Title :
Double change detection method for moving-object segmentation based on clustering
Author :
Liu, Haihua ; Chen, Xinhao ; Chen, Yaguang ; Xie, Changsheng
Author_Institution :
Coll. of Electron. & Inf. Eng., South-Central Univ. for Nationalities, Wuhan
Abstract :
In this paper, an efficient moving object segmentation algorithm in the wavelet domain is proposed using three successive frames. The change detection method, which employs fuzzy C-means clustering technique to classify motion features of four wavelet sub-bands, is used twice to separate significant change pixels in the wavelet domain from the background. After applying the intersect operation, the change detection masks are obtained in wavelet domain. Finally, further object shape information and accurate extraction of the moving object is obtained in original resolution according to current object edge map. The experimental results demonstrate the algorithm effective
Keywords :
edge detection; image motion analysis; image segmentation; pattern clustering; video signal processing; wavelet transforms; change detection masks; double change detection; fuzzy C-means clustering; moving-object segmentation; object edge map; object shape information; wavelet domain; Change detection algorithms; Data mining; Educational institutions; Layout; Motion detection; Motion estimation; Object detection; Shape; Video sequences; Wavelet domain;
Conference_Titel :
Circuits and Systems, 2006. ISCAS 2006. Proceedings. 2006 IEEE International Symposium on
Conference_Location :
Island of Kos
Print_ISBN :
0-7803-9389-9
DOI :
10.1109/ISCAS.2006.1693761