Title :
Motion Vector Based Moving Object Detection and Tracking in the MPEG Compressed Domain
Author :
Yokoyama, Takanori ; Iwasaki, Toshiki ; Watanabe, Toshinori
Author_Institution :
Grad. Sch. of Inf. Syst., Univ. of Electro-Commun., Chofu
Abstract :
As MPEG standards prevail, the opportunities to handle MPEG compressed videos increase, and the video indexing and management that can directly process the compressed videos become important. MPEG video coding standards use motion compensation to compress video data, and the motion compensation generates motion vectors that contain motion information similar to optical flows between regions in different frames. Although motion vectors are useful for video analysis, they are not always generated along moving objects, and it is difficult to analyze moving objects using only these vectors. In this paper, we propose a moving object detection and tracking method in the MPEG compressed domain for video surveillance and management. In our method, we introduce images that record moving regions and accumulate unmoving regions in which the moving objects are expected to exist after the current frame. By utilizing these images, we can detect and track moving objects using only motion vectors even if the motion vectors of moving objects become zero vectors due to their behaviors and are lost due to their picture type. We demonstrate the effectiveness of the proposed method through several experiments using actual videos acquired by an MPEG video camera.
Keywords :
image sequences; motion compensation; object detection; video coding; video surveillance; MPEG compressed domain; MPEG compressed videos; MPEG standards; MPEG video camera; MPEG video coding standards; motion compensation; motion vector; moving object detection; object tracking; optical flows; video analysis; video indexing; video management; video surveillance; Image coding; Image motion analysis; Indexing; MPEG standards; Motion analysis; Motion compensation; Object detection; Tracking; Transform coding; Video coding; MPEG video; compressed domain; motion vector; moving object detection; moving object tracking;
Conference_Titel :
Content-Based Multimedia Indexing, 2009. CBMI '09. Seventh International Workshop on
Conference_Location :
Chania
Print_ISBN :
978-1-4244-4265-2
Electronic_ISBN :
978-0-7695-3662-0
DOI :
10.1109/CBMI.2009.33