Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Multi-scale direction-aware SAR object detection network via global information fusion (2312.16943v5)

Published 28 Dec 2023 in cs.CV

Abstract: Deep learning has driven significant progress in object detection using Synthetic Aperture Radar (SAR) imagery. Existing methods, while achieving promising results, often struggle to effectively integrate local and global information, particularly direction-aware features. This paper proposes SAR-Net, a novel framework specifically designed for global fusion of direction-aware information in SAR object detection. SAR-Net leverages two key innovations: the Unity Compensation Mechanism (UCM) and the Direction-aware Attention Module (DAM). UCM facilitates the establishment of complementary relationships among features across different scales, enabling efficient global information fusion and transmission. Additionally, DAM, through bidirectional attention polymerization, captures direction-aware information, effectively eliminating background interference. Extensive experiments demonstrate the effectiveness of SAR-Net, achieving state-of-the-art results on aircraft (SAR-AIRcraft-1.0) and ship datasets (SSDD, HRSID), confirming its generalization capability and robustness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (63)
  1. T. Liu, J. Zhang, G. Gao, J. Yang, and A. Marino, “Cfar ship detection in polarimetric synthetic aperture radar images based on whitening filter,” IEEE Trans. Geosci. Remote Sens., vol. 58, no. 1, pp. 58–81, 2019.
  2. Y. Fan, F. Wang, and H. Wang, “A transformer-based coarse-to-fine wide-swath sar image registration method under weak texture conditions,” Remote Sens., vol. 14, no. 5, p. 1175, 2022.
  3. M. Kang, K. Ji, X. Leng, and Z. Lin, “Contextual region-based convolutional neural network with multilayer fusion for sar ship detection,” Remote Sens., vol. 9, no. 8, p. 860, 2017.
  4. Z. Lin, K. Ji, X. Leng, and G. Kuang, “Squeeze and excitation rank faster r-cnn for ship detection in sar images,” IEEE Geosci. Remote Sens. Lett., vol. 16, no. 5, pp. 751–755, 2018.
  5. L. Yu, H. Wu, Z. Zhong, L. Zheng, Q. Deng, and H. Hu, “Twc-net: A sar ship detection using two-way convolution and multiscale feature mapping,” Remote Sens., vol. 13, no. 13, p. 2558, 2021.
  6. H. Wan, J. Chen, Z. Huang, R. Xia, B. Wu, L. Sun, B. Yao, X. Liu, and M. Xing, “Afsar: An anchor-free sar target detection algorithm based on multiscale enhancement representation learning,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–14, 2021.
  7. R. Xia, J. Chen, Z. Huang, H. Wan, B. Wu, L. Sun, B. Yao, H. Xiang, and M. Xing, “Crtranssar: A visual transformer based on contextual joint representation learning for sar ship detection,” Remote Sens., vol. 14, no. 6, p. 1488, 2022.
  8. J. Oh, G.-Y. Youm, and M. Kim, “Spam-net: A cnn-based sar target recognition network with pose angle marginalization learning,” IEEE Trans. Circuits Syst. Video Technol., vol. 31, no. 2, pp. 701–714, 2020.
  9. Y. Feng, J. Chen, Z. Huang, H. Wan, R. Xia, B. Wu, L. Sun, and M. Xing, “A lightweight position-enhanced anchor-free algorithm for sar ship detection,” Remote Sens., vol. 14, no. 8, p. 1908, 2022.
  10. D. Li, Q. Liang, H. Liu, Q. Liu, H. Liu, and G. Liao, “A novel multidimensional domain deep learning network for sar ship detection,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–13, 2021.
  11. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 2117–2125.
  12. T. Zhang, X. Zhang, and X. Ke, “Quad-fpn: A novel quad feature pyramid network for sar ship detection,” Remote Sens., vol. 13, no. 14, p. 2771, 2021.
  13. K. Li, M. Zhang, M. Xu, R. Tang, L. Wang, and H. Wang, “Ship detection in sar images based on feature enhancement swin transformer and adjacent feature fusion,” Remote Sens., vol. 14, no. 13, p. 3186, 2022.
  14. J. Pang, K. Chen, J. Shi, H. Feng, W. Ouyang, and D. Lin, “Libra r-cnn: Towards balanced learning for object detection,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 821–830.
  15. L. Bai, C. Yao, Z. Ye, D. Xue, X. Lin, and M. Hui, “A novel anchor-free detector using global context-guide feature balance pyramid and united attention for sar ship detection,” IEEE Geosci. Remote Sens. Lett., vol. 20, pp. 1–5, 2023.
  16. P. Guo, T. Celik, N. Liu, and H.-C. Li, “Break through the border restriction of horizontal bounding box for arbitrary-oriented ship detection in sar images,” IEEE Geosci. Remote Sens. Lett., 2023.
  17. X. Leng, K. Ji, K. Yang, and H. Zou, “A bilateral cfar algorithm for ship detection in sar images,” IEEE Geosci. Remote Sens. Lett., vol. 12, no. 7, pp. 1536–1540, 2015.
  18. G. Gao, S. Gao, J. He, and G. Li, “Adaptive ship detection in hybrid-polarimetric sar images based on the power–entropy decomposition,” IEEE Trans. Geosci. Remote Sens., vol. 56, no. 9, pp. 5394–5407, 2018.
  19. H. Lang, Y. Xi, and X. Zhang, “Ship detection in high-resolution sar images by clustering spatially enhanced pixel descriptor,” IEEE Trans. Geosci. Remote Sens., vol. 57, no. 8, pp. 5407–5423, 2019.
  20. H. Dai, L. Du, Y. Wang, and Z. Wang, “A modified cfar algorithm based on object proposals for ship target detection in sar images,” IEEE Geosci. Remote Sens. Lett., vol. 13, no. 12, pp. 1925–1929, 2016.
  21. T. Li, Z. Liu, R. Xie, and L. Ran, “An improved superpixel-level cfar detection method for ship targets in high-resolution sar images,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 11, no. 1, pp. 184–194, 2017.
  22. W. An, C. Xie, and X. Yuan, “An improved iterative censoring scheme for cfar ship detection with sar imagery,” IEEE Trans. Geosci. Remote Sens., vol. 52, no. 8, pp. 4585–4595, 2013.
  23. L. Zhai, Y. Li, and Y. Su, “Inshore ship detection via saliency and context information in high-resolution sar images,” IEEE Geosci. Remote Sens. Lett., vol. 13, no. 12, pp. 1870–1874, 2016.
  24. C.-Q. Zhang, Z.-W. Zhang, M.-Z. Chong, and Y.-H. Tan, “A joint unsupervised super-resolution and sar object detection network,” in Proc. Int. Conf. Comput. Commun. Secur. (ICCCS), 2023, pp. 1027–1030.
  25. Y. Zhao, L. Zhao, Z. Liu, D. Hu, G. Kuang, and L. Liu, “Attentional feature refinement and alignment network for aircraft detection in sar imagery,” arXiv:2201.07124, 2022.
  26. Y. Zhao, L. Zhao, C. Li, and G. Kuang, “Pyramid attention dilated network for aircraft detection in sar images,” IEEE Geosci. Remote Sens. Lett., vol. 18, no. 4, pp. 662–666, 2020.
  27. M. Zhao, X. Zhang, and A. Kaup, “Multitask learning for sar ship detection with gaussian-mask joint segmentation,” IEEE Trans. Geosci. Remote Sens., 2023.
  28. C. Yang, C. Zhang, Z. Fan, Z. Yu, Q. Sun, and M. Dai, “A multi-channel aggregation framework for object detection in large-scale sar image,” in Proc. Int. Conf. Acoust. Speech Signal Process. (ICASSP), 2023, pp. 1–5.
  29. K. Cheng, H. Cui, H. A. Ghafoor, H. Wan, Q. Mao, and Y. Zhan, “Tiny object detection via regional cross self-attention network,” IEEE Trans. Circuits Syst. Video Technol., 2022.
  30. Y. Zhang, M. Ding, Y. Bai, M. Xu, and B. Ghanem, “Beyond weakly supervised: Pseudo ground truths mining for missing bounding-boxes object detection,” IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 4, pp. 983–997, 2019.
  31. Y. Huang, Q. Jiang, and Y. Qian, “A novel method for video moving object detection using improved independent component analysis,” IEEE Trans. Circuits Syst. Video Technol., vol. 31, no. 6, pp. 2217–2230, 2020.
  32. Y. Li, E. Zhu, H. Chen, J. Tan, and L. Shen, “Dense crosstalk feature aggregation for classification and localization in object detection,” IEEE Trans. Circuits Syst. Video Technol., 2022.
  33. X. Zhou, S. Wu, R. Shi, B. Zheng, S. Wang, H. Yin, J. Zhang, and C. Yan, “Transformer-based multi-scale feature integration network for video saliency prediction,” IEEE Trans. Circuits Syst. Video Technol., 2023.
  34. B. Singh and L. S. Davis, “An analysis of scale invariance in object detection snip,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 3578–3587.
  35. B. Singh, M. Najibi, and L. S. Davis, “Sniper: Efficient multi-scale training,” Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 31, 2018.
  36. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “Ssd: Single shot multibox detector,” in Proc. Eur. Conf. Comput. Vis. (ECCV).   Springer, 2016, pp. 21–37.
  37. S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, “Path aggregation network for instance segmentation,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 8759–8768.
  38. C. Zhu, Y. He, and M. Savvides, “Feature selective anchor-free module for single-shot object detection,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 840–849.
  39. F. Ni and Y. Yao, “Multi-task learning via scale aware feature pyramid networks and effective joint head,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2019, pp. 0–0.
  40. M. Tan and Q. Le, “Efficientnet: Rethinking model scaling for convolutional neural networks,” in Proc. Int. Conf. Mach. Learn. (ICML).   PMLR, 2019, pp. 6105–6114.
  41. S. Liu, D. Huang, and Y. Wang, “Learning spatial fusion for single-shot object detection,” arXiv:1911.09516, 2019.
  42. K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, and Q. Tian, “Centernet: Keypoint triplets for object detection,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2019, pp. 6569–6578.
  43. G. Yang, J. Lei, Z. Zhu, S. Cheng, Z. Feng, and R. Liang, “Afpn: Asymptotic feature pyramid network for object detection,” arXiv:2306.15988, 2023.
  44. P.-Y. Chen, M.-C. Chang, J.-W. Hsieh, and Y.-S. Chen, “Parallel residual bi-fusion feature pyramid network for accurate single-shot object detection,” IEEE Trans. Image Process., vol. 30, pp. 9099–9111, 2021.
  45. Z. Jin, D. Yu, L. Song, Z. Yuan, and L. Yu, “You should look at all objects,” in Proc. Eur. Conf. Comput. Vis. (ECCV).   Springer, 2022, pp. 332–349.
  46. Z. Jin, B. Liu, Q. Chu, and N. Yu, “Safnet: A semi-anchor-free network with enhanced feature pyramid for object detection,” IEEE Trans. Image Process., vol. 29, pp. 9445–9457, 2020.
  47. C. Li, L. Li, Y. Geng, H. Jiang, M. Cheng, B. Zhang, Z. Ke, X. Xu, and X. Chu, “Yolov6 v3. 0: A full-scale reloading,” arXiv:2301.05586, 2023.
  48. B. Graham, A. El-Nouby, H. Touvron, P. Stock, A. Joulin, H. Jégou, and M. Douze, “Levit: a vision transformer in convnet’s clothing for faster inference,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2021, pp. 12 259–12 269.
  49. Q. Wan, Z. Huang, J. Lu, G. Yu, and L. Zhang, “Seaformer: Squeeze-enhanced axial transformer for mobile semantic segmentation,” arXiv:2301.13156, 2023.
  50. H. Zhang, Y. Wang, F. Dayoub, and N. Sunderhauf, “Varifocalnet: An iou-aware dense object detector,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021, pp. 8514–8523.
  51. Z. Gevorgyan, “Siou loss: More powerful learning for bounding box regression,” arXiv:2205.12740, 2022.
  52. X. Li, W. Wang, L. Wu, S. Chen, X. Hu, J. Li, J. Tang, and J. Yang, “Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection,” Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 33, pp. 21 002–21 012, 2020.
  53. W. Zhirui, K. Yuzhuo, Z. Xuan, W. Yuelei, Z. Ting, and S. Xian, “Sar-aircraft-1.0: High-resolution sar aircraft detection and recognition dataset,” J. Radars, vol. 12, no. 4, pp. 906–922, 2023.
  54. T. Zhang, X. Zhang, J. Li, X. Xu, B. Wang, X. Zhan, Y. Xu, X. Ke, T. Zeng, H. Su et al., “Sar ship detection dataset (ssdd): Official release and comprehensive data analysis,” Remote Sens., vol. 13, no. 18, p. 3690, 2021.
  55. S. Wei, X. Zeng, Q. Qu, M. Wang, H. Su, and J. Shi, “Hrsid: A high-resolution sar images dataset for ship detection and instance segmentation,” IEEE Access, vol. 8, pp. 120 234–120 254, 2020.
  56. K. Wang, J. H. Liew, Y. Zou, D. Zhou, and J. Feng, “Panet: Few-shot image semantic segmentation with prototype alignment,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2019, pp. 9197–9206.
  57. S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 28, 2015.
  58. Z. Cai and N. Vasconcelos, “Cascade r-cnn: Delving into high quality object detection,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 6154–6162.
  59. G. Jocher, A. Chaurasia, and J. Qiu, “Ultralytics yolov8.” 2023. [Online]. Available: https://github.com/ultralytics/ultralytics
  60. K. Fu, J. Fu, Z. Wang, and X. Sun, “Scattering-keypoint-guided network for oriented ship detection in high-resolution and large-scale sar images,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 14, pp. 11 162–11 178, 2021.
  61. H. Chang, X. Fu, J. Dong, J. Liu, and Z. Zhou, “Mlsdnet: Multi-class lightweight sar detection network based on adaptive scale distribution attention,” IEEE Geosci. Remote Sens. Lett., 2023.
  62. Z. Zhou, J. Chen, Z. Huang, J. Lv, J. Song, H. Luo, B. Wu, Y. Li, and P. S. Diniz, “Hrle-sardet: A lightweight sar target detection algorithm based on hybrid representation learning enhancement,” IEEE Trans. Geosci. Remote Sens., vol. 61, pp. 1–22, 2023.
  63. J. He, N. Su, C. Xu, Y. Liao, Y. Yan, C. Zhao, W. Hou, and S. Feng, “A cross-modality feature transfer method for target detection in sar images,” IEEE Trans. Geosci. Remote Sens., 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Mingxiang Cao (9 papers)
  2. Jie Lei (52 papers)
  3. Weiying Xie (31 papers)
  4. Jiaqing Zhang (30 papers)
  5. Daixun Li (9 papers)
  6. Yunsong Li (41 papers)
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now