Traffic engineering & control · 1987 · 17 citations · 0 references
ComputingComputer ScienceComputer SystemsComputer VisionMachine VisionTransportationIntelligent Transportation SystemsMotion AnalysisRoad TransportTraffic EngineeringTraffic SafetyRoad Feature DetectionRoad Network MonitoringRoad Traffic NetworksTraffic Monitoring SystemsTraffic SurveillanceVehicle Detection
This paper shows how with suitable reduction of image data and appropriate feature extraction, it is possible to track several vehicles concurrently through a road network of almost arbitary complexity. The solution is believed to be cost-effective, using off-the-shelf technology and readily-available computing power. The processing falls into 2 parts: (1) feature highlighting and extraction, carried out by the RAPAC image processing system; and (2) vehicle tracking, carried out with a 5MHZ 8086-based microcomputer. The system promises a cost-effective solution to the automatic monitoring of turning movements by road traffic. With this system accuracies of 90 to 95 per cent have been achieved on simple networks such as T-junctions.