Précédent|Prochain

Méthode de détection des changements d’image hyperspectrale basée sur les caractéristiques conjointes des différences centrales et l’attention spectro-spatiale

  • role： First author第一作者
  • Affiliation：

    College of Computer Science, Chongqing University, Chongqing 401331, China

  • Email：zhoutianyuan1016@163.com
  • Introduction：周天媛，研究方向为高光谱变化检测。E-mail： zhoutianyuan1016@163.com
ZHOU Tianyuan1,  
  • Affiliation：

    College of Optoelectronic Engineering, Chongqing University, Chongqing 401331, China

LIU Jiamin2,  
  • Affiliation：

    School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

GUO Tan3,  
  • Affiliation：

    College of Computer Science, Chongqing University, Chongqing 401331, China

FU Chuan1,  
  • role： Corresponding author通信作者
  • Affiliation：

    College of Computer Science, Chongqing University, Chongqing 401331, China

  • Email：luoflyn@163.com
  • Introduction：罗甫林，研究方向为遥感智能解译。E-mail： luoflyn@163.com
LUO Fulin1*

résumé

Les images hyperspectrales multi-temporelles sont largement utilisées dans la détection de changements grâce à leur richesse en bandes spectrales et détails d’image. Les algorithmes de détection de changements hyperspectraux basés sur l’apprentissage supervisé dépendent souvent d’un grand nombre d’échantillons annotés, ce qui entraîne des coûts d’annotation élevés. À cet égard, cet article propose un réseau nommé JCDS²AN (Réseau des caractéristiques de différences centrales conjointes et attention spectro-spatiale) pour la détection de changements dans les images hyperspectrales. Ce réseau peut atténuer les fluctuations des caractéristiques de changement avec un nombre limité d’échantillons et apprendre des caractéristiques de changement représentatives à partir d’un échantillonnage annoté restreint. JCDS²AN intègre des blocs d’attention spectro-spatiale multi-échelle pour capturer des caractéristiques spatiales et spectrales à différentes échelles, ainsi qu’une stratégie d’échange de pixels centraux guidée par les caractéristiques différentielles pour permettre une interaction efficace entre les caractéristiques de changement et les caractéristiques des deux phases temporelles. Une comparaison a été réalisée avec huit autres méthodes de détection de changements hyperspectraux, validée par des expériences visuelles et quantitatives sur trois ensembles de données publics. Les résultats montrent que JCDS²AN proposée surpasse les autres méthodes de détection de changements hyperspectraux.

mots-clés

image hyperspectrale; imagerie de télédétection; détection de changement; caractéristiques multi-échelle; guidage des caractéristiques différentielles; pixel central

References

  1. 1.
    Abeywickrama T, Cheema M A and Taniar D. 2016. k-nearest neighbors on road networks: a journey in experimentation and in-memory implementation. Proceedings of the VLDB Endowment, 9(6): 492-503
  2. 2.
    Bovolo F and Bruzzone L. 2007. A theoretical framework for unsupervised change detection based on change vector analysis in the polar domain. IEEE Transactions on Geoscience and Remote Sensing, 45(1): 218-236
  3. 3.
    Celik T. 2009. Unsupervised change detection in satellite images using principal component analysis and k-means clustering. IEEE Geoscience and Remote Sensing Letters, 6(4): 772-776
  4. 4.
    Chen H R X, Wu C, Du B, Zhang L P and Wang L. 2020. Change detection in multisource VHR images via deep siamese convolutional multiple-layers recurrent neural network. IEEE Transactions on Geoscience and Remote Sensing, 58(4): 2848-2864
  5. 5.
    Chollet F. 2017. Xception: deep learning with depthwise separable convolutions//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE: 1800-1807
  6. 6.
    Cortes C and Vapnik V. 1995. Support-vector networks. Machine Learning, 20(3): 273-297
  7. 7.
    Ding J G, Li X R and Zhao L Y. 2022. CDFormer: a hyperspectral image change detection method based on transformer encoders. IEEE Geoscience and Remote Sensing Letters, 19: 6015405
  8. 8.
    Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X H, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J and Houlsby N. 2021. An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929
  9. 9.
    Gong M G, Jiang F L, Qin A K, Liu T F, Zhan T, Lu D, Zheng H H and Zhang M Y. 2022. A spectral and spatial attention network for change detection in hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 60: 5521614
  10. 10.
    Hasanlou M and Seydi S T. 2018. Hyperspectral change detection: an experimental comparative study. International Journal of Remote Sensing, 39(20): 7029-7083
  11. 11.
    Hu M Q, Wu C and Zhang L P. 2024. GlobalMind: global multi-head interactive self-attention network for hyperspectral change detection. ISPRS Journal of Photogrammetry and Remote Sensing, 211: 465-483
  12. 12.
    Hyvärinen A and Oja E. 2000. Independent component analysis: algorithms and applications. Neural Networks, 13(4/5): 411-430
  13. 13.
    Jaturapitpornchai R, Matsuoka M, Kanemoto N, Kuzuoka S, Ito R and Nakamura R. 2019. Newly built construction detection in SAR images using deep learning. Remote Sensing, 11(12): 1444
  14. 14.
    Ji M, Liu L F, Du R L and Buchroithner M F. 2019. A comparative study of texture and convolutional neural network features for detecting collapsed buildings after earthquakes using pre- and post-event satellite imagery. Remote Sensing, 11(10): 1202
  15. 15.
    Jiang H W, Hu X Y, Li K, Zhang J M, Gong J Q and Zhang M. 2020. PGA-SiamNet: pyramid feature-based attention-guided siamese network for remote sensing orthoimagery building change detection. Remote Sensing, 12(3): 484
  16. 16.
    Khan S H, He X M, Porikli F and Bennamoun M. 2017. Forest change detection in incomplete satellite images with deep neural networks. IEEE Transactions on Geoscience and Remote Sensing, 55(9): 5407-5423
  17. 17.
    Khelifi L and Mignotte M. 2020. Deep learning for change detection in remote sensing images: comprehensive review and meta-analysis. IEEE Access, 8: 126385-126400
  18. 18.
    Li F T, Zhou F D, Zhang G, Xiao J F and Zeng P. 2024. HSAA-CD: a hierarchical semantic aggregation mechanism and attention module for non-agricultural change detection in cultivated land. Remote Sensing, 16(8): 1372
  19. 19.
    Lin Y, Li S T, Fang L Y and Ghamisi P. 2020. Multispectral change detection with bilinear convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 17(10): 1757-1761
  20. 20.
    Liu R, Lehman J, Molino P, Such F P, Frank E, Sergeev A and Yosinski J. 2018. An intriguing failing of convolutional neural networks and the CoordConv solution//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal: Curran Associates Inc.: 9628-9639
  21. 21.
    Qu J H, Hou S X, Dong W Q, Li Y S, Xie W Y. 2022. A Multilevel Encoder-Decoder Attention Network for Change Detection in Hyperspectral Images. IEEE Transactions on Geoscience and Remote Sensing, 60:5518113
  22. 22.
    Luo F L, Zhou T Y, Liu J M, Guo T, Gong X W and Ren J C. 2023. Multiscale diff-changed feature fusion network for hyperspectral image change detection. IEEE Transactions on Geoscience and Remote Sensing, 61: 5502713
  23. 23.
    Mou L C, Bruzzone L and Zhu X X. 2019. Learning spectral-spatial-temporal features via a recurrent convolutional neural network for change detection in multispectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 57(2): 924-935
  24. 24.
    Nielsen A A, Conradsen K and Simpson J J. 1998. Multivariate Alteration Detection (MAD) and MAF postprocessing in multispectral, bitemporal image data: new approaches to change detection studies. Remote Sensing of Environment, 64(1): 1-19
  25. 25.
    Qu J H, Hou S X, Dong W Q, Li Y S and Xie W Y. 2022a. A multilevel encoder-decoder attention network for change detection in hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 60: 5518113
  26. 26.
    Qu J H, Xu Y S, Dong W Q, Li Y S and Du Q. 2022b. Dual-branch difference amplification graph convolutional network for hyperspectral image change detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5519912
  27. 27.
    Shaw P, Uszkoreit J and Vaswani A. 2018. Self-attention with relative position representations//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). New Orleans: Association for Computational Linguistics: 464-468
  28. 28.
    Song R X, Ni W H, Cheng W and Wang X H. 2022. CSANet: cross-temporal interaction symmetric attention network for hyperspectral image change detection. IEEE Geoscience and Remote Sensing Letters, 19: 6010105
  29. 29.
    Wang Q, Yuan Z H, Du Q and Li X L. 2019. GETNET: a general end-to-end 2-D CNN framework for hyperspectral image change detection. IEEE Transactions on Geoscience and Remote Sensing, 57(1): 3-13
  30. 30.
    Wang Y H, Hong D F, Sha J J, Gao L R, Liu L, Zhang Y G and Rong X H. 2022. Spectral-spatial-temporal transformers for hyperspectral image change detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5536814
  31. 31.
    Wu C, Du B and Zhang L P. 2014. Slow feature analysis for change detection in multispectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 52(5): 2858-2874
  32. 32.
    Yang B, Mao Y, Chen J, Liu J Q, Chen J and Yan K. 2023. Review of remote sensing change detection in deep learning: bibliometric and analysis. National Remote Sensing Bulletin, 27(9): 1988-2005
  33. 33.
    Zhang L P and Wu C. 2017. Advance and future development of change detection for multi-temporal remote sensing imagery. Acta Geodaetica et Cartographica Sinica, 46(10): 1447-1459

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