딥러닝과 전이학습을 이용한 콘크리트 균열 인식 및 시각화
Recognition and Visualization of Crack on Concrete Wall using Deep Learning and Transfer Learning
2
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structureas it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized forit. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack’s image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with orwithout crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualizationof crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were appliedfor each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizingcrack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, andregarding to the false negative error, the case using 50 data per category showed the best result.
Abstract
Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structureas it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized forit. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack’s image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with orwithout crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualizationof crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were appliedfor each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizingcrack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, andregarding to the false negative error, the case using 50 data per category showed the best result.
참고문헌 (21)
- Geoff Boeing, "New Insights into Rental Housing Markets across the United States: Web Scraping and Analyzing Craigslist Rental Listings", Journal of Planning Education and Research, 37(4), pp.457~476 (2016), SAGE Publications[DOI]
- Byun, G. J., "Crack evaluation technique and crack repair of concrete structures", Magazine of the Korea Concrete Institute, 12(6), pp.97~108 (2000)[DOI]
- Genda Chen, "Damage detection of reinforced concrete beams with novel distributed crack", strain sensors, 2016, pp.3(3), 225~243[DOI]
- "Transfer learning tutorial" (2019)[URL]
- Devikar, P., "Transfer learning for image classification of various dog breeds", International Journal of Adavanced Research in Computer Engineering & Technology, 5(12), pp.2707~2715 (2016)
- Syed Ibrahim Hassan, "CNN을 이용한 딥러닝 기반 하수관 손상 탐지 분류 시스템", 한국정보통신학회논문지, 22(3), pp.451~457 (2018), 한국정보통신학회[DOI]
- Kang, H. K., "Causes and mitigation of concrete cracking", Magazine of the Korea Concrete Institute, 20(5), pp.61~68 (2008)[DOI]
- Kim, W., "Major causes for deterioration in concrete structures", Magazine of the Korea Conrete Institute, 7(6), pp.14~22 (1995)[DOI]
- Krizhevsky, A., "ImageNet classification with deep convolutional neural networks", Advances in Neural Information Processing Systems, pp.1097~1105 (2012)
- Yann LeCun, "Deep learning", Nature, 521(7553), pp.436~444 (2015), Springer Science and Business Media LLC[DOI]
- 이방연, "콘크리트 구조물의 표면 균열 평가 기법", 비파괴검사학회지, 27(2), pp.173~182 (2007), 한국비파괴검사학회
- 이예인, "딥러닝을 이용한 영상 기반의 콘크리트 구조물 박락 탐지", 콘크리트학회 논문집, 30(1), pp.91~99 (2018), 한국콘크리트학회
- Sinno Jialin Pan, "A Survey on Transfer Learning", IEEE Transactions on Knowledge and Data Engineering, 22(10), pp.1345~1359 (2010), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Mohammad Pour-Ghaz, "Wireless Crack Detection in Concrete Elements Using Conductive Surface Sensors and Radio Frequency Identification Technology", Journal of Materials in Civil Engineering, 26(5), pp.923~929 (2014), American Society of Civil Engineers (ASCE)[DOI]
- Simard, P. Y., "Best practices for convolutional neural networks applied to visual document analytsis", Proceedings of the Seventh International Conference on Document Analysis and Recognition, 2, pp.958~962 (2003)
- Song, G., "Concrete structural health monitoring using embedded piezoceramic transducers", Smart Materials and Structures, 16, pp.959~968 (2007)[DOI]
- Wimal Suaris, "Detection of crack growth in concrete from ultrasonic intensity measurements", Materials and Structures, 20(3), pp.214~220 (1987), Springer Science and Business Media LLC[DOI]
- Szegedy, C., "Rethinking the inception architecture for computer vision", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2818~2826 (2016)
- Szegedy, C., "Going deeper with convolutions", The IEEE Conference on Computer Vision and Pattern Recognition, pp.1~9 (2015)
- Xia, X., "Inception-v3 for flower classification. Image, Vision and Computing", 2017 2nd International Conference on IEEE, pp.783~787 (2017)
- Yoon, W. H., "About crack of concrete structure", Magazine of the Korea Concrete Institute, 3(3), pp.66~74 (1991)[DOI]