Title :
A fast and robust moving object segmentation in video sequences
Author :
Changick Kim ; Jenq-Neng Hwang
Author_Institution :
Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
Abstract :
The new video coding standard MPEG-4 is enabling content-based functionalities as well as high coding efficiency considering shape information of moving objects. A novel algorithm for segmentation of moving objects in video sequences and VOP (video object planes) extraction is presented. This algorithm begins with a robust double edge map from the difference between two successive frames. After removing edges which belong to previous frame, the edge map, named ME (moving edge) is used to extract VOP. The proposed algorithm is evaluated for MPEG-4 test sequences and produces promising results.
Keywords :
feature extraction; image segmentation; image sequences; video coding; MPEG-4; object segmentation; segmentation; video coding; video object planes; video sequences; Data mining; Image edge detection; MPEG 4 Standard; Noise level; Noise robustness; Object segmentation; Shape; Video coding; Video compression; Video sequences;
Conference_Titel :
Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-5467-2
DOI :
10.1109/ICIP.1999.822869
