DEVELOPMENT AND EVALUATION OF A BREADBOARD VIDEO IMAGING SYSTEM FOR WIDE AREA VEHICLE DETECTION

Traffic engineers are constantly seeking new technology and equipment to deal with the problem of urban congestion. Among the most promising concepts available today is the use of video imaging for vehicle detection, automatic surveillance, and extraction of data needed for developing advanced control concepts. A recently developed video detection system is presented in this paper. This system operates on real time, can simultaneously detect traffic at multiple points within the camera's view, and emulates loop detectors. The system was installed and tested both off-line and in real time through taped data and field installations, respectively, and was directly compared to loops. The results suggest similar accuracy levels. In speed measurements, higher accuracies are expected for video systems than for loops. Finally, software is being developed for real-time extraction of traffic parameters, state variables (i.e., queue lengths and size), and measures of effectiveness (delays, stops, energy consumption, etc.) by the same device.