Vision-based displacement sensor for monitoring dynamic response using robust object search algorithm

Abstract

This paper develops a vision-based displacement measurement system for remote monitoring of vibration of largesize structures such as bridges and buildings. The system consists of one or multiple video cameras and a notebook computer. With a telescopic lens, the camera placed at a stationary point away from a structure captures images of an object on the structure. The structural displacement is computed in real time through processing the captured images. A robust object search algorithm developed in this paper enables accurate measurement of the displacement by tracking existing features on the structure without requiring a conventional target panel to be installed on the structure. A sub-pixel technique is also proposed to further reduce measurement errors cost-effectively. The efficacy of the vision system in remote measurement of dynamic displacements was demonstrated through a shaking table test and a field experiment on a long-span bridge.

Dynamic displacement measurement of large-scale structures based on the Lucas–Kanade template tracking algorithm

“…Screw is an important part which is widely used in engineering and large-scale structures. As reported in [16], when the target panel is difficult to install, specific features or components, such as screws and gusset plates, can be regarded as the tracking object. Here, we take the screw as the template for tracking.…”

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

“…The proposed EEM technique is robust in tracking low‐contrast features due to utilization of edge information in the form of EEM codes, which contain gradient magnitudes and orientations, rather that pixel intensities directly. Research in literature has shown similarity matching can be made robust by using pixel gradients rather than pixel intensities (Freeman and Roth, ; Kaneko et al., ; Fukuda et al., ).…”

“…The authors’ team previously developed the orientation code matching (OCM) technique, which uses gradient information of images to achieve robust displacement measurement against lighting changes in tracking artificial target (Fukuda et al., ). Upon validating its robustness in template matching against illumination change and occlusion, the OCM was further applied to measurements of bridge displacements in the field (Feng et al., ; Feng and Feng, ).…”

Vision-based multipoint displacement measurement for structural health monitoring

“…Sensors currently available for measuring structural displacements can be classified as contact‐type (e.g., linear variable differential transformer) and noncontact‐type (e.g., GPS, laser vibrometer, and radar interferometry system) sensors . The contact sensor requires physical access to structures to install the sensor and connect it to a stationary reference point, which is often difficult or even impossible to locate.…”

“…Moreover, these sensors need to be wired to external devices for data acquisition and power supply, making the installation even more cumbersome, time‐consuming, and costly. The GPS sensors are easier to install but the measurement accuracy is limited, usually with errors in the range of 5 mm and 10 mm . The noncontact laser vibrometer/displacement sensor is generally accurate, but it is not only costly but also has limited measurement distance (typically less than five meters) because longer distance measurement would require the use of a higher‐intensity laser beam that endangers human health .…”