• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.120-129
• /
• 2023

Hanger cable tension is a major response that can determine the integrity and safety of suspension bridges. In general, the vibration method is used to estimate hanger cable tension on operational suspension bridges. It measures natural frequencies from hanger cables and indirectly estimates tension using the geometry conditions of the hanger cables. This study estimated the hanger cable tension of the Palyeong Bridge using a vision-based system. The vision-based system used digital camcorders and tripods considering the convenience and economic efficiency of measurement. Measuring the natural frequencies for high-order modes required for the vibration method is difficult because the hanger cable response measured using the vision-based system is displacement-based. Therefore, this study proposed a back analysis technique for estimating tension using the natural frequencies of low-order modes. Optimization for the back analysis technique was performed by defining the difference between the natural frequencies of hanger cables measured in the field and those calculated using finite element analysis as the objective function. The direct search method that does not require the partial derivatives of the objective function was applied as the optimization method. The reliability and accuracy of the back analysis technique were verified by comparing the tension calculated using the method with that estimated using the vibration method. Tension was accurately estimated using the natural frequencies of low-order modes by applying the back analysis technique.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.25 no.2
• /
• pp.110-116
• /
• 2005

It is very important to reduce the computational processing time for the application of the vision system in real time such as inspection, the determination of object's dimension and welding etc, because the vision system model involves a lot of measurement data acquired by CCD camera. Also, a lot of computation time is required in estimating the parameters in the vision system model if the iterative batch estimation method such as Newton Raphson is used. Thus, the effective computation method such as the Extended Kalman Filtering(EKF) is required to solve the above problems. The EKF has much advantages in that it takes explicitly into account the measurement uncertainties, and is a simple and efficient recursive procedures. Thus, this study is to develop the EKF algorithm to compute the parameters in the vision system model in real time. This vision system model involves the six parameters to account for the cameras inner and outer parameters. Also the EKF is applied to estimate the object's dimension. Finally, practicality of the estimation scheme of the vision system based on the EKF is verified experimently by performing the estimation of object's dimension.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.6
• /
• pp.810-812
• /
• 2014

In this paper, a hagwon-bus boarding danger warning system based on computer vision is proposed to protect children from an accident causing injuries or death. Three zones are defined and different algorithms are applied to detect moving objects. In zone 1, a block-based entropy value is calculated using the absolute difference image generated by the absolute differential estimation between background image and incoming video frame. In zone 2, an effective and robust motion object tracking algorithm is performed based on the particle filter. Experimental results demonstrate the efficient and effectively of the algorithm for moving object inspection in each zone.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.25 no.4
• /
• pp.321-327
• /
• 2012

To evaluate whether or not their product is in conformity with its drawing, today's factories manufacturing rubber and/or plastic products use manual process. In manual conformity inspection process, a person decides conformity as comparing drawing to image of product with his eyes. The manual process is tedious and time-consuming in addition that it is impossible to automatically record various informations related to inspection. To solve such problems, this paper proposes automatic drawing conformity inspection system based on computer vision technologies such as image feature matching and bilinear interpolation. The test results show that proposed system is a lot faster when comparing with manual system.

• Journal of the Korean Society of Industry Convergence
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2014

This paper describes a new technology to develop the character recognition technology based on pattern recognition for non-contacting inspection optical lens slant or precision parts, and including external form state of lens or electronic parts for the performance verification, this development can achieve badness finding. And, establish to existing reflex data because inputting surface badness degree of scratch's standard specification condition directly, and error designed to distinguish from product more than schedule error to badness product by normalcy product within schedule extent after calculate the error comparing actuality measurement reflex data and standard reflex data mutually. Developed system to smallest 1 pixel unit though measuring is possible 1 pixel as $37{\mu}m{\times}37{\mu}m$ ($0.1369{\times}10-4mm^2$) the accuracy to $1.5{\times}10-4mm$ minutely measuring is possible performance verification and trust ability through an experiment prove.

• Smart Structures and Systems
• /
• v.33 no.1
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• Smart Structures and Systems
• /
• v.5 no.4
• /
• pp.469-482
• /
• 2009

The emerging sensor-based structural health monitoring (SHM) technology has a potential for cost-effective maintenance of aging civil infrastructure systems. The author proposes to integrate continuous and global monitoring using on-structure sensors with targeted local non-destructive evaluation (NDE). Significant technical challenges arise, however, from the lack of cost-effective sensors for monitoring spatially large structures, as well as reliable methods for interpreting sensor data into structural health conditions. This paper reviews recent efforts and advances made in addressing these challenges, with example sensor hardware and health monitoring software developed in the author's research center. The hardware includes a novel fiber optic accelerometer, a vision-based displacement sensor, a distributed strain sensor, and a microwave imaging NDE device. The health monitoring software includes a number of system identification methods such as the neural networks, extended Kalman filter, and nonlinear damping identificaiton based on structural dynamic response measurement. These methods have been experimentally validated through seismic shaking table tests of a realistic bridge model and tested in a number of instrumented bridges and buildings.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.81-86
• /
• 2023

Recently, there has been an increased demand for light-emitting diode (LED) due to the growing emphasis on environmental protection. However, the use of GaN-based sapphire in LED manufacturing leads to the generation of defects, such as dislocations caused by lattice mismatch, which ultimately reduces the luminous efficiency of LEDs. Moreover, most inspections for LED semiconductors focus on evaluating the luminous efficiency after packaging. To address these challenges, this paper aims to detect defects at the wafer stage, which could potentially improve the manufacturing process and reduce costs. To achieve this, image processing and deep learning-based defect detection techniques for Sapphire Epi-Wafer used in Green LED manufacturing were developed and compared. Through performance evaluation of each algorithm, it was found that the deep learning approach outperformed the image processing approach in terms of detection accuracy and efficiency.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.325-334
• /
• 2023

Computer vision-based damage detection enables non-contact, efficient and low-cost bridge health monitoring, which reduces the need for labor-intensive manual inspection or that for a large number of on-site sensing instruments. By leveraging recent semantic segmentation approaches, we can detect regions of critical structural components and identify damages at pixel level on images. However, existing methods perform poorly when detecting small and thin damages (e.g., cracks); the problem is exacerbated by imbalanced samples. To this end, we incorporate domain knowledge to introduce a hierarchical semantic segmentation framework that imposes a hierarchical semantic relationship between component categories and damage types. For instance, certain types of concrete cracks are only present on bridge columns, and therefore the noncolumn region may be masked out when detecting such damages. In this way, the damage detection model focuses on extracting features from relevant structural components and avoid those from irrelevant regions. We also utilize multi-scale augmentation to preserve contextual information of each image, without losing the ability to handle small and/or thin damages. In addition, our framework employs an importance sampling, where images with rare components are sampled more often, to address sample imbalance. We evaluated our framework on a public synthetic dataset that consists of 2,000 railway bridges. Our framework achieves a 0.836 mean intersection over union (IoU) for structural component segmentation and a 0.483 mean IoU for damage segmentation. Our results have in total 5% and 18% improvements for the structural component segmentation and damage segmentation tasks, respectively, compared to the best-performing baseline model.