Journal of the Architectural Institute of Korea Structure & Construction (대한건축학회논문집:구조계)

Architectural Institute of Korea (대한건축학회)
권호 표지
DOI QR코드

DOI QR Code

Comparison of Deep Learning-based CNN Models for Crack Detection

콘크리트 균열 탐지를 위한 딥 러닝 기반 CNN 모델 비교

  • 설동현 (경북대학교 건설환경에너지공학부) ;
  • 오지훈 (경북대학교 건축학부) ;
  • 김홍진 (경북대학교 건축학부)
  • Received : 2020.01.06
  • Accepted : 2020.02.16
  • Published : 2020.03.30
⟨ Previous Next ⟩

Abstract

The purpose of this study is to compare the models of Deep Learning-based Convolution Neural Network(CNN) for concrete crack detection. The comparison models are AlexNet, GoogLeNet, VGG16, VGG19, ResNet-18, ResNet-50, ResNet-101, and SqueezeNet which won ImageNet Large Scale Visual Recognition Challenge(ILSVRC). To train, validate and test these models, we constructed 3000 training data and 12000 validation data with 256×256 pixel resolution consisting of cracked and non-cracked images, and constructed 5 test data with 4160×3120 pixel resolution consisting of concrete images with crack. In order to increase the efficiency of the training, transfer learning was performed by taking the weight from the pre-trained network supported by MATLAB. From the trained network, the validation data is classified into crack image and non-crack image, yielding True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), and 6 performance indicators, False Negative Rate (FNR), False Positive Rate (FPR), Error Rate, Recall, Precision, Accuracy were calculated. The test image was scanned twice with a sliding window of 256×256 pixel resolution to classify the cracks, resulting in a crack map. From the comparison of the performance indicators and the crack map, it was concluded that VGG16 and VGG19 were the most suitable for detecting concrete cracks.

Keywords

Acknowledgement

Supported by : 경북대학교

이 논문은 2018학년도 경북대학교 국립대학육성사업 지원비에 의하여 연구되었음

References

  1. Special Act on the Safety and Maintenance of Facilities, Act No. 15535 (2018).
  2. Detailed Instructions for Safety and Maintenance of Facilities (Safety Inspection and Diagnosis) (2019). Korea Infrastructure Safety and Technology Corporation.
  3. Fujita, Y., Mitani, Y., & Hamamoto, Y. (2006). A Method for Crack Detection on a Concrete Structure. In 18th International Conference on Pattern Recognition (ICPR'06), 901-904.
  4. Yamaguchi, T., Nakamura, S., Saegusa, R., & Hashimoto, S. (2007). Image-Based Crack Detection for Real Concrete Surfaces. IEEJ Transactions on Electrical and Electronic Engineering, 3(1), 128-135. https://doi.org/10.1002/tee.20244
  5. Fujita, Y., & Hamamoto, Y. (2010). A robust automatic crack detection method from noisy concrete surfaces. Machine Vision and Applications, 22(2), 245-254. https://doi.org/10.1007/s00138-009-0244-5
  6. Fujita, Y., & Hamamoto, Y. (2010). A robust automatic crack detection method from noisy concrete surfaces. Machine Vision and Applications, 22(2), 245-254. https://doi.org/10.1007/s00138-009-0244-5
  7. Lee, B. Y., Kim, Y. Y., Yi, S.-T., & Kim, J.-K. (2013). Automated image processing technique for detecting and analysing concrete surface cracks. Structure and Infrastructure Engineering, 9(6), 567-577. https://doi.org/10.1080/15732479.2011.593891
  8. Santhi, B., Krishnamurthy, G., Siddharth, S., & Ramakrishnan, P.K.. (2012). Automatic detection of cracks in pavements using edge detection operator. Journal of Theoretical and Applied Information Technology. 36. 199-205.
  9. Abdel-Qader, I., Abudayyeh, O., & Kelly, M. E. (2003). Analysis of Edge-Detection Techniques for Crack Identification in Bridges. Journal of Computing in Civil Engineering, 17(4), 255-263. https://doi.org/10.1061/(ASCE)0887-3801(2003)17:4(255)
  10. LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989). Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation, 1(4), 541-551. https://doi.org/10.1162/neco.1989.1.4.541
  11. https://bskyvision.com/425
  12. https://www.sallys.space/blog/2018/01/26/cnn-imagenet/
  13. Cha, Y. J., Choi, W., & Buyukozturk, O. (2017). Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks. Computer-Aided Civil and Infrastructure Engineering, 32(5), 361-378. https://doi.org/10.1111/mice.12263
  14. Li, S., & Zhao, X. (2019). Image-Based Concrete Crack Detection Using Convolutional Neural Network and Exhaustive Search Technique. Advances in Civil Engineering, 2019, 1-12.
  15. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. In NIPS.
  16. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2014). Going Deeper with Convolutions. Retrieved November 26, 2019 from https://arxiv.org/abs/1409.4842
  17. Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. Retrieved November 26, 2019 from https://arxiv.org/abs/1409.1556.
  18. He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. Retrieved November 26, 2019 from https://arxiv.org/abs/1512.03385.
  19. Iandola, F., Han, S., Moskewicz, M., Ashraf, K., Dally, W., & Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. Retrieved November 26, 2019 from https://arxiv.org/abs/1602.07360.
  20. Lee, M., & Seo, K. (2018). Comparison of Region-based CNN Methods for Defects Detection on Metal Surface, 67(7), 865-870. https://doi.org/10.5370/KIEE.2018.67.7.865
  21. https://www.statista.com/statistics/808190/worldwide-large-s cale-visual-recognition-challenge-error-rates/
  22. https://kr.mathworks.com/help/deeplearning/examples/traindeep-learning-network-to-classify-new-images.html