VISATRAM: A Vision System for Automatic Traffic Monitoring

Project Status:┬áComplete (Years: 1991 – 2000)

Research Description

Our VISATRAM uses a PC-486 based machine and a simple frame grabber to collect important traffic data such as 3D sizes and speeds of vehicles in a multi-lane highway traffic in real time. As an important application of our spatio-temporal panoramic modeling approach, we used TV camera mounted above the highway to monitor the traffic through two slice windows, and a panoramic view image and an epipolar plane image are formed for each lane. VISATRAM has a potential impact on intelligent transportation system (ITS) in many aspects such as traffic statistics, traffic control and automatic tolling system, with very economic and easy installation. This work has been presented at various conferences and published in a number of journals. The paper at the IEEE International Workshop on Applications of Computer Vision 1996 received a high rating from the Program Committee, and thus a revised paper was submitted by invitation to a special issue of Journal of Image Vision and Computing (JIVC). A prototype system has been tested with real road images under various light conditions, including shadows in daytime and lights at night, in collaboration with the Chinas Public Transportation Corporation for highway traffic monitoring and management around 1996.


China National Advanced Research Program, Image Mosaic-based Visual Scene Modeling and Target Recognition, 1/1996-12/2000, Co-PIs: G. Xu, Z. Zhu

China Public Transportation Engineering Corporation, Real-Time Vision System for Traffic Monitoring, 1995-1996, PI: Z. Zhu

China National Science Foundation, Motion Estimation Using Gradients of Image Intensity, 1/1994-12/1996, Co-PI: Z. Zhu

China National Advanced Research Program, Comprehensive Understanding of Multiple Sensing Systems, 1/1991-12/1995, Co-PIs: G. Xu, Z. Zhu