On-Line Measuring System for Urban Highway Traffic Flow Based on Video Detection Technique


Article Preview

In intelligent transportation systems (ITS) for urban highway-nets, the data of traffic flow is very important to control and lead to traffic. According to chromatic aberration between vehicles and road surfaces in images caught from moving vehicles, a new method is proposed to analyze on-line traffic states based on video detection technique. firstly video for 10 frame/second sampling, difference operation of same region of two neighbored image is used to detect moving vehicle very quickly on measurement strap; secondly the result of difference was grayed ,horizontal projection and adaptive threshold methods are adopted to recognize moving vehicle and type of vehicle by statistical analysis, which is very expedient, accurate and quick. The results of experiments show that the correct recognition rate of this system reaches up to 96%.And the combination of phase control of road control, which can intelligent lead to traffic by on-line and satisfies the requirements of practical application.



Advanced Materials Research (Volumes 108-111)

Edited by:

Yanwen Wu






C. Ning "On-Line Measuring System for Urban Highway Traffic Flow Based on Video Detection Technique", Advanced Materials Research, Vols. 108-111, pp. 713-717, 2010

Online since:

May 2010





[1] Liu Wenzhi: Application of imaging2based vehicle detector on expressway. Journal of Highway and Transportation Research and Development , 2003, 20(2), Page(s): 88 - 91.

[2] Fujimura K.: A method for generating adaptive background to detect moving object, Trans. SICE., 33(9): 963-968, Sept. 1997. (in Japanese).

[3] Ju Yongfeng , Zhu Hui , Pan Yong: Vehicle flow detection algorithm based on computer vision. Journal of Chang'an University (Natural Science Edition), 2004 , 24 (1) , Page(s) : 92 - 95.

[4] Xiao Wangxin, Zhang Xue , Huang Wei. Adaptive thresholds edge detection of traffic image. Journal of Traffic and Transportation Engineering , 2003 , 3(4) , Page(s) : 104 - 107.

[5] Gutchess D , Trajkovic M , Cohen2Solal E , et al.: A background model initialization algorithm for video surveillance. Vancouver , BC: Institute of Electrical and Electronics Engineers Inc , 2001, Page(s) : 733-740.

[6] Li Zhihui , Zhang Changhai , Qi Zhaowei , et al.: Background ext raction model and shadow detection algorithm in t raffic flow video detection . Journal of Jilin University ( Engineering and Technology Edition) , 2006 , 36 (6) , Page(s): 993-997.

[7] Wren C R , Azarbayejani A , Darrell T , et al.: Pfinder : real-time t racking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence , 1997 , 19 (7) , Page(s) : 780-785.

DOI: 10.1109/34.598236

[8] Andrea C A F , Vittorio M.: Background initialization in cluttered sequences∥Computer Vision and Pattern Recognition Workshop , 2006: 197.

[9] Stauffer C , Grimson W E L.: Adaptive background mixture models for real-time t racking. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1999 (2) , Page(s) : 246-252.

DOI: 10.1109/cvpr.1999.784637

[10] Hinz S.: Spatio-temporal matching of moving objects in optical and sar data. PIA07 - Photogrammetric Image Analysis --Munich, Germany, September 19-21.

In order to see related information, you need to Login.