Précédent|Prochain

Deep unfolding network for hyperspectral anomaly detection

  • role： First author第一作者
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    School of Mathematics and Statistics, Southeast University, Nanjing 210089, China

  • Email：lichenyu@seu.edu.cn
  • Introduction：李晨玉，研究方向为遥感大数据。E-mail： lichenyu@seu.edu.cn
LI Chenyu12,  
  • role： Corresponding author通信作者
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China

  • Email：hongdf@aircas.ac.cn
  • Introduction：洪丹枫，研究方向人工智能，多模态遥感大数据。E-mail： hongdf@aircas.ac.cn
HONG Danfeng13*,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    School of Mathematics and Statistics, Southeast University, Nanjing 210089, China

    College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China

ZHANG Bing124

résumé

Hyperspectral Anomaly Detection(HAD) is one of the most critical topic in hyperspectral remote sensing and has been extensively addressed in the literature over the past decade. Among them, Low-Rank Representation(LRR) models are widely used owing to their powerful separation ability for the background and targets. But their applications in practical situations still remain limited due to the extreme dependence on manual parameter selection and relatively poor generalization ability. To this end, this paper combines the LRR model with deep learning techniques to propose a new underlying network for HAD, called LRR-Net. This method efficiently solves the LRR model with the help of the Alternating Direction Method of Multipliers (ADMM) optimizer, and incorporates the solution as a priori knowledge into the deep network to guide the optimization of parameters, providing a theoretical basis for deep networks. In addition, LRR-Net converts a series of regularized parameters into learnable network parameters in an end-to-end manner, thus avoiding manual tuning of parameters. Experimental results obtained from publicly available datasets and our datasets demonstrate that the LRR-Net method outperforms many state-of-the-art model-based and deep-based algorithms of hyperspectral anomaly detection. Overall, deep learning networks are powerful in learning and are robust compared to traditional models in processing datasets with different complexity. However, despite the strong fitting ability of deep learning data, the necessary prior information is lacking, which often makes the algorithm fall into the local optima, which leads to the failure of deep learning to guarantee the stability of HAD results. The model-based algorithm can better make up for this defect, which can often get better results by improving the separability between the background and the target. Nonetheless, these LRR-based methods are unable to effectively suppress background noise due to their limited representation power, such as shadows, trees, and edges in complex scenes, with relatively large volatility in detection effects. The LRR-Net presented in this paper combines the advantages of the above two methods, and the experimental results of four typical scenarios show that the search of the optimal parameters in the neural network can effectively solve the HAD problem in an adaptive way, which is more physically meaningful.

mots-clés

hyperspectral remote sensing image;anomaly detection;deep unfolding;Low-Rank Representation (LRR);Alternating Direction Multiplier Method (ADMM)

References

  1. 1.
    Boyd S, Parikh N, Chu E, Peleato B and Eckstein J. 2011. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends® in Machine Learning, 3(1): 1-122
  2. 2.
    Chang C I. 2022. Effective anomaly space for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5526624
  3. 3.
    Chen S Y, Yang S M, Kalpakis K and Chang C I. 2013. Low-rank decomposition-based anomaly detection//Processing of SPIE 8743, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIX. Baltimore: SPIE: 87430N
  4. 4.
    Goodfellow I, Bengio Y and Courville A. 2016. Deep Learning. Cambridge: MIT Press
  5. 5.
    Hong D F, Zhang B, Li H, Li Y X, Yao J, Li C, Werner M., Chanussot J., Zipf A., Xiao X X. Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks. Remote Sensing of Environment, 299(15)：0034-4257
  6. 6.
    Hong D F, Zhang B, Li X, Li Y, Li C, Yao J, Yokoya N, Li H, Jia X, Plaza A, Gamba P, Benediktsson J, Chanusso J. “SpectralGPT: Spectral Foundation Model.” arXiv preprint arXiv:2311.07113, 2023.
  7. 7.
    Huyan N, Zhang X R, Zhou H Y and Jiao L C. 2019. Hyperspectral anomaly detection via background and potential anomaly dictionaries construction. IEEE Transactions on Geoscience and Remote Sensing, 57(4): 2263-2276
  8. 8.
    Jiang T, Li Y S, Xie W Y and Du Q. 2020. Discriminative reconstruction constrained generative adversarial network for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 58(7): 4666-4679
  9. 9.
    Khazai S, Homayouni S, Safari A and Mojaradi B. 2011. Anomaly detection in hyperspectral images based on an adaptive support vector method. IEEE Geoscience and Remote Sensing Letters, 8(4): 646-650
  10. 10.
    Li W and Du Q. 2015. Collaborative representation for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 53(3): 1463-1474
  11. 11.
    Lin Z C, Liu R S and Su Z X. 2011. Linearized alternating direction method with adaptive penalty for low-rank representation//Proceedings of the 24th International Conference on Neural Information Processing Systems (NIPS). Granada: Curran Associates Inc.: 612-620
  12. 12.
    Liu G C, Lin Z C, Yan S C, Sun J, Yu Y and Ma Y. 2013. Robust recovery of subspace structures by low-rank representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1): 171-184
  13. 13.
    Manolakis D and Shaw G. 2002. Detection algorithms for hyperspectral imaging applications. IEEE Signal Processing Magazine, 19(1): 29-43
  14. 14.
    Molero J M, Garzon E M, Garcia I and Plaza A. 2013. Analysis and optimizations of global and local versions of the RX algorithm for anomaly detection in hyperspectral data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2): 801-814
  15. 15.
    Reed I S and Yu X L. 1990. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution. IEEE Transactions on Acoustics, Speech, and Signal Processing, 38(10): 1760-1770
  16. 16.
    Shen H F, Jiang M H, Li J, Zhou C X, Yuan Q Q and Zhang L P. 2022. Coupling model- and data-driven methods for remote sensing image restoration and fusion: improving physical interpretability. IEEE Geoscience and Remote Sensing Magazine, 10(2): 231-249
  17. 17.
    Tong Q X, Zhang B and Zhang L F. 2016. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 20(5): 689-707
  18. 18.
    Vane G and Goetz A F H. 1988. Terrestrial imaging spectroscopy. Remote Sensing of Environment, 24(1): 1-29
  19. 19.
    Wang S Y, Wang X Y, Zhang L P and Zhong Y F. 2022. Auto-AD: autonomous hyperspectral anomaly detection network based on fully convolutional autoencoder. IEEE Transactions on Geoscience and Remote Sensing, 60: 5503314
  20. 20.
    Wu X, Hong D F and Chanussot J. 2023. UIU-Net: U-Net in U-Net for infrared small object detection. IEEE Transactions on Image Processing, 32: 364-376
  21. 21.
    Xie Q, Zhou M H, Zhao Q, Meng D Y, Zuo W M and Xu Z B. 2019. Multispectral and hyperspectral image fusion by MS/HS fusion net//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach: IEEE: 1585-1515
  22. 22.
    Xiong F C, Zhou J, Tao S Y, Lu J F and Qian Y T. 2022a. SNMF-Net: learning a deep alternating neural network for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 60: 5510816
  23. 23.
    Xiong F C, Zhou J, Tao S Y, Lu J F, Zhou J T and Qian Y T. 2022b. SMDS-Net: model guided spectral-spatial network for hyperspectral image denoising. IEEE Transactions on Image Processing, 31: 5469-5483
  24. 24.
    Xu Y, Wu Z B, Li J, Plaza A and Wei Z H. 2016. Anomaly detection in hyperspectral images based on low-rank and sparse representation. IEEE Transactions on Geoscience and Remote Sensing, 54(4): 1990-2000
  25. 25.
    Yang L L, Li C, Han J G, Chen C, Ye Q X, Zhang B C, Cao X B and Liu W Q. 2017. Image reconstruction via manifold constrained convolutional sparse coding for image sets. IEEE Journal of Selected Topics in Signal Processing, 11(7): 1072-1081
  26. 26.
    Yang Y, Sun J, Li H B and Xu Z B. 2020. ADMM-CSNet: a deep learning approach for image compressive sensing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(3): 521-538
  27. 27.
    Zhang B. 2016. Advancement of hyperspectral image processing and information extraction. Journal of Remote Sensing, 20(5): 1062-1090
  28. 28.
    Zhang B. 2018. Remotely sensed big data era and intelligent information extraction. Geomatics and Information Science of Wuhan University, 43(12): 1861-1871
  29. 29.
    Zhang Y, Hua W S, Yan Y, Cui Z H and Suo W K. 2019. Progress in hyperspectral anomaly target detection. Laser Journal, 40(7): 6-9
  30. 30.
    Zhu D H, Du B and Zhang L P. 2020. Band selection-based collaborative representation for anomaly detection in hyperspectral images. Journal of Remote Sensing, 24(4): 427-438

Lire l'article complet

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