Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring

Computer vision for SHM of civil infrastructure: From dynamic response measurement to damage detection – A review

A literature review of next-generation smart sensing technology in structural health monitoring

Structural health monitoring at local and global levels using computer vision technologies has gained much attention in the structural health monitoring community in research and practice. Due to t...

A review of computer vision–based structural health monitoring at local and global levels:

Vision-based systems are promising tools for displacement measurement in civil structures, possessing advantages over traditional displacement sensors in instrumentation cost, installation efforts and measurement capacity in terms of frequency range and spatial resolution. Approximately one hundred papers to date have appeared on this subject, investigating topics like system development and improvement, the viability on field applications and the potential for structural condition assessment. The main contribution of this paper is to present a literature review of vision-based displacement measurement, from the perspectives of methodologies and applications. Video-processing procedures in this paper are summarised as a three-component framework: camera calibration, target tracking and structural displacement calculation. Methods for each component are presented in principle, with discussions about the relative advantages and limitations. Applications in the two most active fields, bridge deformation and cable vibration measurement, are examined followed by a summary of field challenges observed in monitoring tests. Important gaps requiring further investigation are presented, e.g. robust tracking methods, non-contact sensing and measurement accuracy evaluation in field conditions.

/pdf/review-of-machine-vision-based-methodologies-for-591lcxjedi.pdf

Review of machine-vision based methodologies for displacement measurement in civil structures

FBG-Based Structural Performance Monitoring and Safety Evaluation of a Composite Arch Bridge

Most of the vision-based structural identification research focus either on structural input (vehicle location) or output (structural responses) estimation. Combining the vision-based structural input and output from conventional sensors, though gives a normalized response irrespective of the type or load of the vehicles, cost, time, and labor force, are necessary and tedious. Bridge closure is essential and may cause severe problems such as traffic jam of critical urban routes. In this study, a completely non-contact structural identification framework is proposed. Both the structural input and output are obtained by just using cameras and computer vision techniques. The proposed system is verified with a laboratory experiment on a two-span bridge under a moving load. The unit influence line of the two-span bridge is successfully identified and can be used for damage detection.

A Full Version of Vision-Based Structural Identification

This study proposes a data-driven method that detects cable damage from measured cable forces by recognizing biased patterns from the intact conditions. The proposed method solves the pattern recognition problem for cable damage detection through time series classification (TSC) in deep learning, considering that the cable's behavior can be implicitly represented by the measured cable force series. A deep learning model, long short term memory fully convolutional network (LSTM-FCN), is leveraged by assigning appropriate inputs and representative class labels for the TSC problem, First, a TSC classifier is trained and validated using the data collected under intact conditions of stay cables, setting the segmented data series as input and the cable (or cable pair) ID as class labels. Subsequently, the classifier is tested using the data collected under possible damaged conditions. Finally, the cable or cable pair corresponding to the least classification accuracy is recommended as the most probable damaged cable or cable pair. The proposed method was tested on an in-service cable-stayed bridge with damaged stay cables. Two scenarios in the proposed TSC scheme were investigated: 1) raw time series of cable forces were fed into the classifiers; and 2) cable force ratios were inputted in the classifiers considering the possible variation of force distribution between cable pairs due to cable damage. Combining the results of TSC testing in these two scenarios, the cable with rupture was correctly identified. This study proposes a data-driven methodology for cable damage detection that requires the least data preprocessing and feature engineering, which enables fast and convenient early detection in real applications.

Chuan-Zhi Dong

Papers

FBG-Based Structural Performance Monitoring and Safety Evaluation of a Composite Arch Bridge

A Full Version of Vision-Based Structural Identification

Condition Assessment of Stay Cables through Enhanced Time Series Classification Using a Deep Learning Approach.