Title :
Moving object segmentation and tracking in video
Author :
Li, Chun-Ming ; Li, Yu-Shan ; Zhuang, Qing-De ; Li, Qiu-Ming ; Wu, Rui-Hong ; Li, Yang
Author_Institution :
Inst. of Electron. CAD, Xidian Univ., Xi´´an, China
Abstract :
Moving object segmentation and tracking in video is an important task not only in computer motion detection and tracking, but also in MPEG-4. A new moving object segmentation and tracking method based on the improved PCA is presented in this paper. Firstly, the improved PCA is used to segment the moving object in the original image sequence. In this step, three frames are enough for the segmentation of rigid and non-rigid moving object from background. Secondly, tracking is performed by shifting the 3 frame window along the image sequence and repeating the first step in each window.
Keywords :
image motion analysis; image segmentation; image sequences; object detection; principal component analysis; tracking; video coding; MPEG-4; PCA; computer motion detection; image sequence; moving video object segmentation; moving video object tracking; Covariance matrix; Eigenvalues and eigenfunctions; Feature extraction; Image segmentation; Image sequences; Independent component analysis; Matrix decomposition; Object segmentation; Principal component analysis; Tracking; PCA; Segmentation; moving object; tracking;
Conference_Titel :
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on
Conference_Location :
Guangzhou, China
Print_ISBN :
0-7803-9091-1
DOI :
10.1109/ICMLC.2005.1527816
