Train speed measurement and prediction using video and radar detector data

A key component to optimizing traffic signals along a corridor with multiple intersections located near highway-rail grade crossings (HRGCs) is an accurate estimate of a given train's arrival time at each crossing. Based on this information, current signal preemption strategies at the traffic signals near the highway-rail grade crossings (HRGCs) could be improved with a resulting improvement in driver and pedestrian safety and transportation system delay. This paper introduces a procedure for the real-time train speed estimation using data from Autoscope video detection and a Doppler radar detector. The two detectors were used in parallel because each, on its own, has a number of issues that preclude accurate detection of simultaneous trains (e.g. trains on different tracks in the detection zone at the same time). A multi-track test bed was chosen for the data collection, speed estimation and verification. A linear regression model was used for calibration of video and radar detection.