Research on License Plate Tracking and Detection Based on Optical Flow

Abstract:

Aiming at regulating the toll evasion behaviors in highway weight charges and reducing charge disputes caused by jumping, this article studied the algorithm that tracks vehicle beating when it is passing the scale. Based on license plate location, vehicle movement could be characterized by tracking the plate centroid using Lucas-Kanade optical flow algorithm. The optical flow vector of the centroid was calculated frame by frame, which could be used for drawing trajectory of centroid coordinates, and calculating beating parameters. In order to expand the detection range and adaptability of the algorithm, through calculating optical flow hierarchically combined with Gaussian pyramid, then tracking centroid from high lever to low in the image pyramid, it could achieve the capture of the vehicle' fast moving. Through experiments, trajectory reflected vehicle beating information well, which provides a strong evidence means for levy problem of the highway weight charges.

• Periodical: Applied Mechanics and Materials (Volumes 135-136)
• Pages: 775-780
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.135-136.775
• Online since: October 2011
• Authors: Hong Ke Xu, Chao Cai, Hao Chen, Jian Wu Fang, Shu Guang Li
• Keywords: Centroid Tracking, Gaussian Pyramid, Image Processing, L-K Optical Flow

References

[1] G. X. Wang, Q. Liu, C. Zhu, Discussion of related issues on the highway weight charges, Jilin Science & Technology of Communications, 2007, (4): 57-58.

[2] Y. J. Ding, Development and application of video detection in highway information collection, Transportation Information Industry, vol. 26, 2004, pp.139-140.

[3] H. K. Xu, J. W. Fang, Q. L. Hu, M. He, J. Li, Detection of vehicle beating trajectories using color license plate location, 2010 Chinese Control and Decision Conference, CCDC 2010, 2010, pp.4211-4216.

DOI: 10.1109/ccdc.2010.5498385

[4] R C. Gonzalez, R E. Woods, Digital Image Processing, Third Edition, Publishing House Of Electronics Industry, 2010, pp.649-701, 817-879.

[5] X. T. Wang, Research of ship motion factors determination principle using optical flow, NAVIGATION OF CHINA, Serial No. 59, No. 2, Jun. 2004, pp.7-10.

[6] G. Bradski, A. Kaebler, Learning OpenCV, TSINGHUA UNIVERSITY PRESS, 2009, pp.357-360.

[7] Y. H. Cheng, Optical flow-based video tracking facial feature points, Computer and Modernization, Serial No. 179, No. 7, 2010, pp.120-122.

[8] J. H. Hu, Y. M. Li, X. L. Pan, Improved optical flow method for vehicle identification and tracking, Science Technology and Engineering, Vol. 10, No. 23, Aug. 2010, pp.5814-5817.

[9] H. Li, T. W. Yang, P. Z. Ren, Z. H. Li, Tracking of moving target in complex background using optical flow, Opto-Electronic Engineering, Vol. 33, No. 10, Oct. 2006, pp.13-17.

[10] Y. J. Xiahou, S. R. Gong, C. P. Liu, C. Liu, Video segmentation algorithm with Gaussian distribution and the LK optical flow method, MICROELECTRONICS & COMPUTER, Vol. 26, No. 6, June. 2009, pp.239-245.

[11] Z. J. Jiang, H. R. Yi, A feature tracking method based on image pyramid optical flow, Geomatics and Information Science of Wuhan University, Vol. 32, No. 8, Aug. 2007, pp.680-683.