http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
배현진 ( Bae Hyun Jin ),장근영 ( Jang Keun Young ),안윤규 ( An Yun-kyu ) 한국구조물진단유지관리공학회 2019 한국구조물진단유지관리공학회 학술발표대회 논문집 Vol.23 No.1
This paper proposes an automated crack evaluation technique for a high-rise bridge pier using a climbing robot. The proposed technique enables to automatically detect and quantify the bridge pier cracks even where cannot easily access by human for visual inspection. To achieve it, high quality images are obtained by scanning the vision cameras embedded on the climbing robot along the bridge pier surface. Then, a feature extraction-based image stitching algorithm is newly developed and applied for establishing the entire region of interest (ROI) images. The ROI images are then processed with a semantic segmentation algorithm for automated crack detection. Finally, the detected cracks are precisely quantified by a crack quantification algorithm. The proposed technique is validated using in-situ test data obtained from Jang-Duck bridge located at Gangneung city, South Korea. The test results reveal that the proposed technique successfully evaluate the bridge pier cracks with precision of 90.92 % and recall of 97.47 %.
드론 및 등반 로봇을 활용한 교량의 딥러닝 기반 균열 평가
안윤규(Yun-Kyu An),배현진(Hyun Jin Bae),장근영(Keun Young Jang) 한국비파괴검사학회 2021 한국비파괴검사학회지 Vol.41 No.6
본 연구는 드론 및 등반 로봇을 활용하여 취득한 사회기반시설물 영상에 대해 딥러닝 기반으로 균열을 평가하는 기법을 제안한다. 디지털 카메라를 부착한 드론과 등반 로봇 시스템을 구축 및 활용하여 교량의 고교각에 발생한 균열을 계측하기 위한 각 시스템의 장단점을 비교 분석하였으며, 분석한 장단점을 기반으로 각 시스템에 적합한 딥러닝 네트워크를 개발하여 균열을 자동으로 검출 및 평가하였다. 본 제안 기술은 강원도 춘천시에 있는 등선교와 강릉시에 있는 장덕교에서 각각 드론과 등반 로봇을 활용하여 실험적으로 검증하였다. This paper presents a deep learning-based crack evaluation of civil infrastructures using drone and robot. Digital camera-embedded drone and climbing robot systems were developed for the automated crack evaluation of high-rise bridge piers. The optimal deep learning networks for the drone and climbing robot were proposed by analyzing the advantages and disadvantages of each system. The proposed techniques were experimentally validated using the drone and climbing robot systems at the Deung-Seon bridge in Chuncheon city and the Jang-Duck bridge in Gangneung city, South Korea.
딥러닝 기반의 이종영상 처리를 통한 콘크리트 균열 탐지
장근영 ( Jang Keun Young ),안윤규 ( An Yun-kyu ) 한국구조물진단유지관리공학회 2018 한국구조물진단유지관리공학회 학술발표대회 논문집 Vol.22 No.1
This paper proposes a deep learning-based crack evaluation technique using hybrid images. The use of the hybrid images combining vision and infrared images are able to improve crack detectability while minimizing false alarms. In particular, large-scale infrastructures can be inspected by an UAV-mounted hybrid image scanning (HIS) system, and the corresponding huge amount of data is typically difficult to be analyzed by experts. To automate such making-decision process, deep convolutional neural network is used in this study. As the very first stage, a lab-scale HIS system is developed using a scanning zig and experimentally validated using a concrete specimen with various-size cracks. The test results reveal that macro- and micro-cracks are successfully and automatically detected with minimizing false-alarms.