A Data Fusion Approach to Automated Vehicle Detector Testing

C. A. MacCarley, California Polytechnic State University - San Luis Obispo
N. Nesse, Loragen Corporation
J. Slonaker, California Department of Transportation

Article comments

Copyright © 2006 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The definitive version is available at http://dx.doi.org/10.1109/DSPWS.2006.265434

Abstract

Vehicle presence detectors have become critical elements of traffic management systems, including applications ranging from intersection signal control to freeway congestion monitoring. The need to assess the accuracy and attributes of each of the many types of sensors motivated the California Department of Transportation to construct the Traffic Detector Testbed on I-405 in Southern California. With up to ten detectors of different types under concurrent test in each of six lanes, a means for automating the testing process became imperative, since traditional human-verification methods were not practical. This paper describes the design and implementation of an automated data acquisition and verification system that processes data from all detectors along with that of a reference image processing system, to create a composite ground truth record against which individual detector performance is assessed. The system architecture, data fusion methodology, computer vision methods, operator interface and system performance results are discussed.