Video cameras and computer image processors have come into widespread use for the detection of vehicles for signal actuation at controlled intersections. Manufacturers’ accuracy and robustness claims vary in the metrics used and data reported, and are selective and inconsistent between competing products. The lack of common testing standards and procedures has left Caltrans and local jurisdictions that may be interested in deploying video intersection detection reliant upon manufacturer claims and non-rigorous perceptions from other deployments. The true performance of these systems is difficult to ascertain by simple observation of signal actuation.
The study builds upon work conducted under the 1995-97 PATH-sponsored Anaheim Field Operational Test (FOT), Task C: VTDS Evaluation in which, in consultation with an extensive advisory board including the FHWA, Caltrans, Anaheim and system manufacturers, a standardized approach for the evaluation of intersection detection systems was developed and applied to one such system deployed as part of the FOT. The project updates and applies these standards and procedures to the testing and comparative evaluation of examples of all currently-manufactured video-based intersection signal actuation systems which have significant deployments in California. The ultimate deliverable is a comprehensive evaluation report on the absolute and relative performance of each system, as well as improved insight into both the advantages and limitations of this class of detectors.
C. Arthur (Art) MacCarley, Ph.D., PE