Moving Target Tracking Based on CamShift Approach and Kalman Filter

The surveillance system has been developed for decades. It has reduced the crime and protected the lives and properties of people successfully. Some surveillance systems are composed of PTZ cameras. Therefore the moving people or target objects could be tracked by the surveillance system. The surveillance system becomes more and more interment. However, there are two problems occurred, target recognition and target shelter. In this paper, we proposed the method of tracking a moving object for improving the performance of intelligent surveillance system. The method combined CamShift and Kalman filter for tracking the moving object in a complex background or in an occlusion case. The proposed method is very efficient and that is easily implemented in a real-time system. Three major problems of surveillance system design, moving object detecting, moving object tracking and tracking the object in occlusion, have been conquered in the experimental results.

[1]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[2]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[3]  Paul Wintz,et al.  Digital image processing (2nd ed.) , 1987 .

[4]  Guo-liang Wang,et al.  Algorithm for Tracking of Fast Motion Objects with Adaptive Mean Shift , 2007, Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007).

[5]  Larry D. Hostetler,et al.  The estimation of the gradient of a density function, with applications in pattern recognition , 1975, IEEE Trans. Inf. Theory.

[6]  Helmut E. Bez,et al.  A practical adaptive approach for dynamic background subtraction using an invariant colour model and object tracking , 2005, Pattern Recognit. Lett..

[7]  Chu-Sing Yang,et al.  PTZ camera based position tracking in IP-surveillance system , 2008, 2008 3rd International Conference on Sensing Technology.

[8]  F. Xavier Roca,et al.  Reactive Object Tracking with a Single PTZ Camera , 2010, 2010 20th International Conference on Pattern Recognition.

[9]  Jesse S. Jin,et al.  Tracking Using CamShift Algorithm and Multiple Quantized Feature Spaces , 2004, VIP.

[10]  R. E. Mortensen,et al.  Filtering for stochastic processes with applications to guidance , 1972 .

[11]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[12]  D.V. Thombre,et al.  Human detection and tracking using image segmentation and Kalman filter , 2009, 2009 International Conference on Intelligent Agent & Multi-Agent Systems.

[13]  Xin Jin,et al.  Mean Shift , 2017, Encyclopedia of Machine Learning and Data Mining.

[14]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Guodong Liu,et al.  Visual servoing control of video tracking system for tracking a flying target , 2011, 2011 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM).

[16]  Wang Yan-chun,et al.  Algorithm for Tracking of Fast Motion Objects with Adaptive Mean Shift , 2007 .

[17]  Hong Ren Wu,et al.  Smart video surveillance system , 2010, 2010 IEEE International Conference on Industrial Technology.

[18]  King-Sun Fu,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Chen-Sen Ouyang,et al.  Mean shift tracking using fuzzy color histogram , 2010, 2010 International Conference on Machine Learning and Cybernetics.

[20]  H.M. Wechsler,et al.  Digital image processing, 2nd ed. , 1981, Proceedings of the IEEE.

[21]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..