Title :
Tracking object using improved Hausdorff measure
Author :
Liu, Ke ; Zhang, Xianmin
Author_Institution :
Inst. of Image Process. & Pattern Recognition, Shanghai Jiaotong Univ., China
Abstract :
This paper describes the techniques for tracking nonrigid object moving in a complex scene. The improvement incorporates that both location and orientation information are used in model-matching and model-updating process. In this paper, we also propose a highly efficient searching strategy of locating object in an image. Results indicate that these techniques can perform well in complex conditions such as moving background and moving camera
Keywords :
computational complexity; image recognition; object recognition; search problems; tracking; highly-efficient searching strategy; improved Hausdorff measure; location information; model-matching; model-updating; nonrigid object tracking; orientation information; Cameras; Image processing; Layout;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location :
Hefei
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.859975