DOI QR코드

DOI QR Code

CNN을 이용한 딥러닝 기반 하수관 손상 탐지 분류 시스템

Damage Detection and Classification System for Sewer Inspection using Convolutional Neural Networks based on Deep Learning

  • Hassan, Syed Ibrahim (Department of Computer Science and Engineering, Sejong University) ;
  • Dang, Lien-Minh (Department of Computer Science and Engineering, Sejong University) ;
  • Im, Su-hyeon (Department of Computer Science and Engineering, Sejong University) ;
  • Min, Kyung-bok (Department of Computer Science and Engineering, Sejong University) ;
  • Nam, Jun-young (Department of Computer Science and Engineering, Sejong University) ;
  • Moon, Hyeon-joon (Department of Computer Science and Engineering, Sejong University)
  • 투고 : 2017.11.29
  • 심사 : 2018.01.12
  • 발행 : 2018.03.28

초록

본 연구는 인공지능 분야의 딥러닝 기술을 기반으로 한 하수관 손상의 자동 탐지 분류 시스템을 제안한다. 성능의 최적화를 위하여 DB 획득 시 발생된 조도 및 그림자 변화와 같은 다양한 환경변화에 강인한 시스템을 구현하였다. 제안된 시스템에서는 Convolutional Neural Network(CNN) 기반의 균열 탐지 및 손상 분류 기법을 구현하였다. 최적의 결과를 위하여 $256{\times}256$ 픽셀 해상도의 CCTV 영상 9,941개를 이용하여 CNN모델을 적용하여 손상부위에 대한 딥러닝을 수행하였고 그 결과 98.76 %의 인식률을 획득하였다. 기계학습을 통한 딥러닝 모델을 기반으로 다양한 환경의 하수도 DB에서 $720{\times}480$ 픽셀 해상도의 646개의 이미지를 추출하여 성능 평가를 수행 하였다. 본 시스템은 다양한 환경에서 구축된 하수관 데이터베이스 에서 손상 유형의 자동 탐지 및 분류에 최적화된 인식률을 제시한다.

We propose an automatic detection and classification system of sewer damage database based on artificial intelligence and deep learning. In order to optimize the performance, we implemented a robust system against various environmental variations such as illumination and shadow changes. In our proposed system, a crack detection and damage classification method using a deep learning based Convolutional Neural Network (CNN) is implemented. For optimal results, 9,941 CCTV images with $256{\times}256$ pixel resolution were used for machine learning on the damaged area based on the CNN model. As a result, the recognition rate of 98.76% was obtained. Total of 646 images of $720{\times}480$ pixel resolution were extracted from various sewage DB for performance evaluation. Proposed system presents the optimal recognition rate for the automatic detection and classification of damage in the sewer DB constructed in various environments.

키워드

참고문헌

  1. M. D. Yang, T. C. Su, "Automated diagnosis of sewer pipe defects based on machine learning approaches,"Expert Systems with Applications, vol. 35, no. 3, pp. 1327-1337, October, 2008. https://doi.org/10.1016/j.eswa.2007.08.013
  2. D. H. Koo, and S. T. Ariaratnam, "Innovative method for assessment of underground sewer pipe condition," Automation in construction, vol. 15, no. 4, pp. 479-488, July, 2006. https://doi.org/10.1016/j.autcon.2005.06.007
  3. W. Zhang, Z. Zhang, D. Qi, and Y. Liu, "Automatic crack detection and classification method for subway tunnel safety monitoring," Sensors, vol. 14, no. 10, pp. 19307-19328, October, 2014. https://doi.org/10.3390/s141019307
  4. T. C. Su, and M. D. Yang, "Application of morphological segmentation to leaking defect detection in sewer pipelines," Sensors, vol. 14, no. 5, pp. 8686-8704, May, 2014. https://doi.org/10.3390/s140508686
  5. Y. J. Cha, W. Choi, and O. Buyukozturk, "Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks," Computer-Aided Civil and Infrastructure Engineering, vol. 32, no. 5, pp. 361-378, March, 2017. https://doi.org/10.1111/mice.12263
  6. Z. Lei, et al, "Road crack detection using deep convolutional neural network," in International Conference on Image Processing on IEEE, Phoenix: AZ, pp. 3708-3712, Sept, 2016.
  7. M. Osama, and S. E. Tariq, "Classification of defects in sewer pipes using neural networks," Journal of infrastructure systems, vol. 6, no. 3, pp. 97-104, Sept, 2000. https://doi.org/10.1061/(ASCE)1076-0342(2000)6:3(97)
  8. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," In Advances in neural information processing systems, pp. 1097-1105, December, 2012.
  9. N. Ejaz, I. Mehmood, S. W. Baik, "Efficient visual attention based framework for extracting key frames from videos," Signal Processing: Image Communication, vol. 28, no. 1, pp. 34-44, January, 2013. https://doi.org/10.1016/j.image.2012.10.002
  10. O. Russakovsky, et al, "Imagenet large scale visual recognition challenge," International Journal of Computer Vision, vol. 115, no. 3, pp. 211-252, April, 2015. https://doi.org/10.1007/s11263-015-0816-y
  11. M. K.Vairalkar, and S. U. Nimbhorkar, "Edge detection of images using sobel operator," International Journal of Emerging Technology and Advanced Engineering, vol. 2, no. 1, pp. 291-293, January, 2012.
  12. P. Soille, Morphological image analysis: principles and applications, 2nd ed, New York, NY: Springer Science & Business Media, 2013.
  13. I. Khalifa, A. E. Aboutabl, and G. S. A. Aziz, "A New Image Model for Predicting Cracks in Sewer Pipes based on Time," International Journal of Computer Applications, vol. 87, no. 9, pp. 25-32, February, 2014. https://doi.org/10.5120/15238-3779

피인용 문헌

  1. 이진 분류를 위하여 거리계산을 이용한 특징 변환 기반의 가중된 최소 자승법 vol.24, pp.2, 2018, https://doi.org/10.6109/jkiice.2020.24.2.219
  2. 소방관의 요구조자 탐색을 위한 인공지능 처리 임베디드 시스템 개발 vol.24, pp.12, 2020, https://doi.org/10.6109/jkiice.2020.24.12.1612