Anterior|Próximo

Rede de detecção de mudanças siamês Nested-UNet (SNU-PS) baseada no espaço de probabilidade posterior de classificação

  • role： First author第一作者
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

    Beijing Municipal Engineering and Technology Center for Land Surface Remote Sensing Data Products, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

  • Email：zhuchuanhai@mail.bnu.edu.cn
  • Introduction：朱传海，研究方向为遥感变化检测与灾情监测。E-mail： zhuchuanhai@mail.bnu.edu.cn
ZHU Chuanhai,  
  • role： Corresponding author通信作者
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

    Beijing Municipal Engineering and Technology Center for Land Surface Remote Sensing Data Products, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

  • Email：chenxuehong@bnu.edu.cn
  • Introduction：陈学泓，研究方向为遥感数据融合、变化检测。E-mail： chenxuehong@bnu.edu.cn
CHEN Xuehong*,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

    Beijing Municipal Engineering and Technology Center for Land Surface Remote Sensing Data Products, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

CHEN Jin,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

    Beijing Municipal Engineering and Technology Center for Land Surface Remote Sensing Data Products, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

YUAN Yuheng,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

    Beijing Municipal Engineering and Technology Center for Land Surface Remote Sensing Data Products, Faculty of Geography Science, Beijing Normal University, Beijing 100875, China

TANG Kai

Resumo

Nos últimos anos, o aprendizado profundo demonstrou grande potencial em tarefas de detecção de mudanças em imagens multitemporais de sensoriamento remoto. Amostras de treinamento suficientes são uma condição importante para que as técnicas de aprendizado profundo possam extrair eficazmente as características das mudanças nas imagens de sensoriamento remoto. No entanto, os conjuntos de dados anotados públicos limitados atualmente não atendem às necessidades de detecção de vários tipos de mudanças em aplicações práticas. Como as mudanças na cobertura do solo geralmente ocupam apenas uma pequena parte da área, as amostras disponíveis de mudanças frequentemente são muito poucas, e existe um sério problema de desequilíbrio em comparação com as amostras sem mudanças. Portanto, como treinar efetivamente redes de detecção de mudanças sob condições de poucas amostras e desequilíbrio é um desafio urgente a ser superado. Em comparação com amostras de detecção de mudanças, a obtenção de amostras de classificação de cobertura do solo em um único instante é muito mais fácil; com o suporte das amostras de classificação, uma rede de classificação de cobertura do solo bem treinada pode fornecer características a priori importantes para a detecção de mudanças. Com base nisso, este artigo propõe uma rede de detecção de mudanças siamês Nested-UNet baseada no espaço de probabilidade posterior de classificação SNU-PS (Siamese Nested-UNet for change detection in Posterior Probability Space), que reduz a dependência das amostras de detecção de mudanças combinando as informações da probabilidade posterior da classificação de cobertura do solo em dois períodos temporais. O método primeiro utiliza amostras de classificação de cobertura do solo para treinar a rede de alta resolução HRNet (High-Resolution Network), obtendo probabilidades posteriores de classificação de objetos para imagens multitemporais; em seguida, as imagens de probabilidade posterior são inseridas na rede de detecção de mudanças siamês Nested-UNet SNU (Siamese Nested-UNet for change detection) para obter os resultados da detecção. Os resultados dos testes nos conjuntos de dados SpaceNet7 e HRSCD demonstram que o SNU-PS pode aproveitar plenamente as informações semânticas da cobertura do solo, mantendo uma precisão estável na detecção de mudanças em diferentes níveis de quantidade de amostras de treinamento; comparado à comparação pós-classificação PCC (Post Classification Comparison), à análise do vetor de mudança no espaço de probabilidade posterior CVAPS (Change-vector analysis in posterior probability space) e a várias redes de detecção de mudanças (SNU, FC-EF, BIT, PCFN), oferece maior e mais estável precisão de detecção de mudanças, especialmente quando há poucas amostras, onde a vantagem é mais evidente. Portanto, o SNU-PS proposto tem melhores perspectivas de aplicação em tarefas de detecção de mudanças em cenários de poucas amostras.

Palavras-chave

cobertura do solo; detecção de mudanças; aprendizado profundo; poucas amostras; desequilíbrio de amostras; rede de segmentação semântica; rede siamês; probabilidade posterior

References

  1. 1.
    Amankwah S O Y, Wang G J, Gnyawali K, Hagan D F T, Sarfo I, Zhen D, Nooni I K, Ullah W and Duan Z. 2022. Landslide detection from bitemporal satellite imagery using attention-based deep neural networks. Landslides, 19(10): 2459-2471
  2. 2.
    Asokan A and Anitha J. 2019. Change detection techniques for remote sensing applications: a survey. Earth Science Informatics, 12(2): 143-160
  3. 3.
    Baker C, Lawrence R L, Montagne C and Patten D. 2007. Change detection of wetland ecosystems using Landsat imagery and change vector analysis. Wetlands, 27(3): 610-619 [DOI: [610:CDOWEU]2.0.CO;2]
  4. 4.
    Bandara W G C and Patel V M. 2022. A transformer-based Siamese network for change detection//IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. Kuala Lumpur: IEEE: 207-210
  5. 5.
    Bouziani M, Goïta K and He D C. 2010. Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge. ISPRS Journal of Photogrammetry and Remote Sensing, 65(1): 143-153
  6. 6.
    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
  7. 7.
    Chan T H, Jia K, Gao S H, Lu J W, Zeng Z N and Ma Y. 2015. PCANet: a simple deep learning baseline for image classification?. IEEE Transactions on Image Processing, 24(12): 5017-5032
  8. 8.
    Chen H, Qi Z P and Shi Z W. 2022a. Remote sensing image change detection with transformers. IEEE Transactions on Geoscience and Remote Sensing, 60: 5607514
  9. 9.
    Chen H and Shi Z W. 2020. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sensing, 12(10): 1662
  10. 10.
    Chen J, Chen X H, Cui X H and Chen J. 2011. Change vector analysis in posterior probability space: a new method for land cover change detection. IEEE Geoscience and Remote Sensing Letters, 8(2): 317-321
  11. 11.
    Chen J, He C Y, Shi P J, Chen Y H and Ma N. 2001. Land use/cover change detection with change vector analysis (CVA): Change magnitude threshold determination. Journal of Remote Sensing, 5(4): 259-266
  12. 12.
    Chen J, Yuan Z Y, Peng J, Chen L, Huang H Z, Zhu J W, Liu Y and Li H F. 2021a. DASNet: dual attentive fully convolutional Siamese networks for change detection in high-resolution satellite images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 1194-1206
  13. 13.
    Chen J N, Lu Y Y, Yu Q H, Luo X D, Adeli E, Wang Y, Lu L, Yuille A L and Zhou Y Y. 2021b. TransuNET: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv: 2102.04306
  14. 14.
    Chen L C, Zhu Y K, Papandreou G, Schroff F and Adam H. 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation//Proceedings of the 15th European Conference on Computer Vision. Munich: Springer: 833-851
  15. 15.
    Chen Y H, Li X B, Chen J and Shi P J. 2002. The change of NDVI time series based on change vector analysis in China, 1983-1992. Journal of Remote Sensing, 6(1): 12-18
  16. 16.
    Chen Z L, Zhou Y, Wang B, Xu X W, He N, Jin S and Jin S R. 2022b. EGDE-Net: a building change detection method for high-resolution remote sensing imagery based on edge guidance and differential enhancement. ISPRS Journal of Photogrammetry and Remote Sensing, 191: 203-222
  17. 17.
    Daudt R C, Le Saux B and Boulch A. 2018. Fully convolutional Siamese networks for change detection//2018 25th IEEE International Conference on Image Processing (ICIP). Athens: IEEE: 4063-4067
  18. 18.
    Daudt R C, Le Saux B, Boulch A and Gousseau Y. 2019. Multitask learning for large-scale semantic change detection. Computer Vision and Image Understanding, 187: 102783
  19. 19.
    Diakogiannis F I, Waldner F, Caccetta P and Wu C. 2020. ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing, 162: 94-114
  20. 20.
    Du P J and Liu S C. 2012. Change detection from multi-temporal remote sensing images by integrating multiple features. Journal of Remote Sensing, 16(4): 663-677
  21. 21.
    El-Hattab M M. 2016. Applying post classification change detection technique to monitor an Egyptian coastal zone (Abu Qir Bay). The Egyptian Journal of Remote Sensing and Space Science, 19(1): 23-36
  22. 22.
    Fang H, Guo S C, Wang X, Liu S C, Lin C and Du P J. 2023. Automatic urban scene-level binary change detection based on a novel sample selection approach and advanced triplet neural network. IEEE Transactions on Geoscience and Remote Sensing, 61: 5601518
  23. 23.
    Fang S, Li K Y, Shao J Y and Li Z. 2022. SNUNet-CD: a densely connected Siamese network for change detection of VHR images. IEEE Geoscience and Remote Sensing Letters, 19: 8007805
  24. 24.
    Foley J A, DeFries R, Asner G P, Barford C, Bonan G, Carpenter S R, Chapin F S, Coe M T, Daily G C, Gibbs H K, Helkowski J H, Holloway T, Howard E A, Kucharik C J, Monfreda C, Patz J A, Prentice I C, Ramankutty N and Snyder P K. 2005. Global consequences of land use. Science, 309(5734): 570-574
  25. 25.
    Gong M G, Niu X D, Zhang P Z and Li Z T. 2017. Generative adversarial networks for change detection in multispectral imagery. IEEE Geoscience and Remote Sensing Letters, 14(12): 2310-2314
  26. 26.
    Hecheltjen A, Thonfeld F and Menz G. 2014. Recent advances in remote sensing change detection-A review//Manakos I and Braun M, eds. Land Use and Land Cover Mapping in Europe. Dordrecht: Springer: 145-178
  27. 27.
    Hermosilla T, Wulder M A, White J C, Coops N C and Hobart G W. 2015. Regional detection, characterization, and attribution of annual forest change from 1984 to 2012 using Landsat-derived time-series metrics. Remote Sensing of Environment, 170: 121-132
  28. 28.
    Jiang J W, Xing Y J, Wei W, Yan E P, Xiang J and Mo D K. 2022. DSNUNet: an improved forest change detection network by combining Sentinel-1 and Sentinel-2 images. Remote Sensing, 14(19): 5046
  29. 29.
    Jin S M, Yang L M, Danielson P, Homer C, Fry J and Xian G. 2013. A comprehensive change detection method for updating the National Land Cover Database to circa 2011. Remote Sensing of Environment, 132: 159-175
  30. 30.
    Kaviani Baghbaderani R, Qu Y, Qi H R and Stutts C. 2020. Representative-discriminative learning for open-set land cover classification of satellite imagery//16th European Conference on Computer Vision-ECCV 2020. Glasgow: Springer: 1-17
  31. 31.
    Ke L, Lin Y K, Zeng Z, Zhang L F and Meng L K. 2018. Adaptive change detection with significance test. IEEE Access, 6: 27442-27450
  32. 32.
    Kussul N, Lavreniuk M, Skakun S and Shelestov A. 2017. Deep learning classification of land cover and crop types using remote sensing data. IEEE Geoscience and Remote Sensing Letters, 14(5): 778-782
  33. 33.
    Li N, Zhu X F, Pan Y Z and Zhan P. 2018. Optimized SVM based on artificial bee colony algorithm for remote sensing image classification. Journal of Remote Sensing, 22(4): 559-569
  34. 34.
    Li Z M, Yan C X, Sun Y and Xin Q C. 2022. A densely attentive refinement network for change detection based on very-high-resolution bitemporal remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 60: 4409818
  35. 35.
    Lin T Y, Goyal P, Girshick R, He K M and Dollár P. 2017. Focal loss for dense object detection//Proceedings of the 2017 IEEE International Conference on Computer Vision. Venice: IEEE: 2999-3007
  36. 36.
    Liu H Y, Wang Z S, Shang F H, Zhang M Y, Gong M G, Ge F H and Jiao L C. 2019. A novel deep framework for change detection of multi-source heterogeneous images//2019 International Conference on Data Mining Workshops (ICDMW). Beijing: IEEE: 165-171
  37. 37.
    Liu J F, Chen K M, Xu G L, Sun X, Yan M L, Diao W H and Han H Z. 2020b. Convolutional neural network-based transfer learning for optical aerial images change detection. IEEE Geoscience and Remote Sensing Letters, 17(1): 127-131
  38. 38.
    Liu R C, Jiang D W, Zhang L L and Zhang Z T. 2020a. Deep depthwise separable convolutional network for change detection in optical aerial images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 1109-1118
  39. 39.
    Liu S C, Bruzzone L, Bovolo F, Zanetti M and Du P J. 2015. Sequential spectral change vector analysis for iteratively discovering and detecting multiple changes in hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 53(8): 4363-4378
  40. 40.
    Lu D S, Li G Y and Moran E. 2014. Current situation and needs of change detection techniques. International Journal of Image and Data Fusion, 5(1): 13-38
  41. 41.
    Lv N, Chen C, Qiu T and Sangaiah A K. 2018. Deep learning and superpixel feature extraction based on contractive autoencoder for change detection in SAR images. IEEE Transactions on Industrial Informatics, 14(12): 5530-5538
  42. 42.
    Milletari F, Navab N and Ahmadi S A. 2016. V-Net: fully convolutional neural networks for volumetric medical image segmentation//2016 Fourth International Conference on 3D Vision (3DV). Stanford: IEEE: 565-571
  43. 43.
    Moustakidis S, Mallinis G, Koutsias N, Theocharis J B and Petridis V. 2012. SVM-based fuzzy decision trees for classification of high spatial resolution remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 50(1): 149-169
  44. 44.
    Peng D F, Zhang Y J and Guan H Y. 2019. End-to-end change detection for high resolution satellite images using improved UNet++. Remote Sensing, 11(11): 1382
  45. 45.
    Peng L K, Chen X H, Chen J, Zhao W Z and Cao X. 2022. Understanding the role of receptive field of convolutional neural network for cloud detection in Landsat 8 OLI imagery. IEEE Transactions on Geoscience and Remote Sensing, 60: 5407317
  46. 46.
    Seong S and Choi J. 2021. Semantic segmentation of urban buildings using a high-resolution network (HRNet) with channel and spatial attention gates. Remote Sensing, 13(16): 3087
  47. 47.
    Shafique A, Cao G, Khan Z, Asad M and Aslam M. 2022. Deep learning-based change detection in remote sensing images: a review. Remote Sensing, 14(4): 871
  48. 48.
    Shi W Z, Zhang M, Zhang R, Chen S X and Zhan Z. 2020. Change detection based on artificial intelligence: state-of-the-art and challenges. Remote Sensing, 12(10): 1688
  49. 49.
    Sui H G, Feng W Q, Li W Z, Sun K M and Xu C. 2018. Review of change detection methods for multi-temporal remote sensing imagery. Geomatics and Information Science of Wuhan University, 43(12): 1885-1898
  50. 50.
    Tan M X and Le Q V. 2019. EfficientNet: rethinking model scaling for convolutional neural networks//Proceedings of the 36th International Conference on Machine Learning. Long Beach: [s.n.]: 6105-6114
  51. 51.
    Tian S Q, Zhong Y F, Zheng Z, Ma A L, Tan X C and Zhang L P. 2022. Large-scale deep learning based binary and semantic change detection in ultra high resolution remote sensing imagery: from benchmark datasets to urban application. ISPRS Journal of Photogrammetry and Remote Sensing, 193: 164-186
  52. 52.
    Van Etten A, Hogan D, Manso J M, Shermeyer J, Weir N and Lewis R. 2021. The multi-temporal urban development spacenet dataset//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE: 6394-6403
  53. 53.
    Varghese A, Gubbi J, Ramaswamy A and Balamuralidhar P. 2019. ChangeNet: a deep learning architecture for visual change detection//European Conference on Computer Vision (ECCV). Munich: Springer: 129-145
  54. 54.
    Wan L, Tian Ye, Kang W C and Ma L. 2022. D-TNet: category-awareness based difference-threshold alternative learning network for remote sensing image change detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5633316
  55. 55.
    Wan L, Xiang Y M and You H J. 2019. A post-classification comparison method for SAR and optical images change detection. IEEE Geoscience and Remote Sensing Letters, 16(7): 1026-1030
  56. 56.
    Wang J D, Sun K, Cheng T H, Jiang B R, Deng C R, Zhao Y, Liu D, Mu Y D, Tan M K and Wang X G. 2021. Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10): 3349-3364
  57. 57.
    Wiratama W, Lee J, Park S E and Sim D. 2018. Dual-dense convolution network for change detection of high-resolution panchromatic imagery. Applied Sciences, 8(10): 1785
  58. 58.
    Wu C, Du B and Zhang L P. 2023. Fully convolutional change detection framework with generative adversarial network for unsupervised, weakly supervised and regional supervised change detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8): 9774-9788
  59. 59.
    Wu C, Zhang L P and Du B. 2017. Kernel slow feature analysis for scene change detection. IEEE Transactions on Geoscience and Remote Sensing, 55(4): 2367-2384
  60. 60.
    Xia H, Tian Y G, Zhang L H and Li S L. 2022. A deep Siamese postclassification fusion network for semantic change detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5622716
  61. 61.
    Xian G, Homer C and Fry J. 2009. Updating the 2001 National Land Cover Database land cover classification to 2006 by using Landsat imagery change detection methods. Remote Sensing of Environment, 113(6): 1133-1147
  62. 62.
    Xie G Y and Niculescu S. 2021. Mapping and monitoring of land cover/land use (LCLU) changes in the crozon peninsula (Brittany, France) from 2007 to 2018 by machine learning algorithms (support vector machine, random forest, and convolutional neural network) and by post-classification comparison (PCC). Remote Sensing, 13(19): 3899
  63. 63.
    Xu Q F, Chen K M, Sun X, Zhang Y, Li H and Xu G L. 2022. Pseudo-Siamese capsule network for aerial remote sensing images change detection. IEEE Geoscience and Remote Sensing Letters, 19: 6000405
  64. 64.
    Xu Q F, Chen K M, Zhou G Y and Sun X. 2021. Change capsule network for optical remote sensing image change detection. Remote Sensing, 13(14): 2646
  65. 65.
    Yang B, Mao Y, Chen J, Liu J Q, Chen J and Yan K. 2022. Review of remote sensing change detection in deep learning: bibliometric and analysis. Journal of Remote Sensing: 1-18
  66. 66.
    Yang K P, Xia G S, Liu Z C, Du B, Yang W, Pelillo M and Zhang L P. 2021. Semantic change detection with asymmetric Siamese networks. arXiv preprint arXiv: 2010.05687
  67. 67.
    Yang M J, Jiao L C, Liu F, Hou B and Yang S Y. 2019. Transferred deep learning-based change detection in remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 57(9): 6960-6973
  68. 68.
    Zhan Y, Fu K, Yan M L, Sun X, Wang H Q and Qiu X S. 2017. Change detection based on deep Siamese convolutional network for optical aerial images. IEEE Geoscience and Remote Sensing Letters, 14(10): 1845-1849
  69. 69.
    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
  70. 70.
    Zhang X Z, Su H, Zhang C, Gu X W, Tan X H and Atkinson P M. 2021. Robust unsupervised small area change detection from SAR imagery using deep learning. ISPRS Journal of Photogrammetry and Remote Sensing, 173: 79-94
  71. 71.
    Zhao J J, Gong M G, Liu J and Jiao L C. 2014. Deep learning to classify difference image for image change detection//2014 International Joint Conference on Neural Networks (IJCNN). Beijing: IEEE: 411-417
  72. 72.
    Zheng Z, Zhong Y F, Tian S Q, Ma A L and Zhang L P. 2022. ChangeMask: deep multi-task encoder-transformer-decoder architecture for semantic change detection. ISPRS Journal of Photogrammetry and Remote Sensing, 183: 228-239
  73. 73.
    Zheng Z, Zhong Y F, Wang J J, Ma A L and Zhang L P. 2021. Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: from natural disasters to man-made disasters. Remote Sensing of Environment, 265: 112636
  74. 74.
    Zhou Z W, Siddiquee M M R, Tajbakhsh N and Liang J M. 2020. Unet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Transactions on Medical Imaging, 39(6): 1856-1867
  75. 75.
    Zhu Q Q, Guo X, Deng W H, Shi S N, Guan Q F, Zhong Y F, Zhang L P and Li D R. 2022. Land-Use/Land-Cover change detection based on a Siamese global learning framework for high spatial resolution remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 184: 63-78
  76. 76.
    Zhu X X, Tuia D, Mou L C, Xia G S, Zhang L P, Xu F and Fraundorfer F. 2017. Deep learning in remote sensing: a comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine, 5(4): 8-36

Leia o 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