The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Road Surface Damage Detection based on Object Recognition using Fast R-CNN

Fast R-CNN을 이용한 객체 인식 기반의 도로 노면 파손 탐지 기법

  • Shim, Seungbo (Korea Institute of Civil Engineering and Building Technology) ;
  • Chun, Chanjun (Korea Institute of Civil Engineering and Building Technology) ;
  • Ryu, Seung-Ki (Korea Institute of Civil Engineering and Building Technology)
  • Received : 2019.02.24
  • Accepted : 2019.03.28
  • Published : 2019.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The road management institute needs lots of cost to repair road surface damage. These damages are inevitable due to natural factors and aging, but maintenance technologies for efficient repair of the broken road are needed. Various technologies have been developed and applied to cope with such a demand. Recently, maintenance technology for road surface damage repair is being developed using image information collected in the form of a black box installed in a vehicle. There are various methods to extract the damaged region, however, we will discuss the image recognition technology of the deep neural network structure that is actively studied recently. In this paper, we introduce a new neural network which can estimate the road damage and its location in the image by region-based convolution neural network algorithm. In order to develop the algorithm, about 600 images were collected through actual driving. Then, learning was carried out and compared with the existing model, we developed a neural network with 10.67% accuracy.

도로 관리 주체는 도로 파손을 보수하기 위해 적지 않은 비용을 투입한다. 이러한 파손은 자연 요인과 노후화로 인하여 필연적으로 발생을 하는데, 효율적인 보수를 위한 유지보수 기술이 필요하다. 이런 수요에 대응하기 위해 여러 가지 기술들이 개발되고 적용되고 있지만, 최근 들어서는 차량용 블랙박스 형태로 수집한 영상 정보를 바탕으로 도로 노면 파손 유지 보수기술이 개발되고 있다. 이 파손 영역을 추출하는 방법에는 여러 가지가 있지만, 본 논문에서는 최근 활발히 연구되고 있는 심층 신경망 구조의 영상인식 기술에 대해 논하고자 한다. 특히 영역 기반의 합성곱 알고리즘을 이용하여 영상 내에서 도로 파손 유무와 그 영역을 추정할 수 있는 새로운 심층 신경망을 소개한다. 이를 개발하기 위해 실제 주행을 통해서 600여장의 영상 데이터를 수집하였고, 이를 활용하여 학습을 수행하였다. 그 결과 기존 모델과 성능을 비교하여 10.67% 향상된 신경망을 개발하였다.

Keywords

References

  1. Buza E., Omanovic S. and Huseinovic A.(2013), "A pothole detection with image processing and spectral clustering," in Proc. the 2nd International Conference on Information Technology and Computer Networks, Antalya, Turkeys, 8-10 October, pp.48-53.
  2. Chun C., Shim S., Kang S. and Ryu S. K.(2018), "Development and evaluation of automatic pothole detection using fully convolutional neural networks," Journal of the Korea Institute of Intelligent Transport System, vol. 17, no. 5, pp.55-64.
  3. Girshick R.(2015), "Fast r-cnn," in Proc. The IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, pp.1440-1448.
  4. Girshick R., Donahue J., Darrell T. and Malik J.(2014), "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proc. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, pp.580-587.
  5. He K., Gkioxari G., Dollar P. and Girshick R.(2017), "Mask R-CNN," in Proc. The IEEE International Conference on Computer Vision (ICCV), Venezia, Italy, pp.2980-2988.
  6. He K., Zhang X., Ren S. and Sun J.(2016), "Deep residual learning for image recognition," in Proc. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, pp.770-778.
  7. Jo Y., Ryu S. K. and Kim Y. R.(2016), "Pothole detection based on the features of intensity and motion," Journal of the Transportation Research Board, no. 2595, pp.18-28.
  8. Jog G. M., Koch C., Golparvar-Fard M. and Brilakis I.(2012), "Pothole properties measurement through visual 2D recognition and 3D reconstruction," Computing in Civil Engineering, pp.553-560.
  9. Koch C. and Brilakis I.(2011), "Pothole detection in asphalt pavement images," Advanced Engineering Information, vol. 25, no. 1, pp.507-515. https://doi.org/10.1016/j.aei.2011.01.002
  10. Krizhevsky A., Sutskever I. and Hinton G. E.(2012), "Imagenet classification with deep convolutional neural networks," in Proc. Advances in Neural Information Processing Systems (NIPS 2012), Montreal, Canada, pp.1097-1105.
  11. Ren S., He K., Girshick R. and Sun J.(2015), "Faster R-CNN: towards real-time object detection with region proposal networks," in Proc. Advances in Neural Information Processing Systems 28 (NIPS 2015), Montreal, Canada, pp.91-99.
  12. Ryu S. K., Kim T. and Kim Y. R.(2015), "Feature-based pothole detection in two-dimensional images," Journal of the Transportation Research Board, no. 2528, pp.9-17.
  13. Simonyan K. and Zisserman A.(2014), "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556.
  14. Uijlings J. R., Van De Sande K. E., Gevers T. and Smeulders A. W.(2013), "Selective Search for Object Recognition," International Journal of Computer Vision, vol. 104, no. 2, pp.154-171. https://doi.org/10.1007/s11263-013-0620-5