Bridge weigh-in-motion using bridge influence surface and computer vision: an experimental study

Complicated traffic scenarios, including random lane change and multiple presences of vehicles on bridges are the main obstacles preventing bridge weigh-in-motion (BWIM) technique from reliable and massive application. To tackle the complicated traffic problems of BWIM, this paper develops a novel BWIM method by integrating the bridge influence surface theory and deep-learning based computer vision technique. For illustration and verification, the proposed method is applied to identify gross weights of vehicles in scale experiments, where various complicated traffic scenarios are simulated. Identification results confirm the favourable robustness, accuracy, and cost- effectiveness of the method.