A Single-Frame Based Approach to Measure Traffic Queue Length

Abstract:

A novel method for measurement of vehicle queue length is presented in this paper. Previous methods proposed by researchers for queue detection are based on video sequences. The method proposed here measures the queue length in signal-frame image acquired by a stationary camera, which avoids the effect of uncontrollable camera motions. Besides, considering the varying illumination, double-threshold method is used for image segmentation and flashlight is applied to the system for realizing the round-the-clock traffic status detect. The experiment results of queue length measure from images of real road scenes show the accuracy and reliability of the proposed method.

• Periodical: Advanced Materials Research (Volumes 468-471)
• Pages: 213-216
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.468-471.213
• Online since: February 2012
• Authors: Qing Wu Li, Hao Li, Guan Ying Huo
• Keywords: Double-Threshold, Image Processing, Queue Length, Signal-Frame Image

References

[1] V. Kastrinaki, M. Zervakis, and K. Kalaitzakis: Image and Vision Computing, Vol. 21, No. 4 (2003), p.359–381.

DOI: 10.1016/s0262-8856(03)00004-0

[2] Michele Zanin, Stefano Messelodi, and Carla Maria Modena, An Efficient Vehicle Queue Detection System Based on Image Processing, Proceedings of the 12th International Conference on Image Analysis and Processing, 2003, pp.232-237.

DOI: 10.1109/iciap.2003.1234055

[3] R. P. Avery, Y. Wang, G.Scott Rutherford, Length-based vehicle classification using images from uncalibrated video cameras, Proceedings of the 7th International IEEE Conference on Intelligent Transportation Systems, 2004, pp.737-742.

DOI: 10.1109/itsc.2004.1398994

[4] M. Fathy, M. Siyal.. IEE Proc.-Vis. Image Signal Process., Vol. 142, No. 5 (1995), p.297–303.

[5] M. Siyal, M. Fathy. Pattern Recognition Letters, Vol. 20, (1999), p.761–770.