The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

HyperConv: spatio-spectral classication of hyperspectral images with deep convolutional neural networks

심층 컨볼루션 신경망을 사용한 초분광 영상의 공간 분광학적 분류 기법

  • Ko, Seyoon (Department of Statistics, Seoul National University) ;
  • Jun, Goo (Department of Epidemiology, Human Genetics & Environmental Sciences, The University of Texas Health Science Center at Houston) ;
  • Won, Joong-Ho (Department of Statistics, Seoul National University)
  • Received : 2016.05.01
  • Accepted : 2016.06.30
  • Published : 2016.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Land cover classification is an important tool for preventing natural disasters, collecting environmental information, and monitoring natural resources. Hyperspectral imaging is widely used for this task thanks to sufficient spectral information. However, the curse of dimensionality, spatiotemporal variability, and lack of labeled data make it difficult to classify the land cover correctly. We propose a novel classification framework for land cover classification of hyperspectral data based on convolutional neural networks. The proposed framework naturally incorporates full spectral features with the information from neighboring pixels and has advantages over existing methods that require additional feature extraction or pre-processing steps. Empirical evaluation results show that the proposed framework provides good generalization power with classification accuracies better than (or comparable to) the most advanced existing classifiers.

초분광 영상 데이터는 픽셀마다 수백 개의 스펙트럼 밴드에 대한 정보가 주어지는 고차원 데이터로, 농업, 식품처리, 광물학, 물리학, 환경학, 지리학 등 광범위한 분야에 활용되고 있다. 그 중 하나는 토지 피복의 분류 문제인데, 이는 자연 재해 예방, 자연 자원 감시, 환경에 대한 정보 수집에 있어서 중요한 문제이다. 하지만 차원의 저주, 시공간적 변동성, 레이블된 데이터의 부족 때문에 토지 피복의 정확한 분류에는 어려움이 따른다. 이 논문에서는 이러한 문제를 해결하기 위해 컨볼루션 신경망에 기반한 새로운 심층 학습 구조를 제안한다. 제안된 구조는 원하는 지점 주변 픽셀의 정보를 컨볼루션 신경망을 통해 처리하고, 그 지점의 스펙트럼 정보를 강조하기 위해 컨볼루션 층의 출력과 스펙트럼 정보를 함께 소프트맥스 분류기의 입력으로 사용한다. 이 구조는 추가적인 특징 추출 과정을 필요로 하지 않고, 그래픽 처리 장치 등을 이용한 병렬화가 간편하다는 점에서 기존 방법들보다 유리하다. 실험 결과, 제안된 구조는 기존에 가장 좋은 성능을 보인 분류기와 비슷하거나 더 좋은 분류 정확도를 보여 좋은 일반화 성능을 보이는 것을 확인할 수 있었다.

Keywords

References

  1. Bengio, Y. (2009). Learning deep architectures for AI, Foundations and Trends in Machine Learning, 2, 1-127. https://doi.org/10.1561/2200000006
  2. Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., and Bengio, Y. (2010). Theano: a CPU and GPU math expression compiler. In Proceedings of the Python for Scientic Computing Conference (SciPy).
  3. Camps-Valls, G., Tuia, D., Bruzzone, L., and Atli Benediktsson, J. (2014). Advances in hyperspectral image classification: Earth monitoring with statistical learning methods, Signal Processing Magazine, IEEE, 31, 45-54.
  4. Chen, Y., Lin, Z., Zhao, X., Wang, G., and Gu, Y. (2014). Deep learning-based classification of hyperspectral data, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7, 2094-2107. https://doi.org/10.1109/JSTARS.2014.2329330
  5. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. Book in preparation for MIT Press. Retrieved from http://www.deeplearningbook.org.
  6. Gualtieri, J. A. and Chettri, S. (2000). Support vector machines for classification of hyperspectral data. In Geoscience and Remote Sensing Symposium, 2000. Proceedings. IGARSS 2000. IEEE 2000 International, 2, 813-815.
  7. Hinton, G. (2010). A practical guide to training restricted Boltzmann machines, Momentum, 9, 926.
  8. Hinton, G., Osindero, S., and Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets, Neural Computation, 18, 1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
  9. Hinton, G. E. and Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks, Science, 313, 504-507. https://doi.org/10.1126/science.1127647
  10. Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. R. (2012). Improving neural networks by preventing co-adaptation of feature detectors, arXiv preprint arXiv:1207.0580.
  11. Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, 1097-1105.
  12. LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., and Jackel, L. D. (1989). Backpropagation applied to handwritten zip code recognition, Neural Computation, 1, 541-551. https://doi.org/10.1162/neco.1989.1.4.541
  13. LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. In Proceedings of the IEEE, 86, 2278-2324.
  14. Masci, J., Meier, U., Ciresan, D., and Schmidhuber, J. (2011). Stacked convolutional auto-encoders for hierarchical feature extraction. In Articial Neural Networks and Machine Learning-ICANN 2011 (pp. 52-59), Springer.
  15. Melgani, F. and Lorenzo, B. (2004). Classification of hyperspectral remote sensing images with support vector machines, IEEE Transactions on Geoscience and Remote Sensing, 42, 1778-1790. https://doi.org/10.1109/TGRS.2004.831865
  16. Nair, V. and Hinton, G. E. (2010). Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), 807-814.
  17. Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.-A. (2008). Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th International Conference on Machine Learning (pp. 1096-1103), ACM.
  18. Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., and Manzagol, P.-A. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion, The Journal of Machine Learning Research, 11, 3371-3408.
  19. Yang, J., Yu, K., Gong, Y., and Huang, T. (2009). Linear spatial pyramid matching using sparse coding for image classification. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on (pp. 1794-1801).