• Smart Structures and Systems
• /
• v.30 no.5
• /
• pp.521-535
• /
• 2022

Efficient management of deteriorating civil infrastructure is one of the most important research topics in many developed countries. In particular, the remote displacement measurement of bridges using linear variable differential transformers, global positioning systems, laser Doppler vibrometers, and computer vision technologies has been attempted extensively. This paper proposes a remote displacement measurement system using closed-circuit televisions (CCTVs) and a computer-vision-based method for in-situ bridge bearings having relatively large displacement due to temperature change in long term. The hardware of the system is composed of a reference target for displacement measurement, a CCTV to capture target images, a gateway to transmit images via a mobile network, and a central server to store and process transmitted images. The usage of CCTV capable of night vision capture and wireless data communication enable long-term 24-hour monitoring on wide range of bridge area. The computer vision algorithm to estimate displacement from the images involves image preprocessing for enhancing the circular features of the target, circular Hough transformation for detecting circles on the target in the whole field-of-view (FOV), and homography transformation for converting the movement of the target in the images into an actual expansion displacement. The simple target design and robust circle detection algorithm help to measure displacement using target images where the targets are far apart from each other. The proposed system is installed at the Tancheon Overpass located in Seoul, and field experiments are performed to evaluate the accuracy of circle detection and displacement measurements. The circle detection accuracy is evaluated using 28,542 images captured from 71 CCTVs installed at the testbed, and only 48 images (0.168%) fail to detect the circles on the target because of subpar imaging conditions. The accuracy of displacement measurement is evaluated using images captured for 17 days from three CCTVs; the average and root-mean-square errors are 0.10 and 0.131 mm, respectively, compared with a similar displacement measurement. The long-term operation of the system, as evaluated using 8-month data, shows high accuracy and stability of the proposed system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.5
• /
• pp.631-636
• /
• 2019

Over the last decade, many researchers have investigated a number of vision-based construction object detection algorithms for the purpose of construction site monitoring. However, previous methods require the ground truth labeling, which is a process of manually marking types and locations of target objects from training image data, and thus a large amount of time and effort is being wasted. To address this drawback, this paper proposes a vision-based construction object detection framework that employs an active learning technique while reducing manual labeling efforts. For the validation, the research team performed experiments using an open construction benchmark dataset. The results showed that the method was able to successfully detect construction objects that have various visual characteristics, and also indicated that it is possible to develop the high performance of an object detection model using smaller amount of training data and less iterative training steps compared to the previous approaches. The findings of this study can be used to reduce the manual labeling processes and minimize the time and costs required to build a training database.

• Korean Journal of Remote Sensing
• /
• v.24 no.3
• /
• pp.235-243
• /
• 2008

Object tracking is a common vision task to detect and trace objects between consecutive frames. It is also important for a variety of applications such as surveillance, video based traffic monitoring system, and so on. An efficient moving vehicle clustering and tracking algorithm suitable for traffic monitoring system is proposed in this paper. First, automatic background extraction method is used to get a reliable background as a reference. The moving blob(object) is then separated from the background by mean shift method. Second, the scale invariant feature based method extracts the salient features from the clustered foreground blob. It is robust to change the illumination, scale, and affine shape. The simulation results on various road situations demonstrate good performance achieved by proposed method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.8
• /
• pp.579-584
• /
• 2016

When surgical instruments are tracked in an image-guided surgical navigation system, a stereo vision system with high accuracy is generally used, which is called optical tracker. However, this optical tracker has the disadvantage that a line-of-sight between the tracker and surgical instrument must be maintained. Therefore, to complement the disadvantage of optical tracking systems, an internal vision sensor is attached to a surgical instrument in this paper. Monitoring the target marker pattern attached on patient with this vision sensor, this surgical instrument is possible to be tracked even when the line-of-sight of the optical tracker is occluded. To verify the system's effectiveness, a series of basic experiments is carried out. Lastly, an integration experiment is conducted. The experimental results show that rotational error is bounded to max $1.32^{\circ}$ and mean $0.35^{\circ}$, and translation error is in max 1.72mm and mean 0.58mm. Finally, it is confirmed that the proposed tool tracking method using an internal vision sensor is useful and effective to overcome the occlusion problem of the optical tracker.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.12
• /
• pp.6098-6104
• /
• 2012

Currently, dozens of CCTVs are widely used in railway station for monitoring passengers in danger and security areas. The most frequent accidents occur at the platform area where passengers boarding the train. However, It is almost impossible that station operator monitors dozens of CCTV screens and recognizes immediately accidents and handle them. Therefore, railway platform monitoring system using image processing technology which automatically detects platform accidents is needed, and in order to that, preferentially, accurate determination of train state in the platform is required. In the paper, we propose train state detection algorithm for vision based railway platform monitoring system. the proposed algorithm determines four different states i.e. trains approach(IN), departure(OUT), stop(ON), and empty(OFF) of the train, in the platform. To evaluate the proposed algorithm, we present the train detection results for the Seoul Metro Line 4 Dongjak and Namtaeryeong Station.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.227-241
• /
• 2021

Object detection techniques based on deep learning such as YOLO have high detection performance and precision in a single channel video stream. In order to expand to multiple channel object detection in real-time, however, high-performance hardware is required. In this paper, we propose a novel back-end server framework, a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel to simultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assembles appropriate component modules from the RODEM (real-time object detection module) Base to create per-channel instances for each channel, enabling efficient parallelization of object detection instances on limited hardware resources through continuous monitoring with respect to resource utilization. Through practical experiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performing object detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provide object detection services with 25 FPS for all 16 channels at the same time.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.181-189
• /
• 2023

In this paper, we present a case study of developing MVIS (Machine Vision Inspection System) designed for exterior quality inspection of stamping dies used in the production of automotive exterior components in a small to medium-sized factory. While the primary processes within the factory, including machining, transportation, and loading, have been automated using PLCs, CNC machines, and robots, the final quality inspection process still relies on manual labor. We implement the MVIS with general-purpose industrial cameras and Python-based open-source libraries and frameworks for rapid and low-cost development. The MVIS can play a major role on improving throughput and lead time of stamping dies. Furthermore, the processed inspection images can be leveraged for future process monitoring and improvement by applying deep learning techniques.

• Agricultural and Biosystems Engineering
• /
• v.1 no.1
• /
• pp.22-29
• /
• 2000

The development of bio-response feedback control system known as the speaking plant approach has been a challenging task for plant production engineers and scientists. In order to achieve the aim of developing such a bio-response feedback control system, the primary concern should be to develop a practical non-invasive technique for monitoring plant growth. Those who are skilled in raising plants can sense whether their plants are under adequate water conditions or not, for example, by merely observing minor color and tone changes before the plants wilt. Consequently, using machine vision, it may be possible to recognize changes in indices that describe plant conditions based on the appearance of growing plants. The interpretation of image information of plants may be based on image features extracted from the original pictorial image. In this study, the performance of a finite element retina was optimized by a genetic algorithm. The optimized finite element retina was evaluated based on the performance of neural plant growth monitor that requires input data given by the finite element retina.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.304-309
• /
• 2015

On construction sites, it is important to monitor the performance of construction equipment and workers to achieve successful construction project management; especially, vision-based detection methods have advantages for the real-time site data collection for safety and productivity analyses. Although many researchers developed vision-based detection methods with acceptable performance, there are still limitations to be addressed: 1) sensitiveness to the shape and appearance changes of moving objects in difference working postures, and 2) high computation time. To deal with the limitations, this paper proposes a detection algorithm of construction equipment based on Integral Channel Features. For validation, 16,850 frames of video streams were recorded and analyzed. The results showed that the proposed method worked in high performance in terms of accuracy and processing time. In conclusion, the developed method can help to understand useful site information including working pattern, working time and input manpower analyses.

• Smart Structures and Systems
• /
• v.24 no.5
• /
• pp.567-585
• /
• 2019

In the past two decades, structural health monitoring (SHM) systems have been widely installed on various civil infrastructures for the tracking of the state of their structural health and the detection of structural damage or abnormality, through long-term monitoring of environmental conditions as well as structural loadings and responses. In an SHM system, there are plenty of sensors to acquire a huge number of monitoring data, which can factually reflect the in-service condition of the target structure. In order to bridge the gap between SHM and structural maintenance and management (SMM), it is necessary to employ advanced data processing methods to convert the original multi-source heterogeneous field monitoring data into different types of specific physical indicators in order to make effective decisions regarding inspection, maintenance and management. Conventional approaches to data analysis are confronted with challenges from environmental noise, the volume of measurement data, the complexity of computation, etc., and they severely constrain the pervasive application of SHM technology. In recent years, with the rapid progress of computing hardware and image acquisition equipment, the deep learning-based data processing approach offers a new channel for excavating the massive data from an SHM system, towards autonomous, accurate and robust processing of the monitoring data. Many researchers from the SHM community have made efforts to explore the applications of deep learning-based approaches for structural damage detection and structural condition assessment. This paper gives a review on the deep learning-based SHM of civil infrastructures with the main content, including a brief summary of the history of the development of deep learning, the applications of deep learning-based data processing approaches in the SHM of many kinds of civil infrastructures, and the key challenges and future trends of the strategy of deep learning-based SHM.