Automated Vehicle Velocity Estimation Using a Dual-Line Asynchronous Sensor

This paper proposes a vision system for vehicle velocity estimation based on asynchronous output data. For real-time velocity estimation, a processing method has been developed and implemented on a digital signal processor. It exploits the sparse asynchronous data representation from the dual-line sensor with high temporal resolution (better than 100 mus) and low latency. The processing concept includes vehicle contours extraction, velocity estimation and scaling. The estimation approach uses the vehicle´s leading edge on both lines to extract the detection time difference, which is used for the vehicle velocity estimation. The dual-line sensor system including this processing concept has been evaluated on several vehicles for velocities ranging from 10 to 120 km/h. The experiments have been performed at a test site with a two-lane road and the results obtained show an absolute velocity estimation error < 4 km/h.