Based on Image Matching and Tracking of Moving Objects

Article Preview

Abstract:

According to the traditional gray-scale value matching algorithm and its defect of high time complexity, this paper presents a matching algorithm based background subtraction. First we find moving target in the background by subtraction, and then match the template image to the target image of motion, which greatly reduces the amount of calculation and improves the matching speed. We effectively predict the target’s location in the next frame by five-point linear prediction method. Simulation shows that the algorithm is better than the traditional gray-scale matching algorithm and it has strong robustness.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

352-356

Citation:

Online since:

April 2012

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] PENG Zhen-ming, ZHANG Qi-heng, WEI Yu-xing, et al. Image matching based on multi-features fusion [J]. High Power Laser and Particle Beams, 2004, 16(3):281-285.

Google Scholar

[2] Meier T, Ngun K N. Video Segmentation for Content-Based Coding[J] . IEEE Trans. on Circuit s and Systems for Video Technology, 1999, 9 (8): 1190 - 1203.

DOI: 10.1109/76.809155

Google Scholar

[3] BARRON J, FLEET D, BEACHEMIN S. Performance of optical flow techniques[J]. International Journal of computer Vision, 1994 ,12 (1) :42 - 47.

Google Scholar

[4] Surendra Gupte, etal. Detection and Classification of Vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2002 (3):37- 40.

Google Scholar

[5] Loutast E, Diamantarast K, Pitast I. Occlusion resistantobject tracking[C] ∥IEEE International Conference on Image Processing, Thessaloniki, Greece, 2001: 65 -68.

Google Scholar