A parallel pipeline based multiprocessor system for real-time measurement of road traffic parameters

Real-time measurement and analysis of road traffic flow parameters such as volume, speed and queue are increasingly required for traffic control and m anagement. Image processing is considered as an attractive and flexible tec hnique for automatic analysis of road traffic scenes for the measurement an d data collection of road traffic parameters. In this paper, the authors de scribe a novel image processing based approach for analysis of road traffic scenes. Combined background differencing and edge detection techniques are used to detect vehicles and measure various traffic parameters such as veh icle count and the queue length, A RISC based multiprocessor system was des igned to enable real-time execution of the authors algorithm, The multiproc essor system has nine processing modules connected in a parallel pipeline f ashion. Results shows that the authors multiprocessor system is able to pro vide measurement of traffic parameters in real-time, Results are presented for real tests of our system by analysing traffic scenes on the highways of Singapore. (C) 2000 Academic Press.