• Smart Structures and Systems
• /
• 제5권4호
• /
• 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.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• 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
• /
• 제31권4호
• /
• 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.

• 한국지능시스템학회논문지
• /
• 제22권1호
• /
• pp.87-93
• /
• 2012

본 논문에서는 TCP/COF의 불량패턴 검출 알고리즘을 제안하고 실시간 검사 시스템을 구현하였다. TCP/COF는 마이크로미터 단위의 패턴 굵기를 갖는 관계로 검사를 위해서는 작업자가 고성능 현미경을 보며 전수 검사 해야 하는 어려움이 있다. 이에 본 연구에서는 작업자로 하여금 모니터를 보면서 검사시스템이 검출해내는 불량에 대해서 검사할 수 있는 시스템을 제안하였다. 검사 알고리즘은 기준 영상과 검사 영상간의 패턴 비교 방법에 의해 수행된다. TCP/COF의 특성에 맞는 고성능 카메라 및 조명시스템을 구현하기 위하여 카메라의 종류와 조명의 형태 및 광원에 따른 다양한 실험을 수행하였다. 실험결과 구현된 검사 시스템은 TCP/COF 필름의 불량 위치를 작업자에게 정확하게 알려줌을 확인할 수 있었다.

• 한국구조물진단유지관리공학회 논문집
• /
• 제28권3호
• /
• pp.1-9
• /
• 2024

본 연구는 대기외란 조건에서 비전센서를 활용하여 구조물의 동적 변위 측정을 위하여 멀티스케일 템플릿 매칭 기법 (TMI: Template Matching with Image pyramids)을 제안하고 제안기법의 변위 측정 성능을 조사하기 위해 진행되었다. 촬영거리에 따른 변위 측정 성능을 평가하기 위해 3층 전단 구조물을 설계하였으며, FHD(1920×1080)급 카메라를 준비하여 변위 계측에 사용하였다. 최초 촬영거리를 10m로 설정하였고, 10m씩 멀어지면서 최대 40m까지 변위 측정 실험을 진행하였다. 실내 조도 조건(450lux)에서 발열 기구를 활용하여 대기외란을 발생시켰으며, 대기외란으로 이미지를 왜곡시켰다. 사전실험을 통해 대기외란시 특징점 기반 변위 측정 방법과 제안기법의 변위 측정 타당성을 비교 검증하였으며, 검증 결과 제안기법의 낮은 측정 에러율을 나타냈다. 대기외란 환경에서 변위 측정 성능평가 결과, 인공 타겟을 활용한 TMI는 대기외란 유무에 따라 변위 측정 성능에 큰 차이가 없었다. 하지만 자연 타겟을 활용하였을 때, 20m 이상의 촬영거리에서 RMSE가 크게 상승하여 제안기법의 운용 한계를 보여줬다. 이는 촬영거리 증가에 따라 자연 타겟의 해상도가 저하되며, 대기외란으로 인한 이미지 왜곡이 템플릿 이미지 추정에 오류가 발생 되어 변위 측정 오차가 높게 발생하는 경향을 나타냈다.

• 전자공학회논문지S
• /
• 제35S권2호
• /
• pp.137-145
• /
• 1998

In this paper, we propose a tube-hole center detection vision algorithm verifying the position of a tele-controlled robot and providing visual information for increasing reliability and efficiency in the diagnosis of steam generator (SG) tubes in nuclear power plant. A tele-controlled robot plays a role in carrying the probe used in inspecting the integrity of SG tubes. Thus accurately locating a tele-controlled robot on the desired tube-hole center is important issue for reliability of inspection. To do this work, we have to find the tube-hole center locations from the input image. At first, we apply the three-class segmentation method modified for this application. WE extract minimum bounding rectangles (MBRs) in the theresholded binary image. Second, for discriminating between MBR by tube and MBR by noise, we introduce the MBR rejection rules as knowledge-based rule set. MBRs are divided into the very dark region MBRs and the very bright region MBRs. In order to describe the region of complete tube-hole, the MBRs need a process of pairing each other. We then can find the tube-hole center from the paired MBR. For more accurately finding the tube-hole center in several sequential images, the centers of some frames need to be averaged. We tested the performance of our method using hundreds of real images.

• 한국산업융합학회 논문집
• /
• 제16권4호
• /
• pp.113-117
• /
• 2013

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.

• Current Optics and Photonics
• /
• 제6권2호
• /
• pp.161-170
• /
• 2022

Three-dimensional (3D) geometric models are introduced to correct vignetting, and a downhill simplex search is applied to determine the coefficients of a 3D model used in digital microscopy. Vignetting is nonuniform illuminance with a geometric regularity on a two-dimensional (2D) image plane, which allows the illuminance distribution to be estimated using 3D models. The 3D models are defined using generalized polynomials and arbitrary coefficients. Because the 3D models are nonlinear, their coefficients are determined using a simplex search. The cost function of the simplex search is defined to minimize the error between the 3D model and the reference image of a standard white board. The conventional and proposed methods for correcting the vignetting are used in experiments on four inspection systems based on machine vision and microscopy. The methods are investigated using various performance indices, including the coefficient of determination, the mean absolute error, and the uniformity after correction. The proposed method is intuitive and shows performance similar to the conventional approach, using a smaller number of coefficients.

• 한국산업융합학회 논문집
• /
• 제20권1호
• /
• pp.19-26
• /
• 2017

In this paper, we describe the design and performance of UAV system toward compact and fully autonomous quadrotors, where they can complete logistics application, rescue work, inspection tour and remote sensing without external assistance systems like ground station computers, high-performance wireless communication devices or motion capture system. we propose high-speed hovering flyght height control method based on state feedback control with image information from active camera and multirate observer because we can get image of the information only every 30ms. Finally, we show the advantages of proposed method by simulations and experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.97.4-97
• /
• 2002

1. Introduction Pose estimation of a three dimensional object has been studied in robot vision area, and it is needed in a number of industrial applications such as process monitoring and control, assembly and PCB inspection. In this research, we propose a new pose estimation method based on principal axes analysis. Here, it is assumed that the locations of x-ray source and the image plane are predetermined and the object geometry is known. To this end, we define a dispersion matrix of an object, which is a discrete form of inertia matrix of the object. It can be determined here from a set of x-ray images, at least three images are required. Then, the pose information is obtained fro...