基于深度学习的SAR弱小目标检测研究进展
作者:
基金项目:

国家自然科学基金联合基金(U20B2068); 国家自然科学基金(62306005, 62006002, 62376004); 安徽省自然科学基金(2208085QF192)


Research Progress of SAR Weak Object Detection Based on Deep Learning
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [76]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    随着合成孔径雷达(SAR)技术的不断进步, 大范围观测和高分辨率成像使得SAR图像中包含了大量特征微弱的小尺寸目标, 通常涵盖飞机、车辆、油罐、船舶等高价值民用目标和关键军事目标, 这类目标尺寸较小、特征微弱、稠密相连、形态多变, 对它们进行精确的检测是当前SAR图像解译的难题. 随着深度学习技术的发展, 研究者们针对SAR弱小目标的成像特性和检测挑战, 通过对深度学习网络的精细调整和优化, 成功地推动了本领域的进步. 本文将全面回顾基于深度学习的SAR图像弱小目标检测, 以数据集和方法为研究对象, 深入分析SAR弱小目标检测任务所面临的主要挑战, 总结最新检测方法的特点和应用场景, 并汇总整理了公开数据集与常用性能评估指标. 最后, 总结本任务的应用现状, 并对未来的发展趋势进行展望.

    Abstract:

    Advancements in synthetic aperture radar (SAR) technology have enabled large-scale observations and high-resolution imaging. Consequently, SAR images now contain numerous small-sized objects with weak features, including aircraft, vehicles, tanks, and ships, which are of high value in civilian and key military assets. However, accurately detecting these objects poses a significant challenge due to their small size, dense connectivity, and variable morphology. Deep learning technology has ushered in a new era of progress in SAR object detection. Researchers have made substantial strides by fine-tuning and optimizing deep learning networks to address the imaging characteristics and detection challenges associated with weak SAR objects. This study provides a comprehensive review of deep learning-based methodologies for weak object detection in SAR images. The primary focus is on datasets and methods, providing a thorough analysis of the principal challenges encountered in SAR weak object detection. This study also summarizes the characteristics and application scenarios of recent detection methods, as well as collates and organizes publicly available datasets and common performance evaluation metrics. In conclusion, this study provides an overview of the current application status of SAR weak object detection and offers insights into future development trends.

    参考文献
    [1] 李毅, 杜兰, 杜宇昂. 基于特征分解卷积神经网络的SAR图像目标检测方法. 雷达学报, 2023, 12(5): 1069–1080.
    [2] Chen JL, Zhang JC, Jin YH, et al. Real-time processing of spaceborne SAR data with nonlinear trajectory based on variable PRF. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5205212.
    [3] Xu F, Shi YL, Ebel P, et al. GLF-CR: SAR-enhanced cloud removal with global-local fusion. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 192: 268–278.
    [4] Pu W. Shuffle GAN with autoencoder: A deep learning approach to separate moving and stationary targets in SAR imagery. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(9): 4770–4784.
    [5] Hu RZ, Li XL, Yeo TS, et al. Refocusing and zoom-in polar format algorithm for curvilinear spotlight SAR imaging on arbitrary region of interest. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(10): 7995–8010.
    [6] Wang Z, Xu N, Guo JX, et al. SCFNet: Semantic condition constraint guided feature aware network for aircraft detection in SAR images. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5239420.
    [7] 徐丰, 王海鹏, 金亚秋. 合成孔径雷达图像智能解译. 北京: 科学出版社, 2020.
    [8] Chen LF, Luo R, Xing J, et al. Geospatial transformer is what you need for aircraft detection in SAR Imagery. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5225715.
    [9] 郭倩, 王海鹏, 徐丰. SAR图像飞机目标检测识别进展. 雷达学报, 2020, 9(3): 497–513.
    [10] Lin TY, Maire M, Belongie S, et al. Microsoft COCO: Common objects in context. Proceedings of the 13th European Conference on Computer Vision. Zurich: Springer, 2014. 740–755.
    [11] Cheng G, Yuan X, Yao XW, et al. Towards large-scale small object detection: Survey and benchmarks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(11): 13467–13488.
    [12] Chen CY, Liu MY, Tuzel O, et al. R-CNN for small object detection. Proceedings of the 13th Asian Conference on Computer Vision. Taipei: Springer, 2017. 214–230.
    [13] Wang XQ, Li G, Zhang XP, et al. A fast CFAR algorithm based on density-censoring operation for ship detection in SAR images. IEEE Signal Processing Letters, 2021, 28: 1085–1089.
    [14] Yang R, Wang R, Deng YK, et al. Rethinking the random cropping data augmentation method used in the training of CNN-based SAR image ship detector. Remote Sensing, 2020, 13(1): 34.
    [15] Zou LC, Zhang H, Wang C, et al. MW-ACGAN: Generating multiscale high-resolution SAR images for ship detection. Sensors, 2020, 20(22): 6673.
    [16] Li L, Wang C, Zhang H, et al. SAR image ship object generation and classification with improved residual conditional generative adversarial network. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 4000105.
    [17] Shi X, Xing MD, Zhang JS, et al. ISAGAN: A high-fidelity full-azimuth SAR image generation method. Proceedings of the 3rd China International SAR Symposium (CISS). Shanghai: IEEE, 2022. 1–4.
    [18] Wang CW, Pei JF, Liu XY, et al. SAR target image generation method using azimuth-controllable generative adversarial network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 9381–9397.
    [19] Zhao CX, Fu XJ, Dong J, et al. SAR ship detection based on end-to-end morphological feature pyramid network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 4599–4611.
    [20] Zhang L, Zhang ZJ, Lu ST, et al. Fast superpixel-based non-window CFAR ship detector for SAR imagery. Remote Sensing, 2022, 14(9): 2092.
    [21] Zhou Z, Cui ZY, Zang ZP, et al. UltraHi-PrNet: An ultra-high precision deep learning network for dense multi-scale target detection in SAR images. Remote Sensing, 2022, 14(21): 5596.
    [22] Wang JP, Lin YQ, Guo J, et al. SSS-YOLO: Towards more accurate detection for small ships in SAR image. Remote Sensing Letters, 2021, 12(2): 93–102.
    [23] Yu L, Wu HY, Zhong Z, et al. TWC-Net: A SAR ship detection using two-way convolution and multiscale feature mapping. Remote Sensing, 2021, 13(13): 2558.
    [24] Feng Y, Chen J, Huang ZX, et al. A lightweight position-enhanced anchor-free algorithm for SAR ship detection. Remote Sensing, 2022, 14(8): 1908.
    [25] Bai L, Yao C, Ye Z, et al. A novel anchor-free detector using global context-guide feature balance pyramid and united attention for SAR ship detection. IEEE Geoscience and Remote Sensing Letters, 2023, 20: 4003005.
    [26] Xu P, Li QY, Zhang B, et al. On-board real-time ship detection in HISEA-1 SAR images based on CFAR and lightweight deep learning. Remote Sensing, 2021, 13(10): 1995.
    [27] Dai WX, Mao YQ, Yuan RA, et al. A novel detector based on convolution neural networks for multiscale SAR ship detection in complex background. Sensors, 2020, 20(9): 2547.
    [28] Liu SW, Kong WM, Chen XF, et al. Multi-scale ship detection algorithm based on a lightweight neural network for spaceborne SAR images. Remote Sensing, 2022, 14(5): 1149.
    [29] Bai QL, Gao G, Zhang X, et al. LSDNet: Lightweight CNN model driven by PNF for PolSAR image ship detection. IEEE Journal on Miniaturization for Air and Space Systems, 2022, 3(3): 135–142.
    [30] Xu XW, Zhang XL, Shao ZK, et al. A group-wise feature enhancement-and-fusion network with dual-polarization feature enrichment for SAR ship detection. Remote Sensing, 2022, 14(20): 5276.
    [31] Zhou YS, Zhang FX, Ma F, et al. Small vessel detection based on adaptive dual-polarimetric feature fusion and sea-land segmentation in SAR images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 2519–2534.
    [32] Huang ZL, Datcu M, Pan ZX, et al. Deep SAR-Net: Learning objects from signals. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 161: 179–193.
    [33] Sun YR, Wang ZR, Sun X, et al. SPAN: Strong scattering point aware network for ship detection and classification in large-scale SAR imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 1188–1204.
    [34] Zhang YP, Lu DD, Qiu XL, et al. scattering-point-guided RPN for oriented ship detection in SAR images. Remote Sensing, 2023, 15(5): 1411.
    [35] An WT, Lin MS, Yang HJ. Stationary marine target detection with time-series SAR imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 6406–6413.
    [36] Kahar S, Hu FM, Xu F. Ship detection in complex environment using SAR time series. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 3552–3563.
    [37] Ge J, Wang C, Zhang B, et al. Azimuth-sensitive object detection of high-resolution SAR images in complex scenes by using a spatial orientation attention enhancement network. Remote Sensing, 2022, 14(9): 2198.
    [38] Su N, He JY, Yan YM, et al. SII-Net: Spatial information integration network for small target detection in SAR images. Remote Sensing, 2022, 14(3): 442.
    [39] Niu YZ, Li YZ, Huang JY, et al. Efficient encoder-decoder network with estimated direction for SAR ship detection. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 4504405.
    [40] Deng YW, Guan DH, Chen YY, et al. SAR-shipnet: SAR-ship detection neural network via bidirectional coordinate attention and multi-resolution feature fusion. Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore: IEEE, 2022. 3973–3977.
    [41] 武俊杰, 孙稚超, 吕争, 等. 星源照射双/多基地SAR成像. 雷达学报, 2023, 12(1): 13–35.
    [42] Schmitt M, Hughes LH, Zhu XX. The SEN1-2 dataset for deep learning in SAR-optical data fusion. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2018, IV-1: 141–146.
    [43] Wang XQ, Zhu D, Li G, et al. Proposal-copula-based fusion of spaceborne and airborne SAR images for ship target detection. Information Fusion, 2022, 77: 247–260.
    [44] Zhang CX, Feng YK, Hu L, et al. A domain adaptation neural network for change detection with heterogeneous optical and SAR remote sensing images. International Journal of Applied Earth Observation and Geoinformation, 2022, 109: 102769.
    [45] Kang WC, Xiang YM, Wang F, et al. CFNet: A cross fusion network for joint land cover classification using optical and SAR images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 1562–1574.
    [46] Gao QW, Feng ZX, Yang SY, et al. Multi-path interactive network for aircraft identification with optical and SAR images. Remote Sensing, 2022, 14(16): 3922.
    [47] Lou X, Liu YC, Xiong ZW, et al. Generative knowledge transfer for ship detection in SAR images. Computers and Electrical Engineering, 2022, 101: 108041.
    [48] Zhang JS, Xing MD, Sun GC, et al. Multiple statistics contributing to few-sample deep learning for subtle trace detection in high-resolution SAR images. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5210114.
    [49] Shi H, Fang ZH, Wang YP, et al. An adaptive sample assignment strategy based on feature enhancement for ship detection in SAR images. Remote Sensing, 2022, 14(9): 2238.
    [50] Xu ZJ, Gao R, Huang K, et al. Triangle distance IoU loss, attention-weighted feature pyramid network, and rotated-SARShip dataset for arbitrary-oriented SAR ship detection. Remote Sensing, 2022, 14(18): 4676.
    [51] Yu JM, Wu T, Zhang X, et al. An efficient lightweight SAR ship target detection network with improved regression loss function and enhanced feature information expression. Sensors, 2022, 22(9): 3447.
    [52] Zhao SY, Zhang ZH, Guo WW, et al. An automatic ship detection method adapting to different satellites SAR images with feature alignment and compensation loss. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5225217.
    [53] Zhang TW, Zhang XL, Li JW, et al. SAR ship detection dataset (SSDD): Official release and comprehensive data analysis. Remote Sensing, 2021, 13(18): 3690.
    [54] Wang YY, Wang C, Zhang H, et al. A SAR dataset of ship detection for deep learning under complex backgrounds. Remote Sensing, 2019, 11(7): 765.
    [55] 孙显, 王智睿, 孙元睿, 等. AIR-SARShip-1.0: 高分辨率SAR舰船检测数据集. 雷达学报, 2019, 8(6): 852–862.
    [56] Wei SJ, Zeng XF, Qu QZ, et al. HRSID: A high-resolution SAR images dataset for ship detection and instance segmentation. IEEE Access, 2020, 8: 120234–120254.
    [57] Zhang TW, Zhang XL, Ke X, et al. LS-SSDD-v1.0: A deep learning dataset dedicated to small ship detection from large-scale Sentinel-1 SAR images. Remote Sensing, 2020, 12(18): 2997.
    [58] Lei SL, Lu DD, Qiu XL, et al. SRSDD-v1.0: A high-resolution SAR rotation ship detection dataset. Remote Sensing, 2021, 13(24): 5104.
    [59] Xia R, Chen J, Huang Z, et al. CRTransSar: A visual transformer based on contextual joint representation learning for SAR ship detection. Remote Sensing, 2022, 14(6): 1488.
    [60] 徐从安, 苏航, 李健伟, 等. RSDD-SAR: SAR舰船斜框检测数据集. 雷达学报, 2022, 11(4): 581–599.
    [61] Zhang P, Xu H, Tian T, et al. SEFEPNet: Scale expansion and feature enhancement pyramid network for SAR aircraft detection with small sample dataset. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 3365–3375.
    [62] 王智睿, 康玉卓, 曾璇, 等. SAR-AIRcraft-1.0: 高分辨率SAR飞机检测识别数据集. 雷达学报, 2023, 12(4): 906–922.
    [63] Chang H, Fu XJ, Lu JH, et al. SPANet: A self-balancing position attention network for anchor-free SAR ship detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16: 8363–8378.
    [64] Tang G, Zhao HR, Claramunt C, et al. PPA-Net: Pyramid pooling attention network for multi-scale ship detection in SAR images. Remote Sensing, 2023, 15(11): 2855.
    [65] Zhu HZ, Xie Y, Huang HH, et al. DB-YOLO: A duplicate bilateral YOLO network for multi-scale ship detection in SAR images. Sensors, 2021, 21(23): 8146.
    [66] Zhao CX, Fu XJ, Dong J, et al. Lpdnet: A lightweight network for SAR ship detection based on multi-level laplacian denoising. Sensors, 2023, 23(13): 6084.
    [67] Yu JM, Zhou GY, Zhou SB, et al. A fast and lightweight detection network for multi-scale SAR ship detection under complex backgrounds. Remote Sensing, 2022, 14(1): 31.
    [68] Yang S, An WT, Li SB, et al. An improved FCOS method for ship detection in SAR images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 8910–8927.
    [69] Zhang LB, Li CY, Zhao LJ, et al. A cascaded three-look network for aircraft detection in SAR images. Remote Sensing Letters, 2020, 11(1): 57–65.
    [70] Zou B, Qin J, Zhang LM. Vehicle detection based on semantic-context enhancement for high-resolution SAR images in complex background. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 4503905.
    [71] Sun Y, Wang WN, Zhang QY, et al. Improved YOLOv5 with Transformer for large scene military vehicle detection on SAR image. Proceedings of the 7th International Conference on Image, Vision and Computing (ICIVC). Xi’an: IEEE, 2022. 87–93.
    [72] Kang YZ, Wang ZR, Fu JM, et al. SFR-Net: Scattering feature relation network for aircraft detection in complex SAR images. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5218317.
    [73] Yan GX, Chen ZH, Wang Y, et al. LssDet: A lightweight deep learning detector for SAR ship detection in high-resolution SAR images. Remote Sensing, 2022, 14(20): 5148.
    [74] Song T, Kim S, Kim ST, et al. Context-preserving instance-level augmentation and deformable convolution networks for SAR ship detection. Proceedings of the 2022 IEEE Radar Conference (RadarConf22). New York: IEEE, 2022. 1–6.
    [75] Sun YR, Sun X, Wang ZR, et al. Oriented ship detection based on strong scattering points network in large-scale SAR images. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5218018.
    [76] Spr?hnle K, Fuchs EM, Pelizari PA. Object-based analysis and fusion of optical and SAR satellite data for dwelling detection in refugee camps. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(5): 1780–1791.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

赵志成,蒋攀,王福田,肖云,李成龙,汤进.基于深度学习的SAR弱小目标检测研究进展.计算机系统应用,2024,33(6):1-15

复制
分享
文章指标
  • 点击次数:719
  • 下载次数: 3077
  • HTML阅读次数: 1728
  • 引用次数: 0
历史
  • 收稿日期:2023-12-21
  • 最后修改日期:2024-01-23
  • 在线发布日期: 2024-05-09
文章二维码
您是第10650722位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号