The Study of Moving Images Track Recording System which Based on Mean Shift Algorithm


Article Preview

Intelligent tracking system based on video recording problem is a key technique in computer vision and research focus, a lot of engineering applications and video tracking technology has a close relationship. This system is a development platform for the ADSP-BF533 core, together with the VisualDSP + + integrated development and debugging environment, implementation, and optimization MeanShift tracking algorithm to achieve real-time tracking of moving target shooting can be used in sporting events, intelligent monitoring. Test data show that the system can control the PTZ camera tracking rigid and non rigid shooting targeting.



Edited by:

Qi Luo






K. F. Wang and H. C. Ke, "The Study of Moving Images Track Recording System which Based on Mean Shift Algorithm", Applied Mechanics and Materials, Vols. 58-60, pp. 1365-1370, 2011

Online since:

June 2011




[1] Dabo Zhang. Principles of Embedded System Design and Application [M]. China Machine Press. (2005).

[2] HanB, Comaniciu D, ZhuY and Davis LS. Sequential kernel density approximation and its application to real-time visual tracking. IEEE Transaction Pattern Analysis and Machine Intelligence, 30(7) . 1186-1197(2008).

DOI: 10.1109/tpami.2007.70771

[3] Ruixia Guo, Yunxing Wu and Yuehui Song. Research of Auto-tracking Video Surveillance System[J]. Video technology and engineering. Vol2. (2006).

[4] Yong Yan. Researches on Algorithm and Implementation of Tunnel Video Surveillance System of Highway[D]. Chong Qing University. (2006).

[5] Comaniciu D, Ramesh V and Meer P. Real-time tracking of nonrigid objects using mean shift[J]. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Hilton Head Island. USA: IEEE. 142-149(2000).

DOI: 10.1109/cvpr.2000.854761

[6] Li Pei-Hua. An improved mean shift algorithm for object tracking[J]. Acta Automatica Sinica. 33(4): 347-354(2007).

In order to see related information, you need to Login.