Title :
Moving object segmentation for video surveillance and conferencing applications
Author :
Alsaqre, Falah E. ; Baozong, Yuan
Author_Institution :
Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
Abstract :
Video surveillance and conferencing systems have an impressive spread both for their practical application and interest as research issue. The common approach used in such systems consists of a good segmentation of moving objects. This paper presents an algorithm for segmenting and extracting moving objects suitable for surveillance and video conferencing applications, where a still background frame can be captured beforehand. Since edge detection is often used to extract accurate boundaries of the objects in the scene, the first step in our algorithm is accomplished by combining two kinds of edge points which are detected from the frame difference and the background subtraction. After removing edge points that belong to the background frame, the resulting moving edge map is fed to the object extracting step. A fundamental task in this step is to declare the candidates of the moving object, followed by applying morphological closing and opening operations. The algorithm is implemented on real video sequences and good segmentation performance is achieved.
Keywords :
edge detection; image motion analysis; image segmentation; mathematical morphology; real-time systems; surveillance; teleconferencing; video signal processing; conferencing application; edge detection; edge point; morphological closing; morphological opening; moving edge map; moving object extraction; moving object segmentation; real-time processing; still background frame; video surveillance; Change detection algorithms; Computerized monitoring; Image edge detection; Image segmentation; Object detection; Object segmentation; Shape; Video sequences; Video surveillance; Videoconference;
Conference_Titel :
Communication Technology Proceedings, 2003. ICCT 2003. International Conference on
Print_ISBN :
7-5635-0686-1
DOI :
10.1109/ICCT.2003.1209889