Reidentification of Trucks in Highway Corridors using Convolutional　Neural Networks to Link Truck Weights to Bridge Responses

摘要

The widespread availability of cost-effective sensing technologies is translating into an increasing number of highwaybridges being instrumented with structural health monitoring (SHM) systems. Current bridge SHM systems are onlycapable of measuring bridge responses and lack the ability to directly measure the traffic loads inducing bridge responses.The output-only nature of the monitoring data available often leaves damage detection algorithms ill-posed and incapableof robust detection. Attempting to overcome this challenge, this study leverages state-of-the-art computer vision techniquesto establish a means of reliably acquiring load data associated with the trucks inducing bridge responses. Using a cyberenabledhighway corridor consisting of cameras, bridge monitoring systems, and weigh-in-motion (WIM) stations,computer vision methods are used to track trucks as they excite bridges and pass WIM stations where their weightparameters are acquired. Convolutional neural network (CNN) methods are used to develop automated vehicle detectorsembedded in GPU-enabled cameras along highway corridors to identify and track trucks from real-time traffic video.Detected vehicles are used to trigger the bridge monitoring systems to ensure structural responses are captured when truckspass. In the study, multiple one-stage object detection CNN architectures have been trained using a customized dataset toidentify various types of vehicles captured at multiple locations along a highway corridor. YOLOv3 is selected for itscompetitive speed and precision in identifying trucks. A customized CNN-based embedding network is trained followinga triplet architecture to convert each truck image into a feature vector and the Euclidean distance of two feature vectors isused as a measure of truck similarity for reidentification purposes. The performance of the CNN-based feature extract isproved to be more robust than a hand-crafted method. Reidentification of the same vehicle allows truck weights measuredat the WIM station to be associated with measured bridge responses collected by bridge monitoring systems.