Analyzing Wheels of Vehicles in Motion Using Laser Scanning

Andreas Mogelmose, Thomas B. Moeslund; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016, pp. 1-8

In this paper, we discuss a lidar-based wheel-width measuring system. Trucks are used for an enormous part of day to day freight delivery across the world, and cause significant wear to the road they use. Road planners and construction engineers rely on traffic statistics to properly design roads. Currently, no system is able to provide them with numbers on the wheel-widths of the vehicles using a particular stretch of road. We present a system which uses a horizontal lidar measuring in a plane close and nearly parallel to the road surface. Input from this is used to detect and analyze tires. A vertical lidar detects passing vehicles so individual tires can be combined into full vehicle models. The system detects 58% of passing vehicles, but correctly counts the number of axles on 85% of detected vehicles. More than 90% of of the axles are correctly classified according to the number of mounted tired (single or dual).