATED CONTENT


Back to Top