Moving target detection based on Genetic K-means Algorithm

Recently, the research on extracting moving objects from video sequences in the current computer vision applications is very popular. A new method based on genetic k-means algorithm from Gaussian mixture model (GMM) to deal with moving target of video image was purposed in this paper. The described method in this paper is learned from clustering idea, which is very different from traditional way. According to Genetic K-means Algorithm, by clustering of pixels on the timeline, the background could be described through several clusters. On the basic of these clusters, moving target detection could be done. Simulation experiment showed that the method could give a good result for the moving target detection.

[1]  Hironobu Fujiyoshi,et al.  Moving target classification and tracking from real-time video , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[2]  Max A. Viergever,et al.  Mutual-information-based registration of medical images: a survey , 2003, IEEE Transactions on Medical Imaging.

[3]  M. Narasimha Murty,et al.  Genetic K-means algorithm , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[4]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[5]  Ujjwal Maulik,et al.  Genetic algorithm-based clustering technique , 2000, Pattern Recognit..