سابِق|تال

View-consistency network for weakly supervised oriented object detection in remote sensing images

  • role： First author第一作者
  • Affiliation：

    School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, China

    Key Laboratory of Electromagnetic Space Information, Chinese Academy of Science, Hefei 230026, China

  • Email：fountain@mail.ustc.edu.cn
  • Introduction：方婷婷，研究方向为遥感目标检测。E-mail：fountain@mail.ustc.edu.cn
FANG Tingting12,  
  • role： Corresponding author通信作者
  • Affiliation：

    School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, China

    Key Laboratory of Electromagnetic Space Information, Chinese Academy of Science, Hefei 230026, China

  • Email：flowice@ustc.edu.cn
  • Introduction：刘斌，研究方向为多媒体信息处理和人工智能安全。E-mail：flowice@ustc.edu.cn
LIU Bin12*,  
  • Affiliation：

    Anhui Provincial Geomatic Center, Hefei 230031, China

    Key Laboratory of JiangHuai Arable Land Resources Protection and Eco-restoration, Hefei 230031, China

CHEN Chunhui34,  
  • Affiliation：

    Anhui Provincial Geomatic Center, Hefei 230031, China

    Key Laboratory of JiangHuai Arable Land Resources Protection and Eco-restoration, Hefei 230031, China

LI Xiangyun34

ملخص

The objective of this study is to propose a novel oriented object detection model that can effectively detect objects in remote sensing images, while alleviating the challenges of labor-intensive and time-consuming annotation processes. Specifically, the aim is to develop an efficient and effective approach that only requires image-level annotations, which can improve the availability and diversity of remote sensing rotation object detection datasets. The proposed model is designed to overcome the limitations of traditional annotation methods that rely on bounding box annotations, which can be subjective, inconsistent, and time-consuming to create. By leveraging image-level annotations, the proposed model can greatly reduce the annotation effort, accelerate the annotation process, and enhance the scalability and applicability of remote sensing object detection in various scenarios and domains.The proposed method introduces a novel weakly supervised oriented object detection paradigm for remote sensing scenes. The model is trained in a progressive manner, starting with coarse image-level annotations and gradually refining the detection results. This approach allows the model to learn from limited annotations and adapt to the complexities of remote sensing data, which often exhibit large scale, diverse appearance, and significant rotation variations. The model incorporates consistency constraints of image-level annotation, the oriented bounding box position and the cluster center distribution in different rotation views, to enhance the accuracy and robustness of the detection performance. The oriented bounding box position consistency ensures that the predicted rotation angles of the bounding boxes are consistent across different views of the same object, while the distribution consistency of clustering centers is measured using the Hungarian loss, which ensures that the predicted object centroids are consistent across different views. These consistency constraints are designed to improve the accuracy of the model in handling rotation variations, which is a common challenge in remote sensing object detection.The proposed model is evaluated on two mainstream remote sensing object detection datasets, DIOR and DOTA-v1.0. The experimental results demonstrate that the performance of the proposed model is significantly improved compared to state-of-the-art weakly supervised remote sensing object detection models. Results show that our performance is significantly improved compared to the state-of-the-art object detectors with less strict weakly-supervised settings in remote sensing images, which also highlight the effectiveness and potential of the proposed image-level annotation-based oriented object detection model in addressing the challenges of remote sensing object detection. Furthermore, the model’s ability to generalize well to different datasets showcases its robustness and versatility.In conclusion, the proposed image-level annotation-based oriented object detection model is an innovative approach that addresses the challenges of labor-intensive and time-consuming annotation processes in remote sensing object detection. By leveraging image-level annotations and incorporating consistency constraints, the proposed model achieves improved detection performance while reducing the annotation effort and improving annotation efficiency. The experimental results on DIOR and DOTA-v1.0 datasets demonstrate the superior performance of the proposed model compared to state-of-the-art models, highlighting its potential for practical applications in remote sensing object detection and related fields. Future research can further explore the potential of image-level annotation-based oriented object detection models by incorporating more advanced techniques, exploring different data sources, and investigating real-world applications in remote sensing, geospatial analysis, and other related fields.

مفهوم

remote sensing;Oriented Object Detection;object detection;Weakly Supervised;deep learning;Rotation Consistency;Image-level Label;Hungarian Loss;DOTA Dataset

References

  1. 1.
    Bilen H and Vedaldi A. 2016. Weakly supervised deep detection networks//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE: 2846-2854
  2. 2.
    Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A and Zagoruyko S. 2020. End-to-end object detection with transformers//16th European Conference on Computer Vision. Glasgow: Springer: 213-229
  3. 3.
    Cheng G, Wang J B, Li K, Xie X X, Lang C B, Yao Y Q and Han J W. 2022. Anchor-free oriented proposal generator for object detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5625411
  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 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE: 2844-2853
  5. 5.
    Feng X X, Han J W, Yao X W and Cheng G. 2020a. Progressive contextual instance refinement for weakly supervised object detection in remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 58(11): 8002-8012
  6. 6.
    Feng X X, Han J W, Yao X W and Cheng G. 2020b. TCANet: triple context-aware network for weakly supervised object detection in remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 59(8): 6946-6955
  7. 7.
    Feng X X, Yao X W, Cheng G and Han J W. 2022. Weakly supervised rotation-invariant aerial object detection network//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE: 14126-14135
  8. 8.
    Girshick R. 2015. Fast R-CNN//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago: IEEE: 1440-1448
  9. 9.
    Han J M, Ding J, Xue N and Xia G S. 2021. ReDet: a rotation-equivariant detector for aerial object detection//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE: 2785-2794
  10. 10.
    He K M, Gkioxari G, Dollár P and Girshick R. 2017. Mask R-CNN//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice: IEEE: 2980-2988
  11. 11.
    Huang Z Y, Zou Y, Bhagavatula V and Huang D. 2020. Comprehensive attention self-distillation for weakly-supervised object detection//Proceedings of the 34th International Conference on Neural Information Processing Systems. Vancouver: Curran Associates Inc.: 1409
  12. 12.
    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
  13. 13.
    Li W T, Chen Y J, Hu K X and Zhu J K. 2022a. Oriented RepPoints for aerial object detection//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE: 1819-1828
  14. 14.
    Li W T, Liu W Y, Zhu J K, Cui M M, Hua X S and Zhang L. 2022b. Box-supervised instance segmentation with level set evolution//17th European Conference on Computer Vision. Tel Aviv: Springer: 1-18
  15. 15.
    Li X Y, Kan M N, Shan S G and Chen X L. 2019. Weakly supervised object detection with segmentation collaboration//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE: 9734-9743
  16. 16.
    Ren S Q, He K M, Girshick R and Sun J. 2015. Faster R-CNN: towards real-time object detection with region proposal networks//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal: MIT Press: 91-99
  17. 17.
    Tang P, Wang X G, Bai S, Shen W, Bai X, Liu W Y and Yuille A. 2020. PCL: proposal cluster learning for weakly supervised object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(1): 176-191
  18. 18.
    Tang P, Wang X G, Bai X and Liu W Y. 2017. Multiple instance detection network with online instance classifier refinement//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE: 3059-3067
  19. 19.
    Tian Z, Shen C H, Wang X L and Chen H. 2021. BoxInst: high-performance instance segmentation with box annotations//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE: 5439-5448
  20. 20.
    Uijlings J R R, van de Sande K E A, Gevers T and Smeulders A W M. 2013. Selective search for object recognition. International Journal of Computer Vision, 104(2): 154-171
  21. 21.
    Wang B L, Zhao Y Q and Li X L. 2022. Multiple instance graph learning for weakly supervised remote sensing object detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 5613112
  22. 22.
    Wei Y C, Shen Z Q, Cheng B W, Shi H H, Xiong J J, Feng J S and Huang T. 2018. TS2C: tight box mining with surrounding segmentation context for weakly supervised object detection//Proceedings of the 15th European Conference on Computer Vision. Munich: Springer: 454-470
  23. 23.
    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 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE: 3974-3983
  24. 24.
    Xie X X, Cheng G, Wang J B, Yao X W and Han J W. 2021. Oriented R-CNN for object detection//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE: 3500-3509
  25. 25.
    Yan G, Liu B X, Guo N, Ye X C, Wan F, You H H and Fan D R. 2019. C-MIDN: coupled multiple instance detection network with segmentation guidance for weakly supervised object detection//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE: 9833-9842
  26. 26.
    Yang X, Yan J C, Feng Z M and He T. 2021a. 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
  27. 27.
    Yang X, Hou L P, Zhou Y, Wang W T and Yan J C. 2021b. Dense label encoding for boundary discontinuity free rotation detection//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE: 15814-15824
  28. 28.
    Yang X, Yang X J, Yang J R, Ming Q, Wang W T, Tian Q and Yan J C. 2021c. Learning high-precision bounding box for rotated object detection via Kullback-Leibler divergence//Proceedings of the 35th International Conference on Neural Information Processing Systems. [s.l.]: Curran Associates Inc.: 1405.
  29. 29.
    Yang X, Zhang G F, Li W T, Zhou Y, Wang X H and Yan J C. 2022. H2RBox: horizontal box annotation is all you need for oriented object detection//The Eleventh International Conference on Learning Representations. Kigali: ICLR
  30. 30.
    Yao X W, Feng X X, Han J W, Cheng G and Guo L. 2021. Automatic weakly supervised object detection from high spatial resolution remote sensing images via dynamic curriculum learning. IEEE Transactions on Geoscience and Remote Sensing, 59(1): 675-685
  31. 31.
    Yuan Y Q，Li L，Yao X W，Li L J，Feng X X，Cheng G and Han J W. 2023. A comprehensive review of optical remote-sensing image object detection datasets. National Remote Sensing Bulletin， 27（12）：2671-2687
  32. 32.
    Zhang L，Zhang Y S，Yu Y，Ma Y Z and Jiang H G. 2022. Survey on object detection in tilting box for remote sensing images. National Remote Sensing Bulletin， 26（9）：1723-1743

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