Y.-W. Chen, D.-Y. Chen, and S.-Y. Lee (Taiwan)
Object Segmentation, Object Tracking
. Object segmentation and tracking are crucial steps for video annotations and classifications in various applications of surveillance video. In this paper, we propose automatic object segmentation and object tracking mechanisms to extract object trajectories in MPEG videos. Background-based object segmentation is used for object segmentation in I-frames and motion clustering approach is proposed for object segmentation in P-frames respectively. A GOP-based approach is proposed to improve the reliability of multi-objects tracking, in which spatial and color information are exploited for object matching. The proposed methods are evaluated for several MPEG-7 testing sequences. Experimental results demonstrate good performance and thus show the effectiveness of the proposed schemes.
Important Links:
Go Back
