Traffic Signal Indicator Classification Based on Color-Shape Feature

Abstract:

Traffic signal lights are generally composed by digital indicator and direction indicator. Its identification and classification is to analysis image content on the base of the semaphores characteristics, to identify the semaphores goals and classify them, including pre-processing, positioning, segmentation and classification. Based on image preprocessing, global threshold processing is used in the HSI color space to find the location of traffic signal lights; then to get each indicator through the projection method dividing; finally to distinguish digital processing and direction indicator by target detection algorithm based on the shape features of traffic signal lights. Simulation experiments show that the algorithm is reliable and executes efficiently with high accuracy.

• Periodical: Advanced Materials Research (Volumes 765-767)
• Pages: 2797-2800
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.765-767.2797
• Online since: September 2013
• Authors: Yong Ren
• Keywords: Color Image Equalization, Colors-Shape Feature, Indicator Classification, Lights Positioning

References

[1] P., RANGANATH S., HUANG W. M., SENGUPTA K. Framework for real-time behavior interpretation from traffic video IEEE Transactions on Intelligent Transportation Systems, 2005, -Volume. 6. -Issue. 1. -P. 43-53.

DOI: 10.1109/tits.2004.838219

[2] ZHOU J., GAO D., ZHANG D. Moving Vehicle Detection for Automatic Traffic Monitoring IEEE Transactions on Vehicular Technology, 2007, -Volume. 56, -Issue. 1. -P. 51-59.

DOI: 10.1109/tvt.2006.883735

[3] ZHANG H., FRITTS J. E., GOLDMAN S. A. Image segmentation evaluation: A survey of unsupervised methods Computer Vision and Image Understanding, 2008, -Volume. 110. –Issue. 2. -P. 260-280.

DOI: 10.1016/j.cviu.2007.08.003

[4] ZHU F. A Video-Based Traffic Congestion Monitoring System Using Adaptive Background Subtraction Proceedings ISECS-IEEE Press, 2009, May, -P. 73-77.

DOI: 10.1109/isecs.2009.64

[5] MILLER O., AVERBUCH A. Color image segmentation based on adaptive local thresholds/ Image and Vision Computing, 2005, -Volume. 23. -Issue. 1. -P. 69-85.

DOI: 10.1016/j.imavis.2004.05.011

[6] Boles W.W., Kanefsky M., Simaan M. A reduced edge distortion median filtering algorithm for binary images Signal Processing, 1990, -Volume. 21. -Issue. 1. -P. 37-47.

DOI: 10.1016/0165-1684(90)90025-t

[7] Johannes P.F., Haeyer D. Gaussian filtering of images: A regularization approach Signal Processing, 1989, -Volume. 18. -Issue. 2. -P. 169-181.

DOI: 10.1016/0165-1684(89)90048-0

[8] ZHU F., LI L.Y. An Optimized Video-Based Traffic Congestion Monitoring System Proceedings Knowledge Discovery and Data Mining -IEEE Press, 2010, Jan., -P. 150-153.

DOI: 10.1109/wkdd.2010.47