The Research on Fast and Efficient Algorithm in Multi - Cameras-Relay Target Tracking

Abstract:

In computer vision field, video target tracking has important significance of research. This article proposed a fast and efficient multi-cameras-relay target tracking method directed at crucial technology questions in video target tracking. First, it separated the foreground and background of monitoring scene using of Markov random field theory, and then established the Markov random field model of foreground and background, so as to accomplish the moving object recognition; The next, it located the accurate positioning and tracking utilizing the combination of Kalman filtering and improved Camshift algorithm; finally, it made more-cameras-relay target tracking on the basis of coordination and synchronous between cameras, to achieve high efficiency of tracking and strong robustness and monitoring of the wide range of target real-time tracking.

• Periodical: Applied Mechanics and Materials (Volumes 190-191)
• Pages: 1198-1204
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.190-191.1198
• Online since: July 2012
• Authors: Xiao Ping Li, Chun Hui Liang, Si Chen, Hui Jie Cui, Jian Qiang Xu, Qiong Xu, Feng Nian Zhao, Xu Mao
• Keywords: Camshift Algorithm, Kalman Filter (KF), Markov Random Field Theory, Multi-Cameras-Relay, Target Tracking

References

[1] Edward H.S.Lo, Mark R, Pickering, Michael R, Frater. Image segmentation from scale and rotation invariant texture features from the double dyadic dual-tree complex wavelet transform[J].Image and Vision Computing,(2011),pp.15-28.

DOI: 10.1016/j.imavis.2010.08.004

[2] BRADSKI G R. Computer Video Face Tracking for Use in a Perceptual User Interface [J]. Inter Technology Journal, Q2 1998:1—15.

[3] K．Fukunaga and L.D．Hostetler, "The estimation of the gradient of a density function，with applications in pattern recognition"，IEEE Trans．Information Theory,1975 Vol 21：32—40

[4] Shiuh-KuWeng, Chung-MingKuo, Shu-KangTu. Video object tracking using adaptive Kalman filter.J.Vis. Commun. ImageR.2006(17):1190—1208

[5] Lowe D G．Distinctive image features from scale-invariant keypoints[J]．International Journal or Computer Vision，2004，60(2)：91—110．

DOI: 10.1023/b:visi.0000029664.99615.94

[6] Diao Qian，Zhang Yimin，Gang Song，Chun Ronglai. A Dynamic Bayesian Network Approach to Multi--cue based Visual Tracking[C].Proceeding soft he17t Interactional Conferences on Patton Recognition(ICPR，04)，2004:167—170.

DOI: 10.1109/icpr.2004.1334087

[7] Phung S I．Bouzerdoum A，Chai D．A novel skin color model in cyber color space and its application to Hantan face detection[ C]// IEEE International Conferences on Image Processing(ICIP'2002)．vol 1，2002：289—292

DOI: 10.1109/icip.2002.1038016

[8] R T Collins, A J Lipton, T Kanabec. A System for Video Surveillance and Monitoring. Proc. Am. Nuclear Soc. (ANS) Eighth Int'1 Topical Meeting Robotic and Remote Systems, Apr.(1999)

[9] DENG Ying-na。ZHU Hong，LI Gang，et a1．Scene model based object tracking method across multiple cameras．Computer Engineering and Applications. 2008．44(5)：55-57．

[10] ROM Yuan. Cheling. Based on CamShift and a few filter mix of Taiwan Kalma video gesture tracking algorithm. Computer application and research, Vol. 26 No. 3200 in March 9

[11] Zhang Guilin. Markov random field in image processing of the application of [D].Wuhan: Huazhong University of science and technology, 2005.

[12] Huang Feiyue, Xu Guang skirt. Much of the application of synchronous video camera [A], the sixteenth national multimedia technology academic conference [C]. 2007:239-245.

[13] NiuEn countries. Many cameras in the environment of target research and system transition [D]. Xian: northwestern polytechnic university, 2006.

[14] NiuEn countries, Cheng Yongmei, Pan Quan, Zhao Chunhui, Yang Tao. The camera view boundary fast automatic generation algorithm [J]. Computer application and research. 2007.24 (3) : 297-299.

[15] Guler．S，Griffith．J．M，Pushee．I．A．Tracking and handoff between multiple perspective camera views[A]，Proceedings of Applied Imagery Pattern Recognition Workshop[C]，Washington，DC，USA，2003：275—28 1．

DOI: 10.1109/aipr.2003.1284284

[16] Wang Xiaolin. Often shine. Large complicated scene of camera relay target tracking research [D]. Shandong: Shandong University, 2009.