Volume 17, No. 4, 2023
Received: 2023/02/10, Accepted: 2023/08/15
Authors:
Chao Wang; Gui-Ning Han; Tian-Yu Qi; Qing-Xiang Yang;
Abstract:
Accurately identifying the vehicle load on the bridge plays an important role in structural stress analysis and safety evaluation. And the extraction of the spatiotemporal information of the vehicle is a crucial issue for identifying the vehicle load. A vehicle spatiotemporal information identification method based on machine vision technology is proposed. Firstly, digital video surveillance cameras are installed in front and side of the monitoring section to capture real-time video of vehicles passing through the monitoring section. Based on the frontal video, the background difference method is used to detect vehicle. Then the transverse position is evaluated according to the distance between the vehicle�s license plate and the lane line. Based on the lateral video and the auxiliary lines with a known distance, other vehicle parameters, including the vehicle�s speed, the number of axles, and the wheelbase, are identified. Secondly, a laboratory model experiment and a field test are carried out to validate the efficiency and accuracy of the proposed method. The results show that the proposed method can conveniently and efficiently identify spatiotemporal information with high accuracy.
Keywords:
machine vision; spatiotemporal information; load identification; orthotropic deck; bridge engineering