Video Vehicle Tracking Based on Improved Mean-Shift Algorithm

Abstract:

An improved Mean-Shift-based Video vehicle tracking algorithm was proposed and which can improve the real-time and accuracy of the vehicle detection technology in the application. First, it eliminates the disturbance from unrelated background by mathematical morphology operation between a traffic image and the mask of fixed background area .Then the image sequences are simulated by absolute difference of adaptive threshold for detecting latent target. At last, clusters video frames with similar characteristics which are regarded of the invariant moments vectors by Mean Shift clustering algorithm. Experimental results shown that the improved algorithm has advantages of reducing king region of vehicle matching and vehicle complete occlusion.

• Periodical: Advanced Materials Research (Volumes 179-180)
• Pages: 1408-1411
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.179-180.1408
• Online since: January 2011
• Authors: Wei Bin Chen, Xin Zhang, Su Qin Luo
• Keywords: Intelligent Transportation, Mathematical Morphology, Mean-Shift, Video Vehicle Tracking

References

[1] Kuo-Lung Wua, Miin-Shen Yang , Mean shift-based clustering, Pattern Recognition , 40(2007) 3035–3052.

DOI: 10.1016/j.patcog.2007.02.006

[2] Stephan R. Harmsen, Nicole J.J.P. Koenderink, Multi-target tracking for flower counting using adaptive motion models, comuters and electronics in agriculture, 65(2009)7-18.

DOI: 10.1016/j.compag.2008.07.004

[3] Bernhard Burgeth_, Andres Bruhn, Mathematical morphology for matrix fields induced by the Loewner ordering in higher dimensions, Signal Processing 87 (2007) 277–290.

DOI: 10.1016/j.sigpro.2005.12.012

[4] F. Camastra,A. Verri, A novel kernel method for clustering, IEEE Trans. Pattern Anal. Mach. Intell. 27(2005)801–805.

DOI: 10.1109/tpami.2005.88

[5] M. Girolami, Mercer kernel based clustering in feature space, IEEE Trans. Neural Networks 13(2002) 780–784.

DOI: 10.1109/tnn.2002.1000150

[6] K.R. Muller,S. Mika,G. R?tsch,K. Tsuda,B. Sch?lkopf, An introduction to kernel-based learning algorithm, IEEE Trans. Neural Networks 12 (2001)181–202.

DOI: 10.1109/72.914517

[7] B.W. Silverman, Density Estimation for Statistics and Data Analysis, Chapman&Hall, New York, (1998).

[8] K. Fukunaga L.D. Hostetler, The estimation of the gradient of a density function with applications in pattern recognition, IEEE Trans. Inf. Theory 21(1975)32–40.

DOI: 10.1109/tit.1975.1055330

[9] Y. Cheng, Mean shift, mode seeking, and clustering, IEEE Trans. Pattern Anal. Mach. Intell. 17(1995)790–799.

DOI: 10.1109/34.400568

[10] R.R. Yager D.P. Filev, Approximate clustering via the mountain method, IEEE Trans. Syst. Man Cybern. 24(1994)1279–1284.

DOI: 10.1109/21.299710