期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2014
卷号：7
期号：1
页码：53-64
DOI：10.14257/ijsip.2014.7.1.06
出版社：SERSC
摘要：Tracking object from video sequences has become a very popular problem in the field of computer vision. Many algorithms have been proposed to solve this problem. Combined with the energy of curvelet coefficients and Kalman filter method, a new object tracking algorithm is proposed based on fast discrete curvelet transform. Firstly, this algorithm is initialized with the establishment of a moving object template and a number of undetermined objects are got with the search strategy. Then, feature vectors are constructed by energy of curvelet coefficients. Finally, the moving object is tracked in next frames using similarity function to match the feature vectors. Experimental results demonstrate the tracking accuracy and efficiency of the proposed algorithm under occlusions.
