DocumentCode :
3606891
Title :
Video Object Segmentation Via Dense Trajectories
Author :
Lin Chen ; Jianbing Shen ; Wenguan Wang ; Bingbing Ni
Author_Institution :
Sch. of Comput. Sci., Beijing Inst. of Technol., Beijing, China
Volume :
17
Issue :
12
fYear :
2015
Firstpage :
2225
Lastpage :
2234
Abstract :
In this paper, we propose a novel approach to segment moving object in video by utilizing improved point trajectories . First, point trajectories are densely sampled from video and tracked through optical flow, which provides information of long-term temporal interactions among objects in the video sequence . Second, a novel affinity measurement method considering both global and local information of point trajectories is proposed to cluster trajectories into groups. Finally, we propose a new graph-based segmentation method which adopts both local and global motion information encoded by the tracked dense point trajectories. The proposed approach achieves good performance on trajectory clustering, and it also obtains accurate video object segmentation results on both the Moseg dataset and our new dataset containing more challenging videos.
Keywords :
graph theory; image motion analysis; image segmentation; image sequences; object detection; video signal processing; affinity measurement method; graph-based segmentation method; motion information; optical flow; point trajectory; video object segmentation; video sequence; Clustering algorithms; Motion segmentation; Object segmentation; Tracking; Trajectory; Video sequences; Dense trajectories; energy optimization; global motion information; point trajectory clustering; video object segmentation;
fLanguage :
English
Journal_Title :
Multimedia, IEEE Transactions on
Publisher :
ieee
ISSN :
1520-9210
Type :
jour
DOI :
10.1109/TMM.2015.2481711
Filename :
7274745
Link To Document :
بازگشت