Real-time monitoring algorithm of highway height limit via binocular vision.

To confront the difficulties for moving vehicles in measuring the actual heights at various highway height limit facilities, this paper proposes a binocular camera height limit target real-time monitoring algorithm. First, an analysis of the height limit scenarios and facilities is made and a large- scale multi-scenario highway height limit dataset is built. Second, the target region is obtained by the detection and tracking algorithm based on deep learning. The binocular disparity is processed by a multi-step and multi-scale filtering algorithm to obtain the high-confidence height limit facility disparity data and thus calculate the distance and height information. Finally, the robust output strategy is adopted and alarms will be activated based on the real-time collected distance and height results. After multi-scenario height limit experiments, the target detection accuracy stands at 98.77%, the missed detection rateat 0. 87%, the false detection rate at 0. 36%, and the average height measurement error within 60 m below 4%. The results show that our algorithm achieves automatic detection and computation of highway height limit targets, as well as real-time and robust delivery of distance and height measurements and early warnings. [ABSTRACT FROM AUTHOR]