Integrating bridge influence surface and computer vision for bridge weigh-in-motion in complicated traffic scenarios

Abstract

Complicated traffic scenarios, including random change of vehicles’ speed and lane, as well as the simultaneous presence of multiple vehicles on bridge, are main obstacles that prevents bridge weigh-in-motion (BWIM) technique from reliable and accurate application. To tackle the complicated traffic problems of BWIM, this paper develops a novel BWIM method which integrates deep-learning-based computer vision technique and bridge influence surface theory. In this study, bridge strains and traffic videos are recorded synchronously as the data source of BWIM. The computer vision technique is employed to detect and track vehicles and corresponding axles from traffic videos so that spatio-temporal paths of vehicle loads on the bridge can be obtained. Then a novel method is proposed to identify the strain influence surface (SIS) of the bridge structure based on the time-synchronized strain signals and vehicle paths. After the SIS is identified, the axle weight (AW) and gross vehicle weight (GVW) can be identified by integrating the SIS, time-synchronized bridge strain, and vehicle paths. For illustration and verification, the proposed method is applied to identify AW and GVW in scale model experiments, in which the vehicle-bridge system is designed with high fidelity, and various complicated traffic scenarios are simulated. Results confirm that the proposed method contributes to improve the existing BWIM technique with respect to complicated traffic scenarios.

A robust bridge weigh‐in‐motion algorithm based on regularized total least squares with axle constraints

“…In this study, the vehicle trajectory is identified by using the deep-learning computer vision technique to track the vehicle, and the positioning error is within 0.5 cm (the proof can be found in Jian et al 16 ), which is small enough compared with the dimension of the bridge and truck model. Therefore, the error introduced by the vehicle tracking is trivial, and the main source of error comes from the identification of the SIS.…”

“…The cameras and strain sensors are strictly time-synchronized to realize the data fusion between the bridge strain and the axle positions. More detail about the experiments and the computer-vision-aided BWIM methodology can be found in Jian et al 16 Vehicles in the experiments are simulated with two remote-control dump truck models. As shown in Figure 4b, the 1/14-scale dump truck model has three axles, among which the rear two axles belong to an axle group.…”

“…The cameras and strain sensors are strictly time‐synchronized to realize the data fusion between the bridge strain and the axle positions. More detail about the experiments and the computer‐vision‐aided BWIM methodology can be found in Jian et al 16 …”

“…First, the accuracy of the classic BWIM approach degrades in complicated traffic scenarios where multiple vehicles are simultaneously present on the bridge, or the vehicle changes its lane and speed 10,11 . Nevertheless, this problem has been basically solved by introducing new sensing technology 9,12–15 with using the bridge influence surface theory 16–18 . Second, a number of studies 4,5,19–22 report an empirical observation that the classic BWIM algorithm is much more accurate in estimating gross vehicle weight (GVW) than axle weight (AW), and within closely spaced axle groups such as tandem and triples, the weighing errors are unacceptably large for individual axles.…”

“…10,11 Nevertheless, this problem has been basically solved by introducing new sensing technology 9,[12][13][14][15] with using the bridge influence surface theory. [16][17][18] Second, a number of studies 4,5,[19][20][21][22] report an empirical observation that the classic BWIM algorithm is much more accurate in estimating gross vehicle weight (GVW) than axle weight (AW), and within closely spaced axle groups such as tandem and triples, the weighing errors are unacceptably large for individual axles. For conciseness, this empirical observation is called the axle weighing problem of BWIM in this paper.…”