предыдущий|следующий

Improved cascade forest deep learning model for hyperspectral imagery classification

  • role： First author第一作者
  • Affiliation：

    Key Laboratory of Land, Environment and Disaster Monitoring. Ministry of Natural Resources, China University of Mining and Technology, Xuzhou 221116, China

  • Email：wufuyu666@163.com
  • Introduction：武复宇，1993年生，男，博士研究生，研究方向为高光谱信息处理。E-mail: wufuyu666@163.com
WU Fuyu1,  
  • Affiliation：

    Key Laboratory of Land, Environment and Disaster Monitoring. Ministry of Natural Resources, China University of Mining and Technology, Xuzhou 221116, China

WANG Xue1,  
  • Affiliation：

    The Second Surveying and Mapping Institute of Hebei, Shijiazhuang 050037, China

DING Jianwei3,  
  • Affiliation：

    Key Laboratory for Satellite Mapping Technology and Applications of Ministry of Natural Resources, Nanjing University, Nanjing 210023, China

DU Peijun4,  
  • role： Corresponding author通信作者
  • Affiliation：

    Key Laboratory of Geographic Information Science, Ministry of Education, East China Normal University, Shanghai 200241, China

    Key Laboratory of Land, Environment and Disaster Monitoring. Ministry of Natural Resources, China University of Mining and Technology, Xuzhou 221116, China

  • Email：tankuncu@126.com
  • Introduction：谭琨，1981年生，男，教授，研究方向为高光谱遥感，环境遥感。E-mail:tankuncu@126.com
TAN Kun21*

реферат

With the release of GF-5 hyperspectral data, hyperspectral remote sensing plays an increasingly important role in environmental monitoring, emergency management, and object extraction. Classification is the primary problem of hyperspectral image applications. Some cascade forest models have been proposed to overcome the limitations of traditional deep neural networks, such as requiring excessive training samples and optimization of a large number of hyperparameters. Traditional cascade forest models have several disadvantages, such as (1) high model complexity, (2) homogeneous base classifiers, and (3) inability to discriminate the similar spectrum. In this study, a novel classification approach based on cascade forest is proposed to solve the above drawbacks.The proposed improved cascade forest is an accumulation of layers, and each layer consists of two decision tree forests and a logistic regression classifier. Compared with traditional models, the number of forests in the improved method is reduced from four to two with the same accuracy and efficiency. Meanwhile, the original completely random tree forest is replaced by an efficient rotation forest to improve the diversity. The logistic regression classifier is added to determine the separating hyperplane among similar spectra. The number of layers is determined by the accuracy of validation set.The proposed method is implemented on three hyperspectral datasets (GF-5, Indian Pines, and Pavia University datasets). DBN, SVM, RoF, RF, and original cascade forest are selected as the contrast methods. Experimental results on three different real hyperspectral datasets confirms the superiority of the proposed method, especially on the Indian Pines dataset, which has a similar spectrum. The improved cascade model can combine multiple classification results from different base classifiers to obtain the final results through the logistic regression classifier, and the quadratic discriminant process of the logistic regression classifier can effectively improve the classification accuracy. The impacts of the number of trees on the final results are discussed. The proposed model obtains the best performance with optimal parameters. Although the single training time is long, the insensitivity of model parameters immensely improves the training efficiency.Compared with DNN, the improved cascade forest has the following advantages: (1) adaptive to determine the number of layers on the basis of the classification accuracy, (2) few hyperparameters are required in the improved cascade forest, making it easy to optimize the structure, and (3) each forest is independently trained because the training process do not have backpropagation, thereby accelerating the improved cascade forest by the CPU.

ключеви́че слова́

remote sensing;hyperspectral classification;cascade forest;rotation forest;ensemble learning;deep learning

References

  1. 1.
    Breiman L. 1996. Stacked regressions. Machine Learning, 24(1): 49-64
  2. 2.
    Cao X H, Wen L, Ge Y M, Zhao J and Jiao L C. 2019. Rotation-based deep forest for hyperspectral imagery classification. IEEE Geoscience and Remote Sensing Letters, 16(7): 1105-1109
  3. 3.
    Chen Y S, Lin Z H, Zhao X, Wang G and Gu Y F. 2014. Deep learning-based classification of hyperspectral data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2094-2107
  4. 4.
    Clarke B. 2003. Comparing Bayes model averaging and stacking when model approximation error cannot be ignored. Journal of Machine Learning Research, 4(4): 683-712
  5. 5.
    Du P J, Xia J S, Xue Z H, Tan K, Su H J and Bao R. 2016. Review of hyperspectral remote sensing image classification. Journal of Remote Sensing, 20(2): 236-256
  6. 6.
    Feng W and Bao W X. 2017. Weight-based rotation forest for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 14(11): 2167-2171
  7. 7.
    Ham J, Chen Y C, Crawford M M and Ghosh J. 2005. Investigation of the random forest framework for classification of hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 43(3): 492-501
  8. 8.
    Hu J, Tan K and Wu L X. 2015. An improved hyperspectral image clasification algorithm based on multinomial logistic regression. Remote Sensing Technology and Application, 30(1): 135-139
  9. 9.
    Jiao Q J, Zhang B, Liu J G and Liu L Y. 2014. A novel two-step method for winter wheat-leaf chlorophyll content estimation using a hyperspectral vegetation index. International Journal of Remote Sensing, 35(21): 7363-7375
  10. 10.
    Li J, Bioucas-Dias J M and Plaza A. 2012. Spectral–spatial hyperspectral image segmentation using subspace multinomial logistic regression and Markov random fields. IEEE Transactions on Geoscience and Remote Sensing, 50(3): 809-823
  11. 11.
    Li J J, Xi B B, Li Y S, Du Q and Wang K Y. 2018. Hyperspectral classification based on texture feature enhancement and deep belief networks. Remote Sensing, 10(3): 396
  12. 12.
    Li X K, Wang J N, Zhang L F, Wu T X, Yang H, Liu K and Jiang H L. 2014. A combined object-based segmentation and support vector machines approach for classification of Tiangong-1 hyperspectral image. Journal of Remote Sensing, 18(zl): 107-115
  13. 13.
    Liu Z, Tang B, He X F, Qiu Q C and Liu F. 2017. Class-specific random forest with cross-correlation constraints for spectral–spatial hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 14(2): 257-261
  14. 14.
    Melgani F and Bruzzone L. 2004. Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(8): 1778-1790
  15. 15.
    Moser G and Serpico S B. 2013. Combining support vector machines and Markov random fields in an integrated framework for contextual image classification. IEEE Transactions on Geoscience and Remote Sensing, 51(5): 2734-2752
  16. 16.
    Pal M. 2005. Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1): 217-222
  17. 17.
    Paoletti M E, Haut J M, Plaza J and Plaza A. 2018. A new deep convolutional neural network for fast hyperspectral image classification. ISPRS Journal of Photogrammetry and Remote Sensing, 145: 120-147
  18. 18.
    Rodríguez J J, Kuncheva L I and Alonso C J. 2006. Rotation forest: a new classifier ensemble method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(10): 1619-1630
  19. 19.
    Seewald A K. 2002. How to make stacking better and faster while also taking care of an unknown weakness//Proceedings of the Nineteenth International Conference on Machine Learning. San Francisco: Morgan Kaufmann: 554-561
  20. 20.
    Tan K, Li E Z, Du Q and Du P J. 2014. An efficient semi-supervised classification approach for hyperspectral imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 97: 36-45
  21. 21.
    Xia J S, Du P J, He X Y and Chanussot J. 2014. Hyperspectral remote sensing image classification based on rotation forest. IEEE Geoscience and Remote Sensing Letters, 11(1): 239-243
  22. 22.
    Xu J H, Shen Y, Liu P F and Xiao L. 2018. Hyperspectral image classification combining kernel sparse multinomial logistic regression and TV-L1 error rejection. Acta Electronica Sinica, 46(1): 175-184
  23. 23.
    Zhang B. 2016. Advancement of hyperspectral image processing and information extraction. Journal of Remote Sensing, 20(5): 1062-1090
  24. 24.
    Zhang B, Chen Z C, Zheng L F, Tong Q X, Liu Y N, Yang Y D and Xue Y Q. 2004. Object detection based on feature extraction from hyperspectral imagery and convex cone projection transform. Journal of Infrared and Millimeter Waves, 23(6): 441-445, 450
  25. 25.
    Zhang L P and Li J Y. 2016. Development and prospect of sparse representation-based hyperspectral image processing and analysis. Journal of Remote Sensing, 20(5): 1091-1101
  26. 26.
    Zhang L P, Zhang L F and Du B. 2016. Deep learning for remote sensing data: a technical tutorial on the state of the art. IEEE Geoscience and Remote Sensing Magazine, 4(2): 22-40
  27. 27.
    Zhang Y Q, Cao G, Li X S and Wang B S. 2018. Cascaded random forest for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(4): 1082-1094
  28. 28.
    Zhao S H, Liu S H, Wu D, Wu Y T and Liu Q Q. 2018. Potential application analysis of GF-5 satellite in ecology and environment fields. Spacecraft Recovery and Remote Sensing, 39(3): 115-120
  29. 29.
    Zhou Z H and Feng J. 2017. Deep forest: towards an alternative to deep neural networks//Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. Melbourne, Australia: IJCAI: 3553-3559
  30. 30.
    Zhu L, Chen Y S, Ghamisi P and Benediktsson J A. 2018. Generative adversarial networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 56(9): 5046-5063

Читать полностью

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website