Vision-based Displacement Measurement System Research Articles

Smart structural health monitoring using computer vision and edge computing

Structural health monitoring (SHM) provides real-time data on the condition and performance of infrastructure, enabling timely and cost-effective maintenance interventions, and hence enhanced safety and extended service life. The computer vision-based non-contact sensor has emerged as a promising alternative to conventional contact-type sensors for structural displacement measurement and SHM. Many of the currently reported vision-based structural displacement measurement systems typically temporarily set up a video camera from a distance to the structure. The collected images or videos are usually stored locally and post-processed offline to obtain structural displacement responses, which is cumbersome and limited to short-term SHM applications. The recent development of technologies empowered by the Internet of Things (IoT) and edge computing has enabled real-time video processing and analysis at the source, minimizing latency, reducing bandwidth requirements, and enabling prompt decision-making, thereby enhancing efficiency and responsiveness compared to traditional offline video recording and processing systems. In this paper, an edge computing vision-based displacement measurement system (EdgeCVDMS) is developed. Video recording, processing, and displacement response identification are entirely performed on an edge device integrated with the vision-based displacement tracking algorithm, thereby greatly reducing the amount of data transmitted to the cloud server. The feasibility and applicability of the developed sensing system are experimentally validated on a laboratory-scaled transmission tower structure. The proposed EdgeCVDMS is cost-effective, easily deployable, and of great potential to be applied for the condition assessment of a larger population of aging civil infrastructure.

Reliability Assessment of a Vision-Based Dynamic Displacement Measurement System Using an Unmanned Aerial Vehicle.

In recent years, many studies have been conducted on the vision-based displacement measurement system using an unmanned aerial vehicle, which has been used in actual structure measurements. In this study, the dynamic measurement reliability of a vision-based displacement measurement system using an unmanned aerial vehicle was examined by measuring various vibrations with a frequency of 0 to 3 Hz and a displacement of 0 to 100 mm. Furthermore, free vibration was applied to model structures with one and two stories, and the response was measured to examine the accuracy of identifying structural dynamic characteristics. The vibration measurement results demonstrated that the vision-based displacement measurement system using an unmanned aerial vehicle has an average root mean square percentage error of 0.662% compared with the laser distance sensor in all experiments. However, the errors were relatively large in the displacement measurement of 10 mm or less regardless of the frequency. In the structure measurements, all sensors demonstrated the same mode frequency based on the accelerometer, and the damping ratios were extremely similar, except for the laser distance sensor measurement value of the two-story structure. Mode shape estimation was obtained and compared using the modal assurance criterion value compared with the accelerometer, and the values for the vision-based displacement measurement system using an unmanned aerial vehicle were close to 1. According to these results, the vision-based displacement measurement system using an unmanned aerial vehicle demonstrated results similar to those of conventional displacement sensors and can thus replace conventional displacement sensors.

A Vision-Based Displacement Measurement System for Foundation Pit

A Vision-Based Displacement Measurement System for Foundation Pit

Reliability verification of a vision-based dynamic displacement measurement for system identification

In this paper, dynamic experiments of various amplitudes with a broad band of frequencies were carried out using a shaking table in order to validate the wide-range reliability of a vision-based displacement measurement system. In addition, the dynamic characteristics of a multiple-degree-of-freedom model structures were estimated using the vision-based measurement method. As a result of error analysis through comparison with a laser displacement sensor (LDS), it was determined that the accuracy of dynamic displacement measurement by the camcorder in the vision-based system is affected by the frequency of the measurement object. From these results, it is judged that the CMOS sensor type has the rolling shutter effect when the velocity between the model structure and the camcorder is high. The accuracy of dynamic characteristics estimation was determined by comparing the dynamic characteristics estimated using the LDSs and the accelerometers. The vision-based measurement system using the camcorder in both time domain and frequency domains showed very similar results to the existing LDS and accelerometer measurements.

Comparative study on displacement measurement sensors for high-speed railroad bridge

This paper presents a comparative study of displacement measurement using four sensors that are being used in the field: they are a ring gauge, a laser Doppler vibrometer (LDV), a vision-based displacement measurement system (VDMS), and an optoelectronic displacement meter (ODM). The comparative study was carried out on a brand-new high-speed railroad bridge designed to produce displacements within a couple of millimeters under the loading of a high-speed train. The tests were carried out on a single-span steel plate girder bridge two times with different train loadings: KTX and HEMU. The measured displacement is compared as raw and further discussion was made on the measurement noise, peak displacement, and frequency response of four sensors. The comparisonsare summarized to show the pros and cons of the used sensors in measuring displacement at a typical high-speed railroad bridge.

Computer Vision-based Displacement Measurement Method With Arbitrarily Positioned Camera

Displacement is broadly used in structural health monitoring as a meaningful indicator of structural status. Measuring structural displacement using conventional devices such as the linear variable differential transformer is challenging due to practical issues such as equipment inaccessibility, insufficient measurement accuracy, or expensive system cost. Recently, computer vision-based displacement measurement methods have been developed to build high field applicable measurement system. However, the existing computer vision-based displacement measurementtechniques still have practical issues such as absence of camera installation point, marker attachment, or lightinduced error. This paper presents a computer vision-based displacement measurement system focusing on solving camera positioning issue. The proposed method adopts homography transform to allow cameras to be positioned at arbitrary point. A laboratory scale experiment was conducted to verify accurate displacement measurement of the proposed method with the arbitrarily positioned camera.

Measurement of Dynamic Characteristics on Structure using Non-marker Vision-based Displacement Measurement System

Measurement of Dynamic Characteristics on Structure using Non-marker Vision-based Displacement Measurement System

Rotational Angle Measurement of Bridge Support Using Image Processing Techniques

Measuring a very small rotational angle accurately and dynamically is indeed a challenging issue, especially in the case of bridge support. Also, existing inclinometers do not have sufficient resolution and accuracy to measure a bridge’s rotational angle. In this study, a new measurement system was developed to provide a practical means for measuring dynamic rotational angle of a bridge support. It features high resolution and accuracy compared with the available systems on the market. By the combinational use of a laser pointer and a vision-based displacement measurement system, the measurement accuracy was significantly increased. The accuracy and applicability were investigated through laboratory tests. From the laboratory tests, it has been found that the developed system can be applicable to bridge support with very small rotational angle. The effectiveness of the developed system was verified through field tests on real bridges. From the full-scale implementation on two PSC girder bridges, it is observed that the proposed system can measure the rotational angle with a high accuracy and reliability.

"임의의 위치에서 사용가능한 영상 기반 변위 계측 시스템"의 정오표

"임의의 위치에서 사용가능한 영상 기반 변위 계측 시스템"의 정오표

임의의 위치에서 사용 가능한 영상 기반 변위 계측 시스템

In this study, a vision-based displacement measurement system is developed to accurately measure the displacement of a structure with locating the camera at arbitrary position. The previous vision-based system brings error when the optical axis of a camera has an angle with the measured structure, which limits the applicability at large structures. The developed system measures displacement by processing the images of a target plate that is attached on the measured position of a structure. To measure displacement regardless of the angle between the optical axis of the camera and the target plate, planar homography is employed to match two planes in image and world coordinate systems. To validate the performance of the present system, a laboratory test is carried out using a small 2-story shear building model. The result shows that the present system measures accurate displacement of the structure even with a camera significantly angled with the target plate.

영상 기반 변위 계측장치의 현장 적용 성능 평가

The on-site performance of a vision-based displacement measurement system (VDMS) was evaluated through a field test on a bridge. The VDMS used in this study is composed of a camera, a marker, a frame grabber, and a laptop. The system measures the displacement by attaching a marker at the location to be measured on the structure, by capturing images of that marker with a fixed rate, and by processing a series of images using a planar homography technique. The developed system was first validated from a laboratory test using a small-scale building structure. The VDMS was then employed in a field test on a railroad bridge with a KTX train running under various conditions. The on-site performance was evaluated by comparing the obtained displacement using the VDMS with the displacement measured from a laser Doppler vibrometer (LDV), which is an expensive and accurate displacement measurement device.

Vision-based remote 6-DOF structural displacement monitoring system using a unique marker

Structural displacement is an important indicator for assessing structural safety. For structural displacement monitoring, vision-based displacement measurement systems have been widely developed; however, most systems estimate only 1 or 2-DOF translational displacement. To monitor the 6-DOF structural displacement with high accuracy, a vision-based displacement measurement system with a uniquely designed marker is proposed in this paper. The system is composed of a uniquely designed marker and a camera with a zooming capability, and relative translational and rotational displacement between the marker and the camera is estimated by finding a homography transformation. The novel marker is designed to make the system robust to measurement noise based on a sensitivity analysis of the conventional marker and it has been verified through Monte Carlo simulation results. The performance of the displacement estimation has been verified through two kinds of experimental tests; using a shaking table and a motorized stage. The results show that the system estimates the structural 6-DOF displacement, especially the translational displacement in Z-axis, with high accuracy in real time and is robust to measurement noise.

Dynamic testing of a laboratory model via vision-based sensing

In the class of not-contact sensors, the techniques of vision-based displacement estimation enable one to gather dense global measurements of static deformation as well as of dynamic response. They are becoming more and more available thanks to the ongoing technology developments. In this work, a vision system, which takes advantage of fast-developing digital image processing and computer vision technologies and provides high sample rate, is implemented to monitor the 2D plane vibrations of a reduced scale frame mounted on a shaking table as available in a laboratory. The physical meanings of the camera parameters, the trade-off between the system resolution and the field-of-view, and the upper limitation of marker density are discussed. The scale factor approach, which is widely used to convert the image coordinates measured by a vision system in the unit of pixels into space coordinates, causes a poor repeatability of the experiment, an unstable experiment precision, and therefore a global poor flexibility. To overcome these problems, two calibrations approaches are introduced: registration and direct linear transformation. Based on the constructed vision-based displacement measurement system, several experiments are carried out to monitor the motion of a scale-reduced model on which dense markers are glued. The experiment results show that the proposed system can capture and successfully measure the motion of the laboratory model within the required frequency band.

Vision-Based Displacement Sensor for Monitoring Dynamic Response Using Robust Object Search Algorithm

This paper develops a vision-based displacement measurement system for remote monitoring of vibration of large-size 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 Estimation from Acceleration Measurements Using a Wireless Smart Sensor

A displacement measurement provides useful information for structural health monitoring (SHM) as it is directly related to stiffness of the structure. Most existing methods of direct measurement such as the Laser Doppler Vibrometer (LDV) and the Liner Variable Differential Transformer (LVDT) are known to have accurate performance but have difficulties particularly in the use of large-scale civil structures as the methods rely on fixed reference points. Alternatively, indirect methods have been developed and widely used methods are Global Positioning System (GPS), vision-based displacement measurement system and displacement estimation from acceleration record. Among the indirect method, the use of accelerometer provides simple and economical in term of both hardware installation and operation. The major problem using acceleration based displacement estimation is low frequency drift caused by double integration. Recently, dynamic displacement estimation algorithm that addresses low-frequency drift problem has been developed. This study utilizes Wireless Smart Sensor (WSN) for estimating dynamic displacement from acceleration measurement in combination with the recently developed displacement estimation algorithm. Integrated into WSN that are low-cost, wireless, compatible with accelerometers, and capable of onboard computation, the displacement can be measured without limit of location on large-scale civil structures. Thus, this approach has the significant potential to impact many applications that require displacement measurements. With the displacement estimation algorithm embedded, the WSN performs in-network data processing to estimate displacements at each distributed sensor location wirelessly using only measured acceleration data. To experimentally validate the performance of displacement estimation using WSN for the use in structures with multiple-degree of freedom, the random vibration test is conducted on the three-story shear building model. The estimated displacement is compared with the reference displacements measured from the laser displacement sensor and the result shows good agreement.

An advanced vision-based system for real-time displacement measurement of high-rise buildings

This paper introduces an advanced vision-based system for dynamic real-time displacement measurement of high-rise buildings using a partitioning approach. The partitioning method is based on the successive estimation of relative displacements and rotational angles at several floors using a multiple vision-based displacement measurement system. In this study, two significant improvements were made to realize the partitioning method: (1) time synchronization, (2) real-time dynamic measurement. Displacement data and time synchronization information are wirelessly transferred via a network using the TCP/IP protocol. The time synchronization process is periodically conducted by the master system to guarantee the system time at the master and slave systems are synchronized. The slave system is capable of dynamic real-time measurement and it is possible to economically expand measurement points at slave levels using commercial devices. To verify the accuracy and feasibility of the synchronized multi-point vision-based system and partitioning approach, many laboratory tests were carried out on a three-story steel frame model. Furthermore, several tests were conducted on a five-story steel frame tower equipped with a hybrid mass damper to experimentally confirm the effectiveness of the proposed system.

Cost-effective vision-based system for monitoring dynamic response of civil engineering structures

This study develops a cost-effective vision-based displacement measurement system for real-time monitoring of dynamic responses of large-size civil engineering structures such as bridges and buildings. The system simply consists of a low-cost digital camcorder and a notebook computer equipped with digital image-processing software developed in this study. A target panel with predesigned marks is attached to a structure, whose movement is captured by the digital camcorder placed at a fixed point away from the measurement point. The captured images are streamed to the notebook computer and processed by the software to compute displacement in real time. The efficacy of the system in measuring dynamic responses was demonstrated through laboratory tests, seismic shaking table tests on a steel building frame, and a field experiment on a bridge. In order to simultaneously measure displacements of multiple points, this study further developed a time synchronization system, in which TCP/IP protocol is employed for communications. The effectiveness of the time synchronization system was also experimentally verified. The vision-based system developed in this study is simple, cost-effective, easy to install, and capable of real-time measurement of dynamic responses, making the system ideal for monitoring civil engineering structures. Copyright © 2009 John Wiley & Sons, Ltd.

Development and application of a vision-based displacement measurement system for structural health monitoring of civil structures

For structural health monitoring (SHM) of civil infrastructures, displacement is a good descriptor of the structural behavior under all the potential disturbances. However, it is not easy to measure displacement of civil infrastructures, since the conventional sensors need a reference point, and inaccessibility to the reference point is sometimes caused by the geographic conditions, such as a highway or river under a bridge, which makes installation of measuring devices time-consuming and costly, if not impossible. To resolve this issue, a vision-based real-time displacement measurement system using digital image processing techniques is developed. The effectiveness of the proposed system was verified by comparing the load carrying capacities of a steel-plate girder bridge obtained from the conventional sensor and the present system. Further, to simultaneously measure multiple points, a synchronized vision-based system is developed using master/slave system with wireless data communication. For the purpose of verification, the measured displacement by a synchronized vision-based system was compared with the data measured by conventional contact-type sensors, linear variable differential transformers (LVDT) from a laboratory test.