A COMPUTER VISION DETECTION SYSTEM FOR NETWORK MODEL VALIDATION
C. Arthur MacCarley, Brian Hemme · 2001
This paper describes the development and testing of a computer- vision-based traffic detection system capable of uniquely identifying vehicles in a traffic network from video images, and later re- identifying each vehicle at subsequent detection sites in the network. This capability permits deterministic validation of microscopic network flow models, origin-destination tables, and travel-time tables. The system is referred to as the Video-based Vehicle Signature Analysis and Tracking (V2SAT) System. Using video cameras are primary sensors, detection modules generate a numeric Video Signature Vector (VSV) for each vehicle, and transmit these to a central Internet- connected correlation computer via a public low-power wireless network. The correlation computer attempts to match vehicles, as represented by their VSVs, generated at successive detection sites to enable a real-time microscopic flow representation of the freeway network. Test results indicate a 93.6% accurate ability to correctly re-identify vehicles at successive sites. The tendency of the system to incorrectly match different vehicles at successive sites was measured at 0.0116%