본문 바로가기
KERD
논문KCI 등재

콘크리트 균열 이미지의 데이터셋을 효율적으로 수집하기 위한 벡터기반의 학습 증강 기법

Vector and Thickness Based Learning Augmentation Method for Efficiently Collecting Concrete Crack Images

김종현
한국컴퓨터정보학회 (The Korean Society Of Computer And Information)|2023.04|한국컴퓨터정보학회논문지 (Journal of The Korea Society of Computer and Information)|제28권 제4호|pp. 65-73|DOI https://doi.org/10.9708/jksci.2023.28.04.065

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

합성곱 신경망데이터 증강Data augmentationCrack detectionConvolutional Neural Networks균열 검출콘크리트 균열Concrete crack탄성왜곡Elastic distortion학습 증강
주제분류컴퓨터학

초록

본 논문에서는 콘크리트 균열 이미지 데이터셋을 효율적으로 얻기 위한 합성곱 신경망 네트워크 학습 기반의 데이터 증강기법을 제안한다. 실제 콘크리트 균열 이미지는 정형화된 형태가 없고 복잡한 패턴을 지니고 있어 얻기 어려울 뿐만 아니라, 데이터를 확보할 때 위험한 상황에 노출될 우려가 있다. 이러한 상황에 노출된 데이터셋 수집 문제를 본 논문에서는 벡터와 두께 기반의 데이터 증강 기법을 통해 비용과 시간적 측면에서 효율적으로 해결한다. 또한 제안한 방법을효율성을 입증하고자 U-Net기반의 균열 검출을 통해 다양한 장면에서 실험을 진행했고, IoU 정확도로 측정했을 때 모든 장면에서 성능이 향상되었다. 콘크리트 균열 데이터를 증강하지 않았을경우 잘못 예측된 경우의 비율이 약 25%였으나, 우리의 방법을 통해 데이터 증강을 했을 경우 잘못 예측된 비율이 3%까지 감소하였다.

Abstract

In this paper, we propose a data augmentation method based on CNN(Convolutional Neural Network) learning for efficiently obtaining concrete crack image datasets. Real concrete crack images are not only difficult to obtain due to their unstructured shape and complex patterns, but also may be exposed to dangerous situations when acquiring data. In this paper, we solve the problem of collecting datasets exposed to such situations efficiently in terms of cost and time by using vector and thickness-based data augmentation techniques. To demonstrate the effectiveness of the proposed method, experiments were conducted in various scenes using U-Net-based crack detection, and the performance was improved in all scenes when measured by IoU accuracy. When the concrete crack data was not augmented, the percentage of incorrect predictions was about 25%, but when the data was augmented by our method, the percentage of incorrect predictions was reduced to 3%.

참고문헌 (40)

  1. Xiaodong Wang, "Study on Breaking Concrete Structures by Pulse Power Technology", Buildings, 12(3), pp.274~ (2022), MDPI AG[DOI]
  2. Dimitrios G. Aggelis, "Health Monitoring of Civil Infrastructure and Materials", The Scientific World Journal, 2014, pp.1~2 (2014), Hindawi Limited[DOI]
  3. In-Ho Kim, "Application of Crack Identification Techniques for an Aging Concrete Bridge Inspection Using an Unmanned Aerial Vehicle", Sensors, 18(6), pp.1881~ (2018), MDPI AG[DOI]
  4. Tingjin Liu, "Crack Detection of Reinforced Concrete Member Using Rayleigh-Based Distributed Optic Fiber Strain Sensing System", Advances in Civil Engineering, 2020, pp.1~11 (2020), Hindawi Limited[DOI]
  5. Tomoyuki Yamaguchi, "Image‐Based Crack Detection for Real Concrete Surfaces", IEEJ Transactions on Electrical and Electronic Engineering, 3(1), pp.128~135 (2008), Wiley[DOI]
  6. Yi-Chang Tsai, "Critical Assessment of Pavement Distress Segmentation Methods", Journal of Transportation Engineering, 136(1), pp.11~19 (2010), American Society of Civil Engineers (ASCE)[DOI]
  7. Dejin Zhang, "An efficient and reliable coarse-to-fine approach for asphalt pavement crack detection", Image and Vision Computing, 57, pp.130~146 (2017), Elsevier BV[DOI]
  8. Albert Ayenu-Prah, "Evaluating Pavement Cracks with Bidimensional Empirical Mode Decomposition", EURASIP Journal on Advances in Signal Processing, 2008(1) (2008), Springer Science and Business Media LLC[DOI]
  9. Subirats, "Automation of pavement surface crack detection using the continuous wavelet transform", 2006 International Conference on Image Processing, pp.3037~3040 (2006), IEEE
  10. L. Ying, "Beamlet Transform-Based Technique for Pavement Crack Detection and Classification", Computer-Aided Civil and Infrastructure Engineering, 25(8), pp.572~580 (2010), Wiley[DOI]
  11. Hizukuri, Akiyoshi, "Development of a classification method for a crack on a pavement surface images using machine learning", Thirteenth International Conference on Quality Control by Artificial Vision 2017, 10338, pp.148~154 (2017), SPIE
  12. Acharjya, Pinaki Pratim, "Study and comparison of different edge detectors for image segmentation", Global Journal of Computer Science and Technology, 12(F13), pp.29~32 (2012)
  13. Graps, Amara, "An introduction to wavelets", IEEE computational science and engineering, 2(2), pp.50~61 (1995)
  14. Zhang, "Road crack detection using deep convolutional neural network", 2016 IEEE international conference on image processing (ICIP), pp.3708~3712 (2016), IEEE
  15. Pauly, "Deeper networks for pavement crack detection", Proceedings of the 34th ISARC, pp.479~485 (2017), IAARC
  17. Hongyan Xu, "Automatic Bridge Crack Detection Using a Convolutional Neural Network", Applied Sciences, 9(14), pp.2867~ (2019), MDPI AG[DOI]
  18. Yadan Li, "YOLOv3-Lite: A Lightweight Crack Detection Network for Aircraft Structure Based on Depthwise Separable Convolutions", Applied Sciences, 9(18), pp.3781~ (2019), MDPI AG[DOI]
  19. Zheng Tong, "Recognition, location, measurement, and 3D reconstruction of concealed cracks using convolutional neural networks", Construction and Building Materials, 146, pp.775~787 (2017), Elsevier BV[DOI]
  20. Xincong Yang, "Automatic Pixel‐Level Crack Detection and Measurement Using Fully Convolutional Network", Computer-Aided Civil and Infrastructure Engineering, 33(12), pp.1090~1109 (2018), Wiley[DOI]
  21. Jinsong Zhu, "An Intelligent Classification Model for Surface Defects on Cement Concrete Bridges", Applied Sciences, 10(3), pp.972~ (2020), MDPI AG[DOI]
  22. Lin, "Feature pyramid networks for object detection", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2117~2125 (2017)
  23. Lu Deng, "Region-Based CNN Method with Deformable Modules for Visually Classifying Concrete Cracks", Applied Sciences, 10(7), pp.2528~ (2020), MDPI AG[DOI]
  24. Ren, "Faster r-cnn: Towards real-time object detection with region proposal networks", Advances in neural information processing systems 28, ~ (2015)
  25. Dai, "R-fcn: Object detection via region-based fully convolutional networks", Advances in neural information processing systems 29, ~ (2016)
  26. Oh, Heekuck, "Segmentation algorithm using iterative clipping for processing noisy pavement images" (1998), Imaging Technologies: Techniques and Applications in Civil Engineering. Second International ConferenceEngineering Foundation; and Imaging Technologies Committee of the Technical Council on Computer Practices, American Society of Civil Engineers
  27. Li, Qingquan, "Novel approach to pavement image segmentation based on neighboring difference histogram method", 2008 Congress on Image and Signal Processing, pp.792~796 (2008), IEEE
  28. Jian Zhou, "Wavelet-based pavement distress detection and evaluation", Optical Engineering, 45(2), pp.027007~027007 (2006), SPIE-Intl Soc Optical Eng[DOI]
  29. Wu, Shuguang, "A segment algorithm for crack dection", 2012 IEEE Symposium on Electrical & Electronics Engineering (EEESYM), pp.674~677 (2012), IEEE
  30. Qingquan Li, "FoSA: F* Seed-growing Approach for crack-line detection from pavement images", Image and Vision Computing, 29(12), pp.861~872 (2011), Elsevier BV[DOI]
  31. Qin Zou, "CrackTree: Automatic crack detection from pavement images", Pattern Recognition Letters, 33(3), pp.227~238 (2012), Elsevier BV[DOI]
  32. Roli, Fabio., "Measure of texture anisotropy for crack detection on textured surfaces", Electronics Letters, 32(14), pp.1274~1275 (1996)
  33. Nguyen, "Free-form anisotropy: A new method for crack detection on pavement surface images", 2011 18th IEEE International Conference on Image Processing, pp.1069~1072 (2011), IEEE
  34. Xu, Wei, "Pavement crack detection based on saliency and statistical features", 2013IEEE International Conference on Image Processing, pp.4093~4097 (2013), IEEE
  35. Yong Hu, "A Novel LBP Based Methods for Pavement Crack Detection", Journal of Pattern Recognition Research, 5(1), pp.140~147 (2010), Journal of Pattern Recognition Research[DOI]
  36. Wenyu Zhang, "Automatic Crack Detection and Classification Method for Subway Tunnel Safety Monitoring", Sensors, 14(10), pp.19307~19328 (2014), MDPI AG[DOI]
  37. Shengyuan Li, "Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique", Advances in Civil Engineering, 2019, pp.1~12 (2019), Hindawi Limited[DOI]
  38. Sattar Dorafshan, "SDNET2018: An annotated image dataset for non-contact concrete crack detection using deep convolutional neural networks", Data in Brief, 21, pp.1664~1668 (2018), Elsevier BV[DOI]
  40. 김종현, "효율적인 균열 데이터 수집을 위한 벡터 기반 데이터 증강과 네트워크 학습", 한국컴퓨터그래픽스학회논문지, 28(2), pp.1~9 (2022), (사)한국컴퓨터그래픽스학회[DOI]

관련 논문AI추천

효율적인 균열 데이터 수집을 위한 벡터 기반 데이터 증강과 네트워크 학습김종현(사)한국컴퓨터그래픽스학회 · 한국컴퓨터그래픽스학회논문지2022 · 제28권 제2호U-Net에 기반한 이미지 복원 기법을 이용한 콘크리트 균열 탐지 방안김도수, 김수민, 손정모한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2020 · 제25권 제10호지하시설물 안전점검을 위한 딥러닝 기반 콘크리트 균열 검출김동규, 이임평, 전의익사단법인 한국터널지하공간학회 · 한국터널지하공간학회 논문집2023 · 제25권 제6호가중치 오차함수를 통한 콘크리트 균열 감지 모델 학습 개선김도수, 손정모, 황혜빈한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2020 · 제25권 제10호데이터 증강을 위한 순환 생성적 적대 신경망 기반의 아스팔트와 콘크리트 균열 영상 간의 변환 기법심승보한국ITS학회 · 한국ITS학회 논문지2022 · 제21권 제5호DreamBooth을 이용한 데이터 증강 기반 구조물 표면 균열 탐지 신경망 모델 개발심승보한국구조물진단유지관리공학회 · 한국구조물진단유지관리공학회 논문집2025 · 제29권 제6호

이 간행물의 다른 논문 (20건)

STFT와 시계열 데이터 이미지화 알고리즘을 활용한 시계열 데이터 분류 성능 분석홍성규, 김상철pp. 1-11딥 러닝을 이용한 VOC 저감 설비 이상 탐지 분석김명호, 손민지pp. 13-20AI를 이용한 인구주택총조사의 자동 분류 개선: 산업 및 직업코드 연구메다드, 김다혜, 김영진, 정영섭, 윤병일pp. 21-29모델 내부/외부 특징량 상관 학습을 통한 지식 증류박훈범, 배승환pp. 31-39걸음걸이 데이터에서 분노 검출을 위한 다중 시간 윈도 특징 추출 기술권범, 오태근pp. 41-51
원문 보기