Grad-CAM을 적용한 선박 기류 신속 분류를 위한 CNN 모델

송민기¹ ; 김두영²^{, *}

1해군사관학교 인공지능학과 사관생도
2해군 소령/해군사관학교 인공지능학과 부교수

CNN for Rapid Classification of Maritime Signal Flag Using Grad-CAM

Mingi Song¹ ; Dooyoung Kim²^{, *}

1Midshipman, Dept. of Artificial Intelligence, Republic of Korea Naval Academy
2LCDR, ROK Navy/Associate professor, Dept. of Artificial Intelligence, Republic of Korea Naval Academy

Correspondence to: ^*Dooyoung Kim Dept. of Artificial intelligence, Republic of Korea Naval Academy 1 jungwon-ro, Jinhae-gu, Changwon-si, Gyungsangnam-do, 51704, Republic of Korea Tel: +82-2-907-5246 E-mail: dykim07@navy.ac.kr

초록

본 논문에서는 해상 상황에서 의사소통 수단으로 사용되는 기류를 해석하기 위해 Grad-CAM을 적용한 CNN 기반의 딥러닝 모델을 제안한다. 먼저, 기류 데이터를 생성하기 위한 가상환경을 구축하여 다양한 기류 이미지를 생성하였다. CNN을 이용한 기류 분류 모델을 설계하였고, 생성한 가상 이미지를 이용해 학습을 진행하였다. 학습 결과 99.4 %의 정확도로 분류하였고 Grad-CAM을 사용해 분석한 결과 기류의 특징을 정확히 이해하여 분류하였음을 확인할 수 있었다.

Abstract

This paper proposes a CNN-based deep learning model with Grad-CAM applied to interpret maritime signal flag used as a means of communication in maritime environments. First, a virtual environment was constructed to generate various maritime signal flag images for creating data. A CNN classification model was designed, and training was proceeded with the generated virtual images. As a result of the experiment, we classified maritime signal flag with an accuracy of 99.4 %, and confirmed by Grad-CAM that the model accurately understood the features of the maritime signal flag.

Keywords:

Maritime Signal Flag, Convolution Neural Network, Explainable AI, Confusion Matrix

키워드:

기류, 합성곱 신경망, 설명 가능한 인공지능, 혼동 행렬

References

Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, “Gradient-based Learning Applied to Document Recognition,” in Proceedings of the IEEE, Vol. 86, No. 11, pp. 2278-2324, Nov. 1998 [https://doi.org/10.1109/5.726791.8]
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2017. “ImageNet Classification with Deep Convolutional Neural Networks,” Communications of the ACM, Vol. 60, No. 6 (June 2017), pp. 84–90. [https://doi.org/10.1145/3065386]
C. Szegedy et al., “Going Deeper with Convolutions,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 1-9. [https://doi.org/10.1109/CVPR.2015.7298594]
S. Liu and W. Deng, “Very Deep Convolutional Neural Network Based Image Classification Using Small Training Sample Size,” 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), Kuala Lumpur, Malaysia, 2015, pp. 730-734. [https://doi.org/10.1109/ACPR.2015.7486599]
K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770-778. [https://doi.org/10.1109/CVPR.2016.90]
G. Huang, Z. Liu, L. Van Der Maaten and K. Q. Weinberger, “Densely Connected Convolutional Networks,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 2261-2269. [https://doi.org/10.1109/CVPR.2017.243]
Mingxing Tan, Quoc V. Le. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. ArXiv Preprint ArXiv:1905.11946, , 2019
B. Zhou, A. Khosla, A. Lapedriza, A. Oliva and A. Torralba, “Learning Deep Features for Discriminative Localization,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 2921-2929. [https://doi.org/10.1109/CVPR.2016.319]
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh and D. Batra, “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 618-626. [https://doi.org/10.1109/ICCV.2017.74]
https://krikienoid.github.io/flagwaver/
J. Nagi et al., “Max-pooling Convolutional Neural Networks for Vision-based Hand Gesture Recognition,” 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuala Lumpur, Malaysia, 2011, pp. 342-347. [https://doi.org/10.1109/ICSIPA.2011.6144164]
Agarap, A. F. “Deep Learning Using Rectified Linear Units (relu),” ArXiv Preprint arXiv:1803.08375, , 2018.
Glorot, Xavier, and Yoshua Bengio, “Understanding the Difficulty of Training Deep Feedforward Neural Networks,” Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, JMLR Workshop and Conference Proceedings, 2010.
Zhilu Zhang, Mert R. Sabuncu. “Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels,” ArXiv Preprint arXiv:1805.07836
Sebastian Ruder. “An Overview of Gradient Descent Optimization Algorithms,” ArXiv Preprint arXiv:1609.04747