предыдущий|следующий

LAFI-Diffusion: построение и генерация датасета для обнаружения морских судов на спутниковых снимках на основе управляемой диффузионной модели

  • role： First author第一作者
  • Affiliation：

    School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China

  • Email：heda@mail.sysu.edu.cn
  • Introduction：何达，研究方向为遥感大数据智能解译。E-mail： heda@mail.sysu.edu.cn
HE Da1,  
  • Affiliation：

    School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China

LI Zeyu1,  
  • Affiliation：

    School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China

LIU Haoran1,  
  • role： Corresponding author通信作者
  • Affiliation：

    National Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, China

  • Email：xikun@nudt.edu.cn
  • Introduction：胡锡坤，研究方向为智能目标识别、遥感野火监测。E-mail： xikun@nudt.edu.cn
HU Xikun2*,  
  • Affiliation：

    National Key Laboratory of Science and Technology on Automatic Target Recognition, National University of Defense Technology, Changsha 410073, China

ZHONG Ping2,  
  • Affiliation：

    School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China

SHI Qian1

реферат

Обнаружение и распознавание кораблей на спутниковых снимках с дистанционного зондирования имеет важное прикладное значение в таких областях, как морской мониторинг, управление судоходством и военная разведка. Однако недостатки существующих наборов данных по масштабам, разнообразию и тонкости сдерживают развитие этой области. Чтобы преодолеть это узкое место, в статье создан крупномасштабный набор данных точного обнаружения кораблей LAFI (large-scale fine-grained ship instance detection) и на основе модели стабильного диффузионного процесса сформирован миллионный набор данных обнаружения кораблей LAFI-Diffusion. Работа содержит следующие инновационные вклады: (1) LAFI — крупнейший и самый разнообразный публичный набор данных кораблей, включающий 8000 высокоразрешающих спутниковых изображений, 49 типов судов и 48717 точно размеченных экземпляров; (2) с использованием управляемой диффузионной модели, под управлением текстовых подсказок «корабль-море» можно генерировать миллионы синтетических изображений в различных морских условиях, погодных условиях и изменениях времени, поддерживая предобучение моделей обнаружения и значительно улучшая их обобщающую способность в сложных морских сценах, одновременно уменьшая помехи окружающей среды; (3) На основе набора данных LAFI в статье проведена систематическая оценка 7 популярных алгоритмов обнаружения ориентированных рамок, что обеспечивает важный эталон для последующих исследований.

ключеви́че слова́

изображения дистанционного зондирования; обнаружение кораблей; набор данных; диффузионная модель; генерация синтетических данных; тонкое распознавание; ориентированные рамки; увеличение данных

References

  1. 1.
    Biswas S S. 2023. Potential use of chat GPT in global warming. Annals of Biomedical Engineering, 51(6): 1126-1127
  2. 2.
    Chen K Y, Wu M, Liu J M and Zhang C. 2020. FGSD: a dataset for fine-grained ship detection in high resolution satellite images. arXiv preprint arXiv: 2003.06832
  3. 3.
    Deng J, Dong W, Socher R, Li L J, Li K and Fei-Fei L. 2009. ImageNet: a large-scale hierarchical image database//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE: 248-255
  4. 4.
    Ding J, Xue N, Long Y, Xia G S and Lu Q K. 2019. Learning RoI transformer for oriented object detection in aerial images//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE: 2844-2853
  5. 5.
    Everingham M, Van Gool L, Williams C K I, Winn J and Zisserman A. 2010. The PASCAL visual object classes (VOC) challenge. International Journal of Computer Vision, 88(2): 303-338
  6. 6.
    Guo B, Zhang R X, Guo H W, Yang W, Yu H, Zhang P and Zou T Y. 2023. Fine-grained ship detection in high-resolution satellite images with shape-aware feature learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16: 1914-1926
  7. 7.
    Han J M, Ding J, Li J and Xia G S. 2022. Align deep features for oriented object detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5602511
  8. 8.
    Heusel M, Ramsauer H, Unterthiner T, Nessler B and Hochreiter S. 2018. GANs trained by a two time-scale update rule converge to a local nash equilibrium//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc.: 6629-6640
  9. 9.
    Huang J, Jiang Z G, Zhang H P and Yao Y. 2017. Ship object detection in remote sensing images using convolutional neural networks. Journal of Beijing University of Aeronautics and Astronsutics, 43(9): 1841-1848
  10. 10.
    Li K, Wan G, Cheng G, Meng L Q and Han J W. 2020. Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS Journal of Photogrammetry and Remote Sensing, 159: 296-307
  11. 11.
    Li Z H, Hou B, Wu Z T, Ren B and Yang C. 2023. FCOSR: a simple anchor-free rotated detector for aerial object detection. Remote Sensing, 15(23): 5499
  12. 12.
    Liang J, Cao J, Sun G, Zhang K, Van Gool L, Timofte R. 2021. SwinIR: Image Restoration Using Swin Transformer. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Montreal, BC, Canada: IEEE: 1833-1844
  13. 13.
    Liu L Y, Bai Y P and Li Y. 2022. Locality-aware rotated ship detection in high-resolution remote sensing imagery based on multiscale convolutional network. IEEE Geoscience and Remote Sensing Letters, 19: 3502805
  14. 14.
    Liu Z K, Yuan L, Weng L B and Yang Y P. 2017. A high resolution optical satellite image dataset for ship recognition and some new baselines//Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. Porto: ICPRAM: 324-331
  15. 15.
    Nie G T and Huang H. 2023. Multi-oriented object detection in aerial images with double horizontal rectangles. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4): 4932-4944
  16. 16.
    Ouyang L H, Fang L Y and Ji X Y. 2022. Multigranularity self-attention network for fine-grained ship detection in remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15: 9722-9732
  17. 17.
    Rombach R, Blattmann A, Lorenz D, Esser P and Ommer B. 2022. High-resolution image synthesis with latent diffusion models//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE: 10674-10685
  18. 18.
    Russell B C, Torralba A, Murphy K P and Freeman W T. 2008. LabelMe: a database and web-based tool for image annotation. International Journal of Computer Vision, 77(1/3): 157-173
  19. 19.
    Tupper E C. 2013. Introduction to Naval Architecture. Kidlington: Butterworth-Heinemann
  20. 20.
    Wang Y Q, Ma L and Tian Y. 2011. State-of-the-art of ship detection and recognition in optical remotely sensed imagery. Acta Automatica Sinica, 37(9): 1029-1039
  21. 21.
    Xia G S, Bai X, Ding J, Zhu Z, Belongie S, Luo J B, Datcu M, Pelillo M and Zhang L P. 2018. DOTA: a large-scale dataset for object detection in aerial images//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE: 3974-3983
  22. 22.
    Xiao Y, Yuan Q, Jiang K, He J, Lin C W, Zhang L. 2024. TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-Resolution. IEEE Transactions on Image Processing, 33: 738-752
  23. 23.
    Xie X X, Cheng G, Wang J B, Yao X W and Han J W. 2021. Oriented R-CNN for object detection//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE: 3500-3509
  24. 24.
    Xie X X, Cheng G, Yao Y Q, Yao X W and Han J W. 2022. Dynamic feature fusion for object detection in remote sensing images. Chinese Journal of Computers, 45(4): 735-747
  25. 25.
    Xu X W, Zhang X L, Wei S J, Shi J, Zhang W S, Zhang T W, Zhan X, Xu Y Q and Zeng T J. 2025. DiffSARShipInst: diffusion model for ship instance segmentation from synthetic aperture radar imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 223: 440-455
  26. 26.
    Xu Y C, Fu M T, Wang Q M, Wang Y K, Chen K, Xia G S and Bai X. 2021. Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(4): 1452-1459
  27. 27.
    Xu Z J and Bai X. 2022. Small ship target detection method for remote sensing images based on dual feature enhancement. Acta Optica Sinica, 42(18): 1828002
  28. 28.
    Yang S, Pei Z Q, Zhou F and Wang G Y. 2020. Rotated faster R-CNN for oriented object detection in aerial images//Proceedings of the 2020 3rd International Conference on Robot Systems and Applications. New York: ACM: 35-39
  29. 29.
    Yang X, Yan J C, Feng Z M and He T. 2021. R3Det: refined single-stage detector with feature refinement for rotating object//Proceedings of the 35th AAAI Conference on Artificial Intelligence. [s.l.]: AAAI: 3163-3171
  30. 30.
    Yang X, Yan J C, Liao W L, Yang X K, Tang J and He T. 2023. SCRDet++: detecting small, cluttered and rotated objects via instance-level feature denoising and rotation loss smoothing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2): 2384-2399
  31. 31.
    Yao Y Q, Cheng G, Xie X X and Han J W. 2021. Optical remote sensing image object detection based on multi-resolution feature fusion. National Remote Sensing Bulletin, 25(5): 1124-1137
  32. 32.
    Ye J Y, He J, Zhang X, Lin Y, Lin H L, He C H and Li W J. 2025. Satellite image synthesis from street view with fine-grained spatial textual guidance: a novel framework. IEEE Geoscience and Remote Sensing Magazine, 13(3): 395-414
  33. 33.
    Yu W Q, Cheng G, Wang M J, Yao Y Q, Xie X X, Yao X W and Han J W. 2023. MAR20: a benchmark for military aircraft recognition in remote sensing images. National Remote Sensing Bulletin, 27(12): 2688-2696
  34. 34.
    Yu Y, Yang X, Li Y S, Han Z J, Da F P and Yan J C. 2025. Wholly-WOOD: wholly leveraging diversified-quality labels for weakly-supervised oriented object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(6): 4438-4454
  35. 35.
    Zhang R, Isola P, Efros A A, Shechtman E and Wang O. 2018. The unreasonable effectiveness of deep features as a perceptual metric//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE: 586-595
  36. 36.
    Zhang Y, Zhu G Y, Shi T J, Zhang K and Yan J H. 2022. Small object detection in remote sensing images based on feature fusion and attention. Acta Optica Sinica, 42(24): 2415001
  37. 37.
    Zhang Z N, Zhang L, Wang Y, Feng P M and He R. 2021. ShipRSImageNet: a large-scale fine-grained dataset for ship detection in high-resolution optical remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 8458-8472
  38. 38.
    Zheng Z H, Ye R G, Hou Q B, Ren D W, Wang P, Zuo W M and Cheng M M. 2023. Localization distillation for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8): 10070-10083
  39. 39.
    Zhou P C, Cheng G, Yao X W and Han J W. 2021. Machine learning paradigms in high-resolution remote sensing image interpretation. National Remote Sensing Bulletin, 25(1): 182-197
  40. 40.
    Zhou Y, Yang X, Zhang G F, Wang J B, Liu Y Y, Hou L P, Jiang X, Liu X Z, Yan J C, Lyu C Q, Zhang W W and Chen K. 2022. MMRotate: a rotated object detection benchmark using PyTorch//Proceedings of the 30th ACM International Conference on Multimedia. New York: ACM: 7331-7334

Читать полностью

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