한국산업정보학회논문지 (Journal of Korea Society of Industrial Information Systems)

한국산업정보학회 (Korea Society of Industrial Information Systems)
권호 표지
DOI QR코드

DOI QR Code

Mask R-CNN을 이용한 항공 영상에서의 도로 균열 검출

Crack Detection on the Road in Aerial Image using Mask R-CNN

  • 이민혜 (군산대학교 컴퓨터정보통신공학부) ;
  • 남광우 (군산대학교 컴퓨터정보통신공학부) ;
  • 이창우 (군산대학교 컴퓨터정보통신공학부)
  • 투고 : 2019.06.07
  • 심사 : 2019.06.19
  • 발행 : 2019.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

기존의 균열 검출 방법은 많은 인력과 시간, 비용이 소모되는 문제점이 있다. 이러한 문제를 해결하고자 차량이나 드론을 이용하여 취득한 영상에서 균열 정보를 파악하고 정보화하는 자동검출시스템이 요구되고 있다. 본 논문에서는 드론으로 촬영한 도로 영상에서의 균열 검출 연구를 진행한다. 획득한 항공영상은 전처리와 라벨링(Labeling) 작업을 통해 균열의 형태정보 데이터셋(data set)을 생성한다. 생성한 데이터셋을 Mask R-CNN(regions with convolution neural network) 딥러닝(deep learning) 모델에 적용하여 다양한 균열 정보가 학습된 새로운 모델을 획득하였다. 획득 모델을 이용한 실험 결과, 제시된 항공 영상에서 균열을 평균 73.5%의 정확도로 검출하였으며 특정 형태의 균열 영역도 예측하는 것을 확인할 수 있었다.

Conventional crack detection methods have a problem of consuming a lot of labor, time and cost. To solve these problems, an automatic detection system is needed to detect cracks in images obtained by using vehicles or UAVs(unmanned aerial vehicles). In this paper, we have studied road crack detection with unmanned aerial photographs. Aerial images are generated through preprocessing and labeling to generate morphological information data sets of cracks. The generated data set was applied to the mask R-CNN model to obtain a new model in which various crack information was learned. Experimental results show that the cracks in the proposed aerial image were detected with an accuracy of 73.5% and some of them were predicted in a certain type of crack region.

키워드

SOJBB3_2019_v24n3_23_f0001.png 이미지

Fig. 1 Preprocessing

SOJBB3_2019_v24n3_23_f0002.png 이미지

Fig. 2 Annotation data using VIA

SOJBB3_2019_v24n3_23_f0003.png 이미지

Fig. 3 Display images and masks

SOJBB3_2019_v24n3_23_f0004.png 이미지

Fig. 4 Example of ideal crack detection (training data set)

SOJBB3_2019_v24n3_23_f0005.png 이미지

Fig. 5 Detection of crack on the roads

Table 1 Accuracy of crack on the roads

SOJBB3_2019_v24n3_23_t0001.png 이미지

참고문헌

  1. Kang, Y. M. and Kang, C. W, Han, K. S., Kim, J. B., “A study on network strategy for smart society by analysis of spatial information technology trends,” Journal of the Korea Institute of Information and Communication Engineering, Vol. 19, No. 6, pp. 1411-1418, 2015. https://doi.org/10.6109/jkiice.2015.19.6.1411
  2. Seo, G. H., "GeoAI-based land-use change monitoring innovation and utilization plan," Technical Report: KRIHS Policy Brief, No. 694. 2018.
  3. Kim, H. J., Eo, Y. D., Lee, J. M. and Bae, G. H., “Application research on Obstruction area detection of building wall using R-CNN technique,” Journal of Cadastre & Land InformatiX, Vol. 48, No. 2, pp. 213-225, 2018. https://doi.org/10.22640/LXSIRI.2018.48.2.213
  4. Joo, Y. J., “Detection method for road pavement defect of UAV imagery based on computer vision,” Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 35, No. 6, pp. 599-608, 2017. https://doi.org/10.7848/KSGPC.2017.35.6.599
  5. Choi, S. W., Lee, K. T., Kim, K. S. and Kwak, S. Y., "Lane departure warning system using deep learning," Journal of the Korea Industrial Information Systems Research Vol. 24 No. 2, pp. 25-31, 2019. https://doi.org/10.9723/JKSIIS.2019.24.2.025
  6. Lee, D. S. and Kwon, S. K., "Vehicle plate detection method by measuring plane similarity using depth information," Journal of the Korea Industrial Information Systems Research, Vol. 24 No. 2, pp. 47-55, 2019. https://doi.org/10.9723/JKSIIS.2019.24.2.047
  7. He, K., Gkioxari G., Dollar P. and Girshick R., "Mask R-CNN", IEEE International Conference on Computer Vision(ICCV), pp. 2980-2988, March 2017.
  8. Eulsukdo Bridge Corporation, "Bridge maintenance management system," Maintenance Guide Book, 2014.
  9. Kim, Y. R., Kim, T. H. and Ryu, S. K., “Pothole detection method in asphalt pavement,” Journal of The Institute of Electronics and Information Engineers, Vol. 51, No. 10, pp. 2382-2389, 2014.
  10. Zhang, A., Kelvin, C. P. W., Li, B., Yang, E., Dai, X., Peng, Y., Fei, Y., Liu, Y., Joshua, Q. Li. and Chen, D., “Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning metwork,” Computer-Aided Civil and Infrastructure Engineering, Vol. 32, No. 5, pp. 1-15, 2017. https://doi.org/10.1111/mice.12249
  11. Krizhevsky A., Sutskever I. and Hinton G., "ImageNet classification with deep convolutional neural networks," Advances in Neural Information Processing Systems (NIPS), pp.1097-1105, 2012.
  12. Lee, D. S. and Yoon, S., Lee, J. W., Park, D. S., “Real-time license plate detection based on faster R-CNN,” KIPS Transactions on Software and Data Engineering, Vol. 5, No. 11, pp. 511-520, 2016. https://doi.org/10.3745/KTSDE.2016.5.11.511
  13. Lee, J. H., Kim, B. M. and Shin, S. Y., "Effects of preprocessing and feature extraction on CNN-based fire detection performance," Journal of the Korea Industrial Information Systems Research Vol. 23 No. 4, pp. 41-53, 2018. https://doi.org/10.9723/JKSIIS.2018.23.4.041
  14. Ren, S., He. K., Girshick R. and Sun J., "Faster R-CNN: Towards real-time object detection with region proposal networks," Advances in Neural Information Processing Systems (NIPS), pp.91-99, 2015.
  15. Dutta, A., Gupta, A. and Zisserman A., Visual geometry group, University of Oxford, http://www.robots.ox.ac.uk/-vgg/software/via (accessed on June, 19th, 2019)
  16. https://github.com/matterport/Mask_RCNN (accessed on June, 19th, 2019)
  17. Lin, T.-Y., Maire M., Belongie S., Hays J., Perona P., Ramanan D., Dollar P. and ZitnickL, C., "Microsoft COCO: common objects in context," European Conference on Computer Vision(ECCV), 2014.