• Journal of Construction Engineering and Project Management
• /
• 제5권4호
• /
• pp.16-22
• /
• 2015

This paper presents an automated computer vision-based system to update BIM data by leveraging multi-modal visual data collected from existing buildings under inspection. Currently, visual inspections are conducted for building envelopes or mechanical systems, and auditors analyze energy-related contextual information to examine if their performance is maintained as expected by the design. By translating 3D surface thermal profiles into energy performance metrics such as actual R-values at point-level and by mapping such properties to the associated BIM elements using XML Document Object Model (DOM), the proposed method shortens the energy performance modeling gap between the architectural information in the as-designed BIM and the as-is building condition, which improve the reliability of building energy analysis. Several case studies were conducted to experimentally evaluate their impact on BIM-based energy analysis to calculate energy load. The experimental results on existing buildings show that (1) the point-level thermography-based thermal resistance measurement can be automatically matched with the associated BIM elements; and (2) their corresponding thermal properties are automatically updated in gbXML schema. This paper provides practitioners with insight to uncover the fundamentals of how multi-modal visual data can be used to improve the accuracy of building energy modeling for retrofit analysis. Open research challenges and lessons learned from real-world case studies are discussed in detail.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.532-536
• /
• 2015

This paper presents an automated computer vision-based system to update BIM data by leveraging multi-modal visual data collected from existing buildings under inspection. Currently, visual inspections are conducted for building envelopes or mechanical systems, and auditors analyze energy-related contextual information to examine if their performance is maintained as expected by the design. By translating 3D surface thermal profiles into energy performance metrics such as actual R-values at point-level and by mapping such properties to the associated BIM elements using XML Document Object Model (DOM), the proposed method shortens the energy performance modeling gap between the architectural information in the as-designed BIM and the as-is building condition, which improve the reliability of building energy analysis. The experimental results on existing buildings show that (1) the point-level thermography-based thermal resistance measurement can be automatically matched with the associated BIM elements; and (2) their corresponding thermal properties are automatically updated in gbXML schema. This paper provides practitioners with insight to uncover the fundamentals of how multi-modal visual data can be used to improve the accuracy of building energy modeling for retrofit analysis. Open research challenges and lessons learned from real-world case studies are discussed in detail.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.273-277
• /
• 2003

A general process of electronic assembly is composed of a series of geometric alignments and bonding/screwing processes. After assembly, the function is tested in a following process of inspection. However, assembly of micro-optic devices requires both processes to be performed in equipment. Coarse geometric alignment is made by using vision and optical function is improved by the following fine motion based on feedback of tunable laser interferometer. The general system is composed of a precision robot system for 3D assembly, a 3D vision guided system for geometric alignment and an optical feedback system with a tunable laser. In this study, we propose a new fast alignment algorithm of micro-optic devices for both of visual and optical alignments. The main goal is to find a fastest alignment process and algorithms with state-of-the-art technology. We propose a new approach with an optimal sequence of processes, a visual alignment algorithm and a search algorithm for an optimal optical alignment. A system is designed to show the effectiveness and efficiency of the proposed method.

• 한국정밀공학회지
• /
• 제30권5호
• /
• pp.513-519
• /
• 2013

Line scan camera has been widely used in the area of inspection of glass, film, fabric, iron, PCB and etc. due to the high resolution and the high speed. We developed the line scan based vision system to inspect tangled and cut-off status of yarn in the manufacturing process. The original image is binarized with a proper threshold, and the gap distances in the yarn are measured in real time, so finally the status of the process is decided by the maximum value of the gap distance. All procedures are executed in real time by realization of multi-processed threads. By implementation of this system, the error of the yarn in manufacturing process can be precedently monitored and the loss of the yarn is decreased efficiently.

• 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.

• 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.

• 한국전자통신학회논문지
• /
• 제15권3호
• /
• pp.513-520
• /
• 2020

최근 기계 학습을 활용한 비전 검사 시스템의 개발이 활발해지고 있다. 본 연구는 기계 학습을 활용한 결함 검사 모델을 개발하고자 한다. 이미지에 대한 결함 검출 문제는 기계 학습에 있어 지도 학습 방법인 분류 문제에 해당한다. 본 연구에서는 특징을 자동 추출하는 알고리즘과 특징을 추출하지 않는 알고리즘을 기반으로 결함 검출 모델을 개발한다. 특징을 자동 추출하는 알고리즘으로 1차원 합성곱 신경망과 2차원 합성곱 신경망을 활용하였으며, 특징을 추출하지 않는 알고리즘으로 다중 퍼셉트론, 서포트 벡터 머신을 활용하였다. 4가지 모델을 기반으로 결함 검출 모델을 개발하였고 이들의 정확도와 AUC를 기반으로 성능 비교하였다. 이미지 분류는 합성곱 신경망을 활용한 모델 개발이 일반적임에도, 본 연구에서 이미지의 화소를 RGB 값으로 변환하여 서포트 벡터 머신 모델을 개발할 때 높은 정확도와 AUC를 얻을 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국내학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
• /
• pp.353-359
• /
• 1988

In this paper, the design and implementation of a multi-processor based die bonder machine for the semiconductor will be described. This is a final research results carried out for two years from June, 1986 to July, 1988. The mechanical system consists of three subsystems such as bonding head module, wafer feeding module, and lead frame feeding module. The overall control system consists of the following three subsystems each of which employs a 16 bit microprocessor MC 68000 : (i) supervisory control system, (ii) visual recognition / inspection system and (iii) the display system. Specifically, the supervisory control system supervises the whole sequence of die bonder machine, performs a self-diagnostics while it controls the bonding head module according to the prespecified bonding cycle. The vision system recognizes the die to inspect the die quality and deviation / orientation of a die with respect to a reference position, while it controls the wafer feeding module. Finally, the display system performs a character display, image display ans various error messages to communicate with operator. Lead frame feeding module is controlled by this subsystem. It is reported that the proposed control system were applied to an engineering sample and tested in real-time, and the results are sucessful as an engineering sample phase.

• Smart Structures and Systems
• /
• 제24권5호
• /
• 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.

• 한국구조물진단유지관리공학회 논문집
• /
• 제26권6호
• /
• pp.175-181
• /
• 2022

구조물의 공용연수가 증가함에 따라 각종 성능 저하가 발생한다. 특히 국내 인프라 구조물은 대부분 경제가 성장하는 시기에 집중적으로 건설되었기 때문에 노후 인프라 비율 급증이 최근 주요 이슈가 되고 있다. 인프라의 노후화는 자칫 안전사고로 이어질 수 있으며 인명 피해까지 유발할 수 있다. 이러한 문제를 사전에 예방하기 위하여 주기적이고 정확한 점검 및 유지관리가 필수적이다. 이 같은 이유로 최근 컴퓨터 비전과 딥러닝을 활용하여 다양한 손상을 탐지하는 연구에 대한 수요가 원격점검 혹은 점검자동화 분야에서 증가하고 있다. 따라서 본 논문에서는 콘크리트 손상의 종류를 세 가지로 구분하여 이를 탐지할 수 있는 신경망 구조를 제안했다. 특히 계층적 학습 기법을 통해 보다 정확하게 다양한 손상을 탐지할 수 있는 신경망을 개발하였다. 이 신경망은 2,026장의 손상 영상으로 학습되었고, 508장의 손상 영상으로 실험하였다. 그 결과 67.04%의 평균 중첩 정확도와 52.65%의 F1 점수를 갖는 알고리즘을 완성하였다. 이 같은 손상 탐지 알고리즘은 향후 구조물의 정확한 상태 진단에 활용될 수 있으리라 기대한다.