Abstract
In this paper, a self-adapting segmentation algorithm for low-quality video Image based on camera information is present in detail. An adaptive threshold value method is used to extract the goal information. Combining features of the goal and video background, an adaptive segmentation algorithm based on hue histogram and saturation histogram is proposed, which can adapt the changing environmental conditions. The experiments have demonstrated the good performance of the self-adapting segmentation algorithm.
Publisher
Trans Tech Publications, Ltd.
Reference7 articles.
1. Wall R J．The Gray level history for threshold boundary determination in image processing to the scene segmentation problem in human chromosome analysis. Los Angeles, USA: University of California, (1974).
2. Tremeau A, Borel N. A region growing and merging algorithm to color segmentation. Pattern Recognition, 1997, 30(7): 1191-1204.
3. Shen X. Segmentation of 2D and 3D image through a hierarchical clustering based on region modeling. Pattern Recognition, 1998, 31(9): 1295-1309.
4. Hager G D. A brief reading guide to dynamic vision. The Johns Hopkings University. http: /www. cs. jhu. ed/~hager, 2001, 1-8.
5. Bhanu B, Peng J. Adaptive integrated image segmentation and object recognition. IEEE transactions on system, man, and cybernetics, part C, applications and reviews, 2000, 30(4): 427-441.