A window-based image processing technique for quantitative and qualitative analysis of road traffic parameters

被引:54
作者
Fathy, M [1 ]
Siyal, MY
机构
[1] Iran Univ Sci & Technol, Dept Comp Engn, Tehran, Iran
[2] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore
关键词
edge detection; image processing; real time; traffic parameters;
D O I
10.1109/25.728525
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Traffic information is an important tool in the planning, maintenance, and control of any modern transport system. Of special interest to traffic engineers are parameters of traffic flow such as volume, speed, type of vehicles, queue parameters, traffic movements at junctions, etc. Various algorithms, mainly based on background differencing techniques, have been applied for this purpose. Since background-based algorithms are very sensitive to ambient lighting conditions, they have not yielded the expected results. In this paper, we describe a novel approach to measure traffic parameters. This approach is based on applying edge-detection techniques to the key regions or windows. This method of measuring road traffic parameters eliminates the need of a background frame, which is an essential, but unreliable technique for background-based image-detection methods. A dynamic threshold selection technique has also been introduced to select the threshold value automatically, The image processing algorithm has been applied to measure basic traffic parameters such as traffic volume, type of vehicles, as well as the complex traffic parameters such as queue parameters and movements of vehicles at traffic junctions.
引用
收藏
页码:1342 / 1349
页数:8
相关论文
共 15 条
[1]  
[Anonymous], TRAFFIC ENG CONTR
[2]  
DICKINSON KW, 1984, TRAFFIC ENG CONTR, V2, P60
[3]  
DICKINSON KW, 1989, II 2 INT C ROAD TRAF
[4]  
Fathy M., 1995, Real-Time Imaging, V1, P297, DOI 10.1006/rtim.1995.1028
[5]   An image detection technique based on morphological edge detection and background differencing for real-time traffic analysis [J].
Fathy, M ;
Siyal, MY .
PATTERN RECOGNITION LETTERS, 1995, 16 (12) :1321-1330
[6]  
HASHIMOTO N, 1988, SUMITOMO ELECT T JAN, P133
[7]  
Hoose N., 1991, COMPUTER IMAGE PROCE
[8]  
Hoose N., 1992, TRAFFIC ENG CONTROL, P140
[9]  
LEE J, 1987, IEEE J ROBOT AUTOMAT, V3
[10]  
Rourke A., 1988, P SEM TRANSP PLANN M