영상장비와 딥러닝을 이용한 고속도로 터널 균열 탐지 시스템 개발
Development of Crack Detection System for Highway Tunnels using Imaging Device and Deep Learning
1
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
빠르게 증가하는 노후 터널을 효율적으로 관리하기 위하여 최근 영상장비를 이용한 점검 방법론들이 많이 제안되고 있다. 하지만기존의 방법론들은 대부분 국한된 영역에서 검증을 수행하였을 뿐 아니라, 다른 물체들이 존재하지 않는 깨끗한 콘크리트 표면에서 검증되어실제 현장에 대한 적용성을 검증하기 어려웠다. 따라서 본 논문에서는 이러한 한계를 극복하기 위하여 비균열 물체 학습에 기반한 6단계 터널균열 탐지 딥러닝 모델 개발 프레임워크를 제안한다. 제안된 프레임워크는 터널에서 취득된 이미지 내 균열 탐색, 픽셀 단위 균열 라벨링, 딥러닝 모델 학습, 비균열 물체 수집, 비균열 물체 재학습, 최종 학습 데이터 구축의 총 6단계로 이루어진다. 제안된 프레임워크를 이용하여 개발된균열 탐지 딥러닝 모델 개발을 수행하였으며, 일반 균열 1561장, 비균열 206장으로 개별 물체 세분화(Instance Segmentation) 모델인 CascadeMask R-CNN을 학습시켰다. 학습된 모델의 현장 적용성을 검토하기 위하여 전선, 전등 등을 포함하는 약 200m 길이의 실제 터널에서 균열 탐지를 수행하였다. 실험 결과 학습된 모델은 99% 정밀도와 92%의 재현율을 나타내며 뛰어난 현장 적용성을 나타내었다.
Abstract
In order to efficiently inspect rapidly increasing old tunnels in many well-developed countries, many inspection methodologies have beenproposed using imaging equipment and image processing. However, most of the existing methodologies evaluated their performance on a clean concretesurface with a limited area where other objects do not exist. Therefore, this paper proposes a 6-step framework for tunnel crack detection deep learningmodel development. The proposed method is mainly based on negative sample (non-crack object) training and Cascade Mask R-CNN. The proposedframework consists of six steps: searching for cracks in images captured from real tunnels, labeling cracks in pixel level, training a deep learning model,collecting non-crack objects, retraining the deep learning model with the collected non-crack objects, and constructing final training dataset. Toimplement the proposed framework, Cascade Mask R-CNN, an instance segmentation model, was trained with 1561 general crack images and 206non-crack images. In order to examine the applicability of the trained model to the real-world tunnel crack detection, field testing is conducted ontunnel spans with a length of about 200m where electric wires and lights are prevalent. In the experimental result, the trained model showed 99%precision and 92% recall, which shows the excellent field applicability of the proposed framework.
참고문헌 (20)
- Sanpei, T., "Fundamental Study for Real-Time Detection of Sudden Displacement by High-Speed Laser Scanner", Journal of Structural Integrity and Maintenance, 3(4), pp.227~232 (2018)
- Yamaguchi, T., "Image‐Based Crack Detection for Real Concrete Surfaces", IEEJ Transactions on Electrical and Electronic Engineering, 3(1), pp.128~135 (2008), Wiley Online Library
- Yu, S. N., "Auto Inspection System Using a Mobile Robot for Detecting Concrete Cracks in a Tunnel", Automation in Construction, 16(3), pp.255~261 (2007), Elsevier
- Lee, S. H., "Introduction of Tunnel Crack Measurement Technology Using Image Scanning", Journal of Korean Society of Steel Construction, 31(6), pp.42~48 (2019)
- Song, Q., "Real-time Tunnel Crack Analysis System via Deep Learning", IEEE Access, 7, pp.64186~64197 (2019), IEEE
- Li, G., "Automatic Tunnel Crack Detection based on U-Net and a Convolutional Neural Network with Alternately Updated Clique", Sensors, 20(3), pp.717~ (2020), MDPI
- Ronneberger, O., "U-net:Convolutional Networks for Biomedical Image Segmentation", International Conference on Medical Image Computing and Computer-assisted Intervention, pp.234~241 (2015), Springer
- 최윤수, "합성곱 신경망을 이용한 아스팔트 콘크리트 도로포장 표면균열 검출", 한국구조물진단유지관리공학회 논문집, 23(6), pp.38~44 (2019), 한국구조물진단유지관리공학회
- Kim B., "Image-based Concrete Crack Assessment using Mask and Region-based Convolutional Neural Network", Structural Control and Health Monitoring, 26(8), pp.1~15 (2019), Wiley
- Kim B., "Automated Multiple Concrete Damage Detection Using Instance Segmentation Deep Learning Model", Applied Sciences, 9(20), pp.1~14 (2020), MDPI
- Jang, K., "Automated Crack Evaluation of a High‐Rise Bridge Pier Using a Ring‐Type Climbing Robot", Computer-aided Civil and Infrastructure Engineering, 26, pp.14~29 (2021), Wiley
- He, K., "Mask r-cnn", Proceedings of the IEEE international conference on computer vision, pp.2961~2969 (2017), IEEE
- Cai, Z., "Cascade r-cnn: Delving into High Quality Object Detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.6154~6162 (2018), IEEE
- Lin, T. Y., "Microsoft Coco: Common Objects in Context", European Conference on Computer Vision, pp.740~755 (2014), Springer
- Chen, K., "MMDetection: Open Mmlab Detection Toolbox and Benchmark", ArXiv Preprint, ArXiv, 1906.07155, ~ (2019)
- Robbins, H., "A Stochastic Approximation Method", The Annals of Mathematical Statistics, pp.400~407 (1951), Institute of Mathematical Statistics
- Pascanu, R., "On the Difficulty of Training Recurrent Neural Networks", International Conference on Machine Learning, pp.1310~1318 (2013), PMLR
- Loshchilov, I., "SGDR: Stochastic Gradient Descent with Warm Restarts", ArXiv Preprint, arXiv, 1608.03983, ~ (2016)
- Deng, J., "Imagenet: A Large-Scale Hierarchical Image Database", 2009 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.248~255 (2009), IEEE
- Xie, S., "Aggregated Residual Transformations for Deep Neural Networks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1492~1500 (2017), IEEE