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

  • 제18권4호
  • /
  • Pages.71-79
  • /
  • 2019
  • /
  • 1738-0774(pISSN)
  • /
  • 2384-1729(eISSN)
한국ITS학회 (The Korea Institute of Intelligent Transport Systems)
권호 표지
DOI QR코드

DOI QR Code

수도 레이블을 활용한 준지도 학습 기반의 도로노면 파손 탐지

Road Surface Damage Detection Based on Semi-supervised Learning Using Pseudo Labels

  • Chun, Chanjun (Korea Institute of Civil Engineering and Building Technology (KICT)) ;
  • Ryu, Seung-Ki (Korea Institute of Civil Engineering and Building Technology (KICT))
  • 투고 : 2019.04.26
  • 심사 : 2019.07.01
  • 발행 : 2019.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

의미론적 분할 형태로 합성곱 신경망을 구성하여 도로노면의 파손을 탐지하는 연구가 진행되고 있다. 이러한 합성곱 신경망 형태의 모델을 생성하기 위해서는 입력 이미지와 이에 상응한 레이블된 이미지 데이터셋으로 수집해야 하고, 이러한 과정에서는 굉장히 많은 시간과 비용이 발생하게 된다. 본 논문에서는 이러한 작업을 완화하기 위하여 수도 레이블링을 활용한 준지도 학습 기반의 도로노면 파손 탐지 기술을 제안하고자 한다. 레이블된 데이터셋과 레이블되지 않은 데이터셋을 적절하게 혼합하여 도로노면 파손을 탐지하는 모델을 업데이트하고, 이를 레이블된 데이터셋만을 활용한 기존 모델과 성능을 비교한다. 주관적인 성능결과, 민감도 부분에서는 조금 저하된 성능을 보였지만, 정밀도 부분에서는 대폭 성능 향상이 있었으며, 최종적으로 $F_1-score$ 또한 높은 수치로 평가되었다.

By using convolutional neural networks (CNNs) based on semantic segmentation, road surface damage detection has being studied. In order to generate the CNN model, it is essential to collect the input and the corresponding labeled images. Unfortunately, such collecting pairs of the dataset requires a great deal of time and costs. In this paper, we proposed a road surface damage detection technique based on semi-supervised learning using pseudo labels to mitigate such problem. The model is updated by properly mixing labeled and unlabeled datasets, and compares the performance against existing model using only labeled dataset. As a subjective result, it was confirmed that the recall was slightly degraded, but the precision was considerably improved. In addition, the $F_1-score$ was also evaluated as a high value.

키워드

참고문헌

  1. Badrinarayanan V., Kendall A. and Cipolla R.(2017), "SegNet: A deep convolutional encoder-decoder architecture for image segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 12, pp.2481-2495. https://doi.org/10.1109/TPAMI.2016.2644615
  2. Bishop C.(2013), Pattern Recognition and Machine Learning, Springer, New York, NY.
  3. Cholaquidis A., Fraimand R. and Sued M.(2018), "On semi-supervised learning," arXiv:1805.09180v2.
  4. 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 Korea Institute of Intelligent Transportation System, vol. 17, no. 5, pp.55-64.
  5. Eigen D., Puhrsch C. and Fergus R.(2014), "Depth map prediction from a single image using a multi-scale deep network," in Proc. the 27th International Conference on Neural Information Processing Systems (NIPS), Montreal, Canada, pp.2366-2374.
  6. Goodfellow I., Bengio Y. and Courville A.(2016), Deep Learning, MIT Press, Cambridge, MA.
  7. Goutte C. and Gaussier E.(2005), "A probabilistic interpretation of precision, recall and F-score, with implication for evaluation," in Proc. the 27th European Conference on Advances in Information Retrieval Research (ECIR), Santiago de Compostela, Spain, pp.345-359.
  8. Han W., Wu C., Zhang X., Sun M. and Min G.(2016), "Speech enhancement based on improved deep neural networks with MMSE pretreatment features," in Proc. the IEEE 13th International Conference on Signal Processing (ICSP), Chengdu, China.
  9. Ioffe S. and Szegedy C.(2015), "Batch normalization: accelerating deep network training by reducing internal covariate shift," in Proc. the 32nd International Conference on Machine Learning (ICML), Lille, France, pp.448-456.
  10. Kim T. and Ryu S. K.(2014), "Review and analysis of pothole detection methods," Journal of Emerging Trends in Computing and Information Sciences, vol. 5, no. 8, pp.603-608.
  11. Kingma D. P. and Ba J. L.(2015), "ADAM: a method for stochastic optimization," in Proc. 3rd International Conference on Learning Representations (ICLR), San Diego, CA, pp.1-15.
  12. Krizhevsky A., Sutskever I. and Hinton G. E.(2012), "Imagenet classification with deep convolutional neural networks," in Proc. the 27th International Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, NV, pp.1097-1105.
  13. Long J., Shelhamer E. and Darrell T.(2015), "Fully convolutional networks for semantic segmentation," in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, pp.3431-3440.
  14. Maclin R. and Opitz D.(1999), "Popular ensemble methods: an empirical study," Journal of Artificial Intelligence Research, vol. 11, no. 1, pp.169-198. https://doi.org/10.1613/jair.614
  15. Nair V. and Hinton G. E.(2010), "Rectified linear units improve restricted boltzmann machines," in Proc. the 27th International Conference on Machine Learning (ICML), Haifa, Israel, pp.807-814.
  16. Ren S., He K., Girshick R. and Sun J.(2017), "Faster R-CNN: towards real-time object detection with region proposal networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp.1137-1149. https://doi.org/10.1109/TPAMI.2016.2577031