Anterior|Siguiente

From optical to SAR： A SAR ship detection algorithm based on multi-level cross-modality alignment

  • role： First author第一作者
  • Affiliation：

    College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China

  • Email：hejiayue@hrbeu.edu.cn
  • Introduction：何佳月， 研究方向为深度学习、SAR图像目标检测。E-mail： hejiayue@hrbeu.edu.cn
HE Jiayue1,  
  • role： Corresponding author通信作者
  • Affiliation：

    College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China

  • Email：sunan08@hrbeu.edu.cn
  • Introduction：宿南， 研究方向为深度学习、多模态遥感图像处理和应用。E-mail： sunan08@hrbeu.edu.cn
SU Nan1*,  
  • Affiliation：

    Research Institute of Information Fusion, Naval Aviation University, Yantai 264001, China

XU Cong’an2,  
  • Affiliation：

    Beijing Institute of Remote Sensing Information, Beijing 100192, China

YIN Lu3,  
  • Affiliation：

    College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China

LIAO Yanping1,  
  • Affiliation：

    College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China

YAN Yiming1

resumen

In recent years, interest in Synthetic Aperture Radar (SAR) ship detection has considerably grown. Its distinctive strengths position it as a pivotal player in numerous fields of research. However, the inherent characteristics of SAR images have presented a range of challenges. For instance, in contrast to optical images, SAR images have counterintuitive feature representation. Additionally, owing to the constrained number of SAR image data, achieving satisfactory results with existing methods that depend on a substantial number of annotated SAR images might be challenging.How to effectively train a high-performance SAR ship detection network with a limited quantity of SAR images should be investigated. Given that single-modality SAR detection algorithms have inherent limitations, other effective modalities that can assist the SAR modality in completing tasks are needed. For instance, in SAR image target detection, optical images can serve as supplementary data sources. A knowledge-rich model can be developed by utilizing a large volume of optical data in training with SAR data. Hence, reasonable training approaches for effectively utilizing images from SAR and optical modalities should be explored.To address these challenges, a SAR ship detection algorithm called MCMA-Net, which is based on multilevel cross-modality alignment, is proposed in this paper. The MCMA-Net enriches SAR feature representation by incorporating valuable knowledge from optical modality. First, we propose a neighborhood–global attention-based feature interaction network (NGAN), which employs a neighborhood attention mechanism that enables the local interaction of low-level features and a global self-attention mechanism that captures global context from high-level features. When the ability of global context modeling is considered, the encoding ability of local features improves, NGAN enables the network to focus on corresponding information at different levels and can promote the subsequent multilevel modality alignment. Second, we propose a multilevel modality alignment module (MLMA), which aligns features in the different hidden spaces of the two modalities from three levels. MLMA facilitates the model to acquire modality-invariant features, bridging the modality gap and realizing optical knowledge transmission. Valuable information from the optical modality can compensate for certain deficiencies in SAR images. With the aid of these two modules, we have incorporated optical superiority information by leveraging SAR’s inherent advantages, achieving an enhancement in the performance of SAR detection tasks.Our algorithm is superior to current detection algorithms. Notably, whether on public SAR image datasets or our own SAR image dataset, the MCMA-Net consistently achieves optimal detection results, which indicates the model’s stable performance and robustness. The visualization results indicate that the MCMA-Net achieves excellent detection capabilities in complex scenarios. The ablation experiments demonstrate that compared with the baseline model, our algorithm achieved a 2.7% increase in mAP on the SSDD dataset. Various experimental results have consistently validated the rationality of the MCMA-Net.

palabra clave

remote sensing;SAR;target detection;cross-modality;feature alignment;attention mechanism

References

  1. 1.
    Bao W, Huang M Y, Zhang Y Q, Xu Y, Liu X J and Xiang X S. 2021. Boosting ship detection in SAR images with complementary pretraining techniques. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 8941-8954
  2. 2.
    Cai Z W and Vasconcelos N. 2018. Cascade R-CNN: delving into high quality object detection//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 6154-6162
  3. 3.
    Cao Q, Ma A L, Zhong Y F, Zhao J, Zhao B and Zhang L P. 2019. Urban classification by multi-feature fusion of hyperspectral image and LiDAR data. Journal of Remote Sensing, 23(5): 892-903
  4. 4.
    Dai J F, Qi H Z, Xiong Y W, Li Y, Zhang G D, Hu H and Wei Y C. 2017. Deformable convolutional networks//2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE: 764-773
  5. 5.
    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//9th International Conference on Learning Representations. Vienna, Austria: OpenReview.net
  6. 6.
    Girshick R. 2015. Fast R-CNN//2015 IEEE International Conference on Computer Vision (ICCV). Santiago, Chile: IEEE: 1440-1448
  7. 7.
    Guo Y C, Du L and Lyu G X. 2021. SAR target detection based on domain adaptive faster R-CNN with small training data size. Remote Sensing, 13(21): 4202
  8. 8.
    Hassani A, Walton S, Li J C, Li S and Shi H. 2023. Neighborhood attention transformer//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, Canada: IEEE: 6185-6194
  9. 9.
    Hou W and Li Y. 2023. Multi-resolution CFAR target detection algorithm and accuracy analysis based on SAR image data. Beijing Survey and Mapping, 37(1): 104-109
  10. 10.
    Karras T, Laine S and Aila T. 2019. A style-based generator architecture for generative adversarial networks//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 4396-4405
  11. 11.
    Li J W, Qu C W and Shao J Q. 2017. Ship detection in SAR images based on an improved faster R-CNN//2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA). Beijing, China: IEEE: 1-6
  12. 12.
    Li W, Wang J J, Gao Y H, Zhang M M, Tao R and Zhang B. 2022. Graph-feature-enhanced selective assignment network for hyperspectral and multispectral data classification. IEEE Transactions on Geoscience and Remote Sensing, 60: 5526914
  13. 13.
    Li Y, Ding Z G, Zhang C, Wang Y and Chen J. 2019. SAR ship detection based on resnet and transfer learning//IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. Yokohama, Japan: IEEE: 1188-1191
  14. 14.
    Lin T Y, Goyal P, Girshick R, He K M and Dollar P. 2017. Focal loss for dense object detection//2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE: 2999-3007
  15. 15.
    Lin Z, Ji K F, Leng X G and Kuang G Y. 2019. Squeeze and excitation rank faster R-CNN for ship detection in SAR images. IEEE Geoscience and Remote Sensing Letters, 16(5): 751-755
  16. 16.
    Liu S, Qi L, Qin H F, Shi J P and Jia J Y. 2018. Path aggregation network for instance segmentation//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 8759-8768
  17. 17.
    Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C Y and Berg A C. 2016. SSD: single shot MultiBox detector//14th European Conference on Computer Vision. Amsterdam, The Netherlands: Springer: 21-37
  18. 18.
    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, ICPRAM 2017. Porto, Portugal: SciTePress: 324-331
  19. 19.
    Lu X, Li B Y, Yue Y X, Li Q Q and Yan J J. 2019. Grid R-CNN//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 7355-7364
  20. 20.
    Miao T, Zeng H C, Yang W, Chu B C, Zou F, Ren W J and Chen J. 2022. An improved lightweight retinaNet for ship detection in SAR images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15: 4667-4679
  21. 21.
    Pappas O, Achim A and Bull D. 2018. Superpixel-level CFAR detectors for ship detection in SAR imagery. IEEE Geoscience and Remote Sensing Letters, 15(9): 1397-1401
  22. 22.
    Redmon J, Divvala S, Girshick R and Farhadi A. 2016. You only look once: unified, real-time object detection//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 779-788
  23. 23.
    Redmon J and Farhadi A. 2017. YOLO9000: better, faster, stronger//2017 IEEE Conference on Computer Vision and Pattern Recognition. Hawaii, USA: IEEE: 6517-6525
  24. 24.
    Redmon J and Farhadi A. 2018. YOLOv3: an incremental improvement. arXiv: 1804.02767
  25. 25.
    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, Canada: MIT Press: 91-99
  26. 26.
    Saito K, Ushiku Y, Harada T and Saenko K. 2019. Strong-weak distribution alignment for adaptive object detection//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 6949-6958
  27. 27.
    Shi Y, Du L, Guo Y C and Du Y. 2022. Unsupervised domain adaptation based on progressive transfer for ship detection: from optical to SAR images. IEEE Transactions on Geoscience and Remote Sensing, 60: 5230317
  28. 28.
    Wang J J, Li W, Gao Y H, Zhang M M, Tao R and Du Q. 2023b. Hyperspectral and SAR Image Classification via Multiscale Interactive Fusion Network. IEEE Transactions on Neural Networks and Learning Systems, 34(12): 10823-10837
  29. 29.
    Wang J J, Li W, Wang Y J, Tao R and Du Q. 2023c. Representation-enhanced status replay network for multisource remote-sensing image classification. IEEE Transactions on Neural Networks and Learning Systems, 1-13
  30. 30.
    Wang S Y, Cai Z C and Yuan J Y. 2023a. Automatic SAR ship detection based on multifeature fusion network in spatial and frequency domain. IEEE Transactions on Geoscience and Remote Sensing, 61: 4102111
  31. 31.
    Wei S J, Zeng X F, Qu Q Z, Wang M, Su H and Shi J. 2020. HRSID: a high-resolution SAR images dataset for ship detection and instance segmentation. IEEE Access, 8: 120234-120254
  32. 32.
    Wu Y, Chen Y P, Yuan L, Liu Z C, Wang L J, Li H Z and Fu Y. 2020. Rethinking classification and localization for object detection//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 10183-10192
  33. 33.
    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. Journal of Remote Sensing, 25(5): 1124-1137
  34. 34.
    Yu Y, Ai H, He X J, Yu S H, Zhong X and Zhu R F. 2020. Attention based feature pyramid networks for ship detection of optical remote sensing image. Journal of Remote Sensing, 24(2): 107-115
  35. 35.
    Zhang F, Lu S T, Xiang D L and Yuan X Z. 2023. An improved superpixel-based CFAR method for high-resolution SAR image ship target detection. Journal of Radars, 12(1): 120-139
  36. 36.
    Zhang M M, Li W, Zhang Y X, Tao R and Du Q. 2023. Hyperspectral and LiDAR data classification based on structural optimization transmission. IEEE Transactions on Cybernetics, 53(5): 3153-3164
  37. 37.
    Zhang Y, Wang X Q, Jiang Z Z, Li G and He Y. 2022. An efficient center-based method with multilevel auxiliary supervision for multiscale SAR ship detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15: 7065-7075
  38. 38.
    Zhao Y, Zhao L J, Xiong B L and Kuang G Y. 2020. Attention receptive pyramid network for ship detection in SAR images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 2738-2756
  39. 39.
    Zhu J Y, Park T, Isola P and Efros A A. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks//2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE: 2242-2251
  40. 40.
    Zhou P C, Cheng G, Yao X W and Han J W. 2021. Machine learning paradigms in high-resolution remote sensing image interpretation. Journal of Remote Sensing, 25(1): 182-197

Leer el 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