Anterior|Siguiente

A background memory model for hyperspectral anomaly detection

  • role： First author第一作者
  • Affiliation：

    State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an 710071, China

  • Email：wyxie@xidian.edu.cn
  • Introduction：谢卫莹，研究方向为多模态遥感图像联合解译。E-mail： wyxie@xidian.edu.cn
XIE Weiying,  
  • role： Corresponding author通信作者
  • Affiliation：

    State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an 710071, China

  • Email：jpzhong@stu.xidian.edu.cn
  • Introduction：钟佳平，研究方向为高光谱遥感图像异常检测和多源数据融合。E-mail： jpzhong@stu.xidian.edu.cn
ZHONG Jiaping*,  
  • Affiliation：

    State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an 710071, China

LI Yunsong

resumen

Hyperspectral images (HSIs) have a wealth of continuous spectrum information, covering hundreds of bands from visible light to infrared wavelengths. The data characteristics of HSIs give it a unique advantage in harnessing the inherent attributes of the spectrum in image processing. This advantage is conducive to making full use of spatial and spectral information and detecting targets in the region of interest. However, due to the high dimensionality of hyperspectral data, the complexity of actual scenes, and the limited number of labeled samples, hyperspectral anomaly detection faces the problem of indistinct background and anomalies and low detection accuracy. Therefore, we propose a background memory model for hyperspectral anomaly detection. First, the pseudo background and anomaly vectors are obtained through an unsupervised rough inspection method based on density estimation. Second, we design a background memory generation adversarial network model based on anomalous prominent regular term constraints. Moreover, we expand the distance between the false background and false anomalies in a weak supervision-pseudo-label manner. Thus, the network has a strong background generation ability while the effect on anomaly reconstruction is weakened, which reduces the generalization of background and anomaly reconstruction and enhances the difference and discrimination between background and anomaly. We also perform adversarial learning in the feature domain and image domain to improve sample generation ability, enabling better learning of the distribution of input samples and strengthening the capability to generate background. Finally, a nonlinear background suppression method is introduced to reduce the false alarm rate and further improve the detection accuracy. The experimental results show that our model has a better detection effect on different datasets than other detection algorithms.HSIs have continuous spectral information of hundreds of bands, which make it possible to capture the deep and intrinsic characteristics in a spectrum. However, due to the high dimension of HSI, the complexity of the scene, and the limitation of labeled samples, hyperspectral anomaly detection remains a challenge. To solve the abovementioned problem, we propose a generative adversarial network with anomaly-highlighted regularization and train it in a weakly supervised manner. We aim to separate the anomaly and background vectors to make the difference more obvious and obtain a more accurate detection map.In this paper, we propose a background memory generative adversarial network for hyperspectral anomaly detection. First, we obtain the pseudo background and anomalies through unsupervised coarse detection based on density estimation as the input of the network. Next, to reduce anomaly contamination in background estimation, we impose the constraint of anomaly-highlighted regularization to expand the distance between the background and anomaly. In the weak supervised pseudo labeling training mode, the network can reconstruct background vectors well but gains poor performance for anomaly reconstruction. Besides, there are two discriminators in the latent and reconstruction domains, which aim to improve the ability of background generation and estimation. Finally, we perform nonlinear background suppression on the detection map as post-processing to reduce the false alarm rate.Compared with other new algorithms with good performance, the proposed method has better detection results in both quantitative and qualitative aspects of different datasets. The AUC score of (Pd, Pf) achieves the highest value across different datasets and outperforms other algorithms and has the advantage of an order of magnitude. For example, the AUC score of (Pd, Pf) achieves 0.99771 for the ABU-1 dataset, while the AUC score of (Pf, τ) is 0.00258, which outperforms the second-best algorithm AED with scores of 0.99760 and 0.02230, respectively. The visual results are consistent with the qualitative results as well. The ROC curve locates near the upper left corner. Under the same false alarm rate, the proposed method has the highest accuracy for most datasets, obtaining higher detection probability and lower false alarm rate, and has better detection performance. The box plot likewise reveals that the background and anomaly of this method are more separable.In this paper, we propose a generative adversarial network memorizing background for hyperspectral anomaly detection. Different from our previous work, we obtain the pseudo background and anomaly vector adaptively in an unsupervised manner to solve the problem of the small number of anomaly samples and lack of prior information. Based on weakly supervised pseudo-labeling learning, we aim to model a hyperspectral anomaly and background vector. As a result, the network can reconstruct background data well but performs poorly on anomaly vector reconstruction. We also apply the constraint of highlighting an anomaly regular term in the network to enhance the separability between background and anomaly. Finally, we perform post-processing of nonlinear background suppression to reduce the false alarm rate under the same detection accuracy. Experimental results show that the proposed method can achieve better detection performance than other algorithms on different datasets.

palabra clave

remote sensing;GAN;hyperspectral image;anomaly detection;weakly supervised learning;unsupervised learning

References

  1. 1.
    Akçay S, Atapour-Abarghouei A and Breckon T P. 2019. Skip-GANomaly: skip connected and adversarially trained encoder-decoder anomaly detection//2019 International Joint Conference on Neural Networks. Budapest: IEEE: 1-8
  2. 2.
    Cui G X and Li D K. 2018. Overview on deep learning based on automatic encoder algorithms. Computer Systems & Applications, 27(9): 47-51
  3. 3.
    Del Giorno A, Bagnell J A and Hebert M. 2016. A discriminative framework for anomaly detection in large videos//Proceedings of the 14th European Conference on Computer Vision. Amsterdam: Springer: 334-349
  4. 4.
    Ding K Z, Li J D and Liu H. 2019. Interactive anomaly detection on attributed networks//Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining. Melbourne: ACM: 357-365
  5. 5.
    Ester M, Kriegel H P, Sander J and Xu X W. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise//Proceedings of the 2nd ACM International Conference on Knowledge Discovery and Data Mining. Portland: ACM: 226-231
  6. 6.
    Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A and Bengio Y. 2014. Generative adversarial nets//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal: ACM: 2672-2680
  7. 7.
    Gutiérrez-Gómez L, Bovet A and Delvenne J C. 2020. Multi-scale anomaly detection on attributed networks//Proceedings of the AAAI Conference on Artificial Intelligence. New York: AAAI: 678-685
  8. 8.
    Han Z, Gao L R, Zhang B, Sun X and Li Q T. 2020. Nonlinear hyperspectral unmixing algorithm based on deep autoencoder networks. Journal of Remote Sensing, 24(4): 388-400
  9. 9.
    Kang X D, Zhang X P, Li S T, Li K L, Li J and Benediktsson J A. 2017. Hyperspectral anomaly detection with attribute and edge-preserving filters. IEEE Transactions on Geoscience and Remote Sensing, 55(10): 5600-5611
  10. 10.
    Kwon H and Nasrabadi N M. 2005. Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 43(2): 388-397
  11. 11.
    Li J Y, Zhang H Y, Zhang L P and Ma L. 2015a. Hyperspectral anomaly detection by the use of background joint sparse representation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2523-2533
  12. 12.
    Li L, Li W, Du Q and Tao R. 2021. Low-rank and sparse decomposition with mixture of Gaussian for hyperspectral anomaly detection. IEEE Transactions on Cybernetics, 51(9): 4363-4372
  13. 13.
    Li S T, Zhang K Z, Duan P H and Kang X D. 2020. Hyperspectral anomaly detection with kernel isolation forest. IEEE Transactions on Geoscience and Remote Sensing, 58(1): 319-329
  14. 14.
    Li W, Du Q and Zhang B. 2015b. Combined sparse and collaborative representation for hyperspectral target detection. Pattern Recognition, 48(12): 3904-3916
  15. 15.
    Li Y S, Xie W Y and Li H Q. 2017. Hyperspectral image reconstruction by deep convolutional neural network for classification. Pattern Recognition, 63: 371-383
  16. 16.
    Liu Y N. 2021. Development of hyperspectral imaging remote sensing technology. Journal of Remote Sensing, 25(1): 440-459
  17. 17.
    Makhzani A, Shlens J, Jaitly N, Goodfellow I and Frey B. 2015. Adversarial autoencoders. arXiv: 1511.05644
  18. 18.
    Molero J M, Garzón E M, García 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
  19. 19.
    Perera P, Nallapati R and Xiang B. 2019. OCGAN: one-class novelty detection using GANs with constrained latent representations//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE: 2893-2901
  20. 20.
    Reed I S and Yu X. 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
  21. 21.
    Song S Z, Zhou H X, Yang Y X and Song J L Q. 2019. Hyperspectral anomaly detection via convolutional neural network and low rank with density-based clustering. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(9): 3637-3649
  22. 22.
    Tong Q X, Zhang B and Zheng L F. 2006. Hyperspectral Remote Sensing. Beijing: Higher Education Press: 1-3
  23. 23.
    Tao R, Zhao X, Li W, Li H-C, and Du Q. 2019. Hyperspectral anomaly detection by fractional Fourier entropy.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(12): 4920-4929
  24. 24.
    Tu B, Zhou C L, Kuang W L, Guo L Y and Ou X F. 2018. Hyperspectral imagery noisy label detection by spectral angle local outlier factor. IEEE Geoscience and Remote Sensing Letters, 15(9): 1417-1421
  25. 25.
    Xie W Y, Lei J, Liu B Z, Li Y S and Jia X P. 2019. Spectral constraint adversarial autoencoders approach to feature representation in hyperspectral anomaly detection. Neural Networks, 119: 222-234
  26. 26.
    Yuan J W, Wu C, Du B, Zhang L P and Wang S G. 2020. Analysis of landscape pattern on urban land use based on GF-5 hyperspectral data. Journal of Remote Sensing, 24(4): 465-478
  27. 27.
    Zhang L L and Cheng B Z. 2019. A stacked autoencoders-based adaptive subspace model for hyperspectral anomaly detection. Infrared Physics & Technology, 96: 52-60
  28. 28.
    Zhang Y X, Du B, Zhang L P and Wang S G. 2016. A low-rank and sparse matrix decomposition-based Mahalanobis distance method for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing, 54(3): 1376-1389
  29. 29.
    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

Leer el texto completo

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