Integration of computer imaging and sensor data for structural health monitoring of bridges

Abstract

The condition of civil infrastructure systems (CIS) changes over their life cycle for different reasons such as damage, overloading, severe environmental inputs, and ageing due normal continued use. The structural performance often decreases as a result of the change in condition. Objective condition assessment and performance evaluation are challenging activities since they require some type of monitoring to track the response over a period of time. In this paper, integrated use of video images and sensor data in the context of structural health monitoring is demonstrated as promising technologies for the safety of civil structures in general and bridges in particular. First, the challenges and possible solutions to using video images and computer vision techniques for structural health monitoring are presented. Then, the synchronized image and sensing data are analyzed to obtain unit influence line (UIL) as an index for monitoring bridge behavior under identified loading conditions. Subsequently, the UCF 4-span bridge model is used to demonstrate the integration and implementation of imaging devices and traditional sensing technology with UIL for evaluating and tracking the bridge behavior. It is shown that video images and computer vision techniques can be used to detect, classify and track different vehicles with synchronized sensor measurements to establish an input-output relationship to determine the normalized response of the bridge.

A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure

“…Zaurin et al [3] used video imagery and bridge responses collected by strain gauges and fused them together to detect loss of connectivity between different composite sections, and change in boundary conditions. In the process, unit influence line of the bridge is extracted and statistical outlier detection is done to differentiate damage state from the baseline state.…”

“…digital cameras), the rate of creation and deployment of computer vision methods for civil engineering applications has been exponentially increasing over the last decade. Computer vision modules, for example, are becoming an integral component of modern Structural Health Monitoring (SHM) frameworks [3]. In this regards, the second and largest part of the paper presents a comprehensive synthesis of the state of the art in computer vision based defect detection and condition assessment of civil infrastructure.…”

Framework for Flexural Rigidity Estimation in Euler-Bernoulli Beams Using Deformation Influence Lines

“…First, the desired response (e.g., vertical deflection or rotation) of a specific location is recorded. Then, by synchronizing the recorded measurement with the location of moving loads (e.g., vehicular loads) and solving an inverse problem, the influence line, u A (ξ), of a unit load can be extracted [10][11][12]19,[21][22][23].…”

“…Algorithms utilizing appropriate structural health indices may increase the SHM classification level and aid engineers in adequately rating structural condition. Appropriate indices include the following essential features [10][11][12][13] 1.…”

An Improved Neuron Segmentation Model for Crack Detection – Image Segmentation Model

“…However, continuous inspection and assessment on the physical and functional conditions of existing civil infrastructure is essential to ensure the safety and serviceability for preventing such kinds of accidents, but is impossible for typically manual operation. Computer vision-based modules, an integral component of modern Structural Health Monitoring (SHM) framework [4], has been adopted to automate the process of defect and damage detection (especially for common crack detection) due to the availability of low cost, high quality and easyto-use visual sensing technologies (e.g., digital cameras).…”