Real-Time Measuring System Based on Vehicle Flow Video Image
Hongjian Wang · 2009
In intelligent transportation systems (ITS), the data of vehicle flow is very important to control and lead to traffic. Based on chromatism in an image sequence brought by moving vehicle which is difference between vehicle and road surface, a new method is proposed to collect real-time traffic flow data in city: 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 90%. And the combination of phase control of road control, which can intelligent lead to traffic by real-time and satisfies the requirements of practical application.