Dynamic Template Tracking System with Application to the Detection of the Railway Spike Defects

Abstract:

This paper presents a novel correlation-based tracking algorithm, which is a generalization of the dynamic template correlation regional tracking (DTCRT) algorithmthe template is dynamic and the correlation is regional, and in particular the target image quality is not always good. The algorithm does not make use of the point-to-point multiplication and then summarizing as the traditional algorithm does. Instead, the DTCRT algorithm introduced. This fact helps to overcome several shortcomings of the point-to-point multiplication and then summarizing. The target is represented by the correlation coefficients. If the correlation coefficient is less than a threshold one can judge then the spike is defected. Since the matching function is a very complex function, the DTCRT algorithm is used to optimize it. Experiments demonstrate the effectiveness, significance and computation efficiency of the proposed railway spike tracking method in real-time identification.

• Periodical: Advanced Materials Research (Volumes 846-847)
• Pages: 1124-1128
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.846-847.1124
• Online since: November 2013
• Authors: Rong Hu*, Xiao Qing Luo
• Keywords: Correlation Coefficient, Dynamic, Template Matching, Threshold, Tracking Regional

References

[1] Jiang Li Fang. The research of the Industrial visual inspection system in pattern recognition[D]. Harbin engineering degree thesis, university of technology, 2008：1-10.

[2] Gao Wen. Computer vision-algorithm and the system theory[M]. Tsinghua university press. 2000: 4-17.

[3] LiBiCheng, PengTianJiang, PengBo. Intelligent image processing technology [M]. Electronic industry press, 2004: 5-6, 193~195.

[4] Li YanLing, Wang Jianping, Zhang Yankun. A new tracking algorithm study [J], journal of electronics. . Vol. 20. No. 5. October. (2005).

[5] ALSHENNAWY A, GADELMAWLA E S，KOURA MM．A new computer vision algorithm for the extraction of straight and curved features of two-dimensional products[J]．Proceedings of the Instituti on of Mechanical Engineers-Part B-Engineering Manufacture，2006，(1)：1141-1150.

DOI: 10.1243/09544054jem475

[6] Li cai Hua. The of research and design intelligent vehicle binocular vision system[D]. Master thesis. Changchun. Jilin university. (2004).

[7] Zhu Yongsong, Guo chengning, the correlation coefficient based on relevant tracking algorithm study [J], journal of Chinese graphics. Vol. 9. No. 8. Aug. (2004).

[8] M. MaureY, ete. WaMoRs-P-An Advanced Platform for Visual Autonomous Road Vehicle Guidance[A]. Proe. SPIE Conf. on Mobile Robots IX. Boston[C]. 1994，2352: 239-248.

[9] YangYiHe, ZhouWeiZhen. Imaging tracking technology introduction[M]. Xian: xidian university press, 1992: 71~73.

[10] Sadayuki Tsugawa. Vision-Based Vehicles in Japan: Machine Vision Systems and Driving.