سابِق|تال

خرائط تغطية الأرض واسعة النطاق بناءً على بيانات متعددة النماذج ودمج متعدد النماذج

  • role： First author第一作者
  • Affiliation：

    Hangzhou Institute for Advanced Study, School of Physics and Optoelectronic Engineering, University of Chinese Academy of Sciences, Hangzhou 310024, China

    Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China

  • Email：ruyifan22@mails.ucas.ac.cn
  • Introduction：茹逸凡，研究方向为机器学习与语义分割、遥感土地覆盖制图、图像处理、多光谱与高光谱。E-mail： ruyifan22@mails.ucas.ac.cn
RU Yifan12,  
  • Affiliation：

    Hangzhou Institute for Advanced Study, School of Physics and Optoelectronic Engineering, University of Chinese Academy of Sciences, Hangzhou 310024, China

TANG Guoliang1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China

  • Email：Lichunlai@mail.sitp.ac.cn
  • Introduction：李春来，研究方向为光谱成像技术、数字图形处理、微弱信号处理技术。E-mail：Lichunlai@mail.sitp.ac.cn
LI Chunlai2*

ملخص

تواجه خرائط تغطية الأرض الحالية تحديات مركزية تتمثل في محدودية مصادر البيانات الفردية، وتجانس البيانات الكبير، وضعف قدرة التعميم للنماذج الفردية. لذلك، استندت هذه الدراسة إلى الميزات الطيفية للصور متعددة الأطياف MSI (Multispectral Imagery) وخصائص بيانات الرادار ذو الفتحة التركيبية SAR (Synthetic Aperture Radar) المختلفة، وقد أنشأت مجموعة بيانات متعددة النماذج (MSI+SAR) لتعويض نقص بيانات SAR الأحادية النموذج في السيناريوهات المعقدة. بالإضافة إلى ذلك، وبعد التقييم المنهجي لسبعة نماذج تمثيلية على مستوى النموذج، تم اقتراح طريقة دمج متعددة النماذج تدمج ثلاثة أنواع من البنى: نماذج FCN تمثل الشبكات العصبية التلافيفية (CNN)، ونماذج ConViT تمثل المحولات البصرية (ViT)، ونماذج CoAtNet تمثل البنية المختلطة بين CNN وViT. تظهر نتائج التجارب أن البيانات متعددة النماذج (MSI+SAR) تحقق تحسينًا ملحوظًا مقارنة ببيانات SAR الأحادية النموذج في دقة الشمول OA (Overall Accuracy) ومؤشر التقاطع المرجح بالتردد FWIoU (Frequency-Weighted Intersection over Union)، وهذان هما مؤشرات تقييم التقسيم الدلالي التمثيلية. كما أن إطار الدمج متعدد النماذج المقترح يُحسن الأداء بشكل إضافي في مؤشري OA وFWIoU. تعزز الطريقة المبتكرة المقترحة في هذه الدراسة ليس فقط قدرة النماذج على استخراج الميزات المعقدة للغطاء الأرضي، بل تحسن أيضًا نتائج التصنيف في خرائط تغطية الأرض واسعة النطاق، مما يؤكد القوة الكبيرة للبيانات متعددة النماذج ودمج النماذج في رسم الخرائط عن بعد.

مفهوم

خرائط تغطية الأرض;متعدد الأطياف;الرادار ذو الفتحة التركيبية;متعدد النماذج;دمج متعدد النماذج;الشبكات العصبية التلافيفية;المحول البصري

References

  1. 1.
    Ajibola S and Cabral P. 2024. A systematic literature review and bibliometric analysis of semantic segmentation models in land cover mapping. Remote Sensing, 16(12): 2222
  2. 2.
    Brown W M and Porcello L J. 1969. An introduction to synthetic-aperture radar. IEEE Spectrum, 6(9): 52-62
  3. 3.
    Chaurasia A and Culurciello E. 2017. LinkNet: exploiting encoder representations for efficient semantic segmentation//2017 IEEE Visual Communications and Image Processing (VCIP). St. Petersburg: IEEE: 1-4
  4. 4.
    Chua L O. 1997. CNN: a vision of complexity. International Journal of Bifurcation and Chaos, 7(10): 2219-2425
  5. 5.
    Congalton R G, Gu J Y, Yadav K, Thenkabail P and Ozdogan M. 2014. Global land cover mapping: a review and uncertainty analysis. Remote Sensing, 6(12): 12070-12093
  6. 6.
    Dai Z H, Liu H X, Le Q V and Tan M X. 2021. CoAtNet: marrying convolution and attention for all data sizes//Proceedings of the 35th International Conference on Neural Information Processing Systems. Virtual Event: Curran Associates Inc.: 3965-3977
  7. 7.
    D’Ascoli S, Touvron H, Leavitt M L, Morcos A S, Biroli G and Sagun L. 2022. ConViT: improving vision transformers with soft convolutional inductive biases. Journal of Statistical Mechanics: Theory and Experiment, 2022: 114005
  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 preprint arXiv: 2010.11929
  9. 9.
    Fitzgerald R W and Lees B G. 1994. Assessing the classification accuracy of multisource remote sensing data. Remote sensing of Environment, 47(3): 362-368
  10. 10.
    García-Mora T J, Mas J F and Hinkley E A. 2012. Land cover mapping applications with MODIS: a literature review. International Journal of Digital Earth, 5(1): 63-87
  11. 11.
    Grekousis G, Mountrakis G and Kavouras M. 2015. An overview of 21 global and 43 regional land-cover mapping products. International Journal of Remote Sensing, 36(21): 5309-5335
  12. 12.
    Haque M A, Reza M N, Ali M, Karim M R, Ahmed S, Lee K D, Khang Y H and Chung S O. 2024. Effects of environmental conditions on vegetation indices from multispectral images: a review. Korean Journal of Remote Sensing, 40(4): 319-341
  13. 13.
    Jacqueminet C, Kermadi S, Michel K, Béal D, Gagnage M, Branger F, Jankowfsky S and Braud I. 2013. Land cover mapping using aerial and VHR satellite images for distributed hydrological modelling of periurban catchments: application to the Yzeron catchment (Lyon, France). Journal of Hydrology, 485: 68-83
  14. 14.
    Joshi N, Baumann M, Ehammer A, Fensholt R, Grogan K, Hostert P, Jepsen M R, Kuemmerle T, Meyfroidt P, Mitchard E T A, Reiche J, Ryan C M and Waske B. 2016. A review of the application of optical and radar remote sensing data fusion to land use mapping and monitoring. Remote Sensing, 8(1): 70
  15. 15.
    LeCun Y, Bottou L, Bengio Y and Haffner P. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278-2324
  16. 16.
    Li Z H, He W, Cheng M F, Hu J X, Yang G Y and Zhang H Y. 2023. SinoLC-1: the first 1 m resolution national-scale land-cover map of China created with a deep learning framework and open-access data. Earth System Science Data, 15(11): 4749-4780
  17. 17.
    Li Z H, He W, Li J P, Lu F X and Zhang H Y. 2024. Learning without exact guidance: updating large-scale high-resolution land cover maps from low-resolution historical labels//Proceedings of the 2014 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE: 27717-27727
  18. 18.
    Li Z H, Zhang H Y, Lu F X, Xue R Y, Yang G Y and Zhang L P. 2022. Breaking the resolution barrier: a low-to-high network for large-scale high-resolution land-cover mapping using low-resolution labels. ISPRS Journal of Photogrammetry and Remote Sensing, 192: 244-267
  19. 19.
    Liu Y H, Wang Y, Zhang Y F, Mei S H, Zou J Q, Li Z H, Lu F X, He W, Zhang H Y, Zhao H L, Chen C, Xia C, Li H, Vivone G, Hänsch R, Taskin G, Yao J, Qin A K, Zhang B, Chanussot J and Hong D F. 2024. Cross-City Semantic Segmentation (C2Seg) in multimodal remote sensing: outcome of the 2023 IEEE WHISPERS C2Seg Challenge. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17: 8851-8862
  20. 20.
    Lu D S, Hetrick S and Moran E. 2010. Land cover classification in a complex urban-rural landscape with QuickBird imagery. Photogrammetric Engineering and Remote Sensing, 76(10): 1159-1168
  21. 21.
    Arpitha M, S A Ahmed and Harishnaika N. 2023. Land use and land cover classification using machine learning algorithms in Google earth engine. Earth Science Informatics, 16(4): 3057-3073
  22. 22.
    Mickaelian A M and Sargsyan L A. 2010. Spectral observations of big objects. Astrophysics, 53(4): 483-489
  23. 23.
    Oetter D R, Cohen W B, Berterretche M, Maiersperger T K and Kennedy R E. 2001. Land cover mapping in an agricultural setting using multiseasonal Thematic Mapper data. Remote Sensing of Environment, 76(2): 139-155
  24. 24.
    Paheding S, Saleem A, Siddiqui M F H, Rawashdeh N, Essa A and Reyes A A. 2024. Advancing horizons in remote sensing: a comprehensive survey of deep learning models and applications in image classification and beyond. Neural Computing and Applications, 36(27): 16727-16767
  25. 25.
    Quan Y H, Tong Y P, Feng W, Dauphin G, Huang W J and Xing M D. 2020. A novel image fusion method of multi-spectral and SAR images for land cover classification. Remote Sensing, 12(22): 3801
  26. 26.
    Rehman A U, Ullah S, Shafique M, Khan M S, Badshah M T and Liu Q J. 2021. Combining Landsat-8 spectral bands with ancillary variables for land cover classification in mountainous terrains of northern Pakistan. Journal of Mountain Science, 18(9): 2388-2401
  27. 27.
    Rodriguez-Galiano V F, Ghimire B, Rogan J, Chica-Olmo M and Rigol-Sanchez J P. 2012. An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67: 93-104
  28. 28.
    Ronneberger O, Fischer P and Brox T. 2015. U-net: convolutional networks for biomedical image segmentation//18th International Conference on Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Munich: Springer: 234-241
  29. 29.
    Sharma A, Liu X W and Yang X J. 2018. Land cover classification from multi-temporal, multi-spectral remotely sensed imagery using patch-based recurrent neural networks. Neural Networks, 105: 346-355
  30. 30.
    Shelhamer E, Long J and Darrell T. 2017. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 640-651
  31. 31.
    Thyagharajan K K and Vignesh T. 2019. Soft computing techniques for land use and land cover monitoring with multispectral remote sensing images: a review. Archives of Computational Methods in Engineering, 26(2): 275-301
  32. 32.
    Tong X Y, Dong R M and Zhu X X. 2025. Global high categorical resolution land cover mapping via weak supervision. ISPRS Journal of Photogrammetry and Remote Sensing, 220: 535-549
  33. 33.
    Van Der Werff H M A and Van Der Meer F D. 2008. Shape-based classification of spectrally identical objects. ISPRS Journal of Photogrammetry and Remote Sensing, 63(2): 251-258
  34. 34.
    Wang J D, Sun K, Cheng T H, Jiang B R, Deng C R, Zhao Y, Liu D, Mu Y D, Tan M K, Wang X G, Liu W Y and Xiao B. 2021. Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10): 3349-3364
  35. 35.
    Wickham J, Stehman S V, Sorenson D G, Gass L and Dewitz J A. 2021. Thematic accuracy assessment of the NLCD 2016 land cover for the conterminous United States. Remote Sensing of Environment, 257: 112357
  36. 36.
    Wu H, Li Y, Lin A Q, Fan H C, Fan K X, Xie J Y and Luo W T. 2024. A review of crowdsourced geographic information for land-use and land-cover mapping: current progress and challenges. International Journal of Geographical Information Science, 38(11): 2183-2215
  37. 37.
    Xu P P, Tsendbazar N E, Herold M, De Bruin S, Koopmans M, Birch T, Carter S, Fritz S, Lesiv M, Mazur E, Pickens A, Potapov P, Stolle F, Tyukavina A, Van De Kerchove R and Zanaga D. 2024. Comparative validation of recent 10 m-resolution global land cover maps. Remote Sensing of Environment, 311: 114316
  38. 38.
    Yang J and Huang X. 2021. The 30 m annual land cover dataset and its dynamics in China from 1990 to 2019. Earth System Science Data Discussions, 13(8): 3907-3925
  39. 39.
    Zhang T T, Du Z R, Yang J Y, Yao X C, Ou C, Niu B W and Yan S. 2021. Land cover mapping and ecological risk assessment in the context of recent ecological migration. Remote Sensing, 13(7): 1381
  40. 40.
    Hong D, Zhang B, Li H, Li Y, Yao J, Li C,Werner M, Chanussot J , Zipf A, Zhu X. 2023. 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: 113856.

قراءة النص الكامل

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