Acceleration‐Based Automated Vehicle Classification on Mobile Bridges

Abstract

Mobile bridges have been used for a broad range of applications including military transportation or disaster restoration. Because mobile bridges are rapidly deployed under a wide variety of conditions, often remaining in place for just minutes to hours, and have irregular usage patterns, a detailed record of usage history is important for ensuring structural safety. To facilitate usage data collection in mobile bridges, a new acceleration-based vehicle classification technique is proposed to automatically identify the class of each vehicle. Herein we present a new technique that is based on the premise that each class of vehicles produces distinctive dynamic patterns while crossing this mobile bridge, and those patterns can be extracted from the system's acceleration responses. Measured acceleration signals are converted to time-frequency images to extract twodimensional patterns. The Viola-Jones object detection algorithm is applied here to extract and classify those patterns. The effectiveness of the technique is investigated and demonstrated using laboratory and full-scale mobile bridges by simulating realistic scenarios.

Edge‐Enhanced Matching for Gradient‐Based Computer Vision Displacement Measurement

“…Vision sensors, among these new techniques, have been broadly applied for civil engineering problems. Famous applications of vision‐sensing techniques include dynamic displacement monitoring (Cha et al., ; Park et al., ; Yoon et al., ), three‐axes (i.e., X‐axis, Y‐axis, and depth) displacement measurement (Park et al., ; Abdelbarr et al., ), surface displacement/strain measurement (Luo et al., ; Almeida et al., ), vision‐based structural analysis (Chen et al., ; Sharif et al., ; Park et al., ), cable tensile force evaluation (Kim et al., ), bridge‐lining inspection (Zhu et al., ), rocking motion and landslide monitoring (Debella‐Gilo and Kääb, ; Greenbaum et al., ), automatic construction progress assessment (Bügler et al., ), 3D object finding in point cloud (Sharif et al., ), surface crack/defection detection based on texture‐based video processing (Cord and Chambon, ; Chen et al., ) or deep learning (Cha et al., ; Cha et al, ; Zhang et al., ), vehicle classification based on spectrogram features (Yeum et al., ), and intelligent transportation (Chen et al., ; Fernandez‐Llorca et al., ). With advancement in image sensors and computer techniques such as computer vision, cloud computing, and wireless data transfer, vision sensors have become more cost‐effective and computation‐efficient, thus have high potential in field application for SHM problems.…”

Probabilistic vehicle weight estimation using physics‐constrained generative adversarial network

“…BWIM uses the bridge responses to estimate vehicle weight while the vehicle passes through the bridge. BWIM has several advantages over pavement‐based WIM and has been receiving increasing attention from both industry and research community (Lydon et al., 2016; Yeum et al., 2016; Yu et al., 2016).…”

A Vibration-Based Vehicle Classification System using Distributed Optical Sensing Technology

“…Using accelerometers and magnetometers, Ma et al developed a wireless automatic vehicle classification prototype system and used a filter algorithm to identify axles ( 4 ). Additionally, Yeum et al used a Viola-Jones algorithm to extract and classify the distinctive dynamic patterns of different vehicles by converting the measured acceleration signals to time-frequency images ( 9 ). Markus and Hostettler also used the frequency-domain features to detect and classify vehicles ( 10 ).…”