Non-Contact vehicle Weigh-in-Motion using computer vision

•Computer vision-based non-contact weigh-in-motion (WIM) system was prototyped.•Methodical validation of computer vision as an implement in weight estimations.•Field experiments were conducted on stationary and moving vehicles.•Experimental results of vehicle weight estimations show percent of error less than 5%. Heavy vehicles must be closely monitored to prevent fatigue-induced deterioration and critical fractures to transportation infrastructure. This paper introduces an innovative computer vision-based non-contact vehicle weigh-in-motion method and presents a proof-of-concept study. The method is based on simple physics that tire-roadway contact force equals the contact pressure multiplied by the contact area. The area can be estimated by measuring tire deformation parameters such as tire-roadway contact length and tire vertical deflection using computer vision, while tire pressure can be streamed from on-board sensors. To demonstrate the feasibility of this method, a computer vision system was developed and experiments were conducted involving empty and fully loaded concrete trucks and a sport utility vehicle. Results show high accuracy of vehicle weight estimation, demonstrating the potential of this computer vision-based method as a non-contact means for weighing vehicles in motion.