Review of road extraction from high-resolution SAR images

doi:10.13474/j.cnki.11-2246.2025.1002

Abstract

Abstract: In view of the poor performance of optical remote sensing images in road extraction at night or under insufficient lighting conditions, this paper introduces SAR images road extraction methods based on semi-automatic and fully automatic approaches, as well as deep learning methods based on discriminative models and generative models.It summarizes their technical principles and applicable scenarios, analyzes the advantages and limitations of various methods in terms of extraction accuracy, computational complexity, and generalization, which provides technical references for road extraction based on SAR in complex environments.Meanwhile, in order to improve the effect of road extraction based on SAR, it is pointed out that the technologies of knowledge distillation, diffusion model-assisted annotation and large model architectures will have great potential.

Key words: SAR, road extraction, semi-automatic methods, fully automatic methods, discriminative models, generative models

CLC Number:

P237

JIANG Kaixin, SONG Shuhua, MAO Jian, SUN Zhen, GUO Guolong, DONG Li, GUO Hui. Review of road extraction from high-resolution SAR images[J]. Bulletin of Surveying and Mapping, 2025, 0(10): 7-13,19.

References

[1] [NIU Zheng,LI Songnian,POUSAEID N. Road extraction using smart phones GPS[C] //Proceedings of the 2nd International Conference on Computing for Geospatial Research & Applications-COM. Geo'11. Washington:ACM Press,2011:1-6. [2] ULMKE M,KOCH W. Road map extraction using GMTI tracking[C] //Proceedings of the 9th International Conference on Information Fusion. Florence:IEEE,2006:1-7. [3] MILETIEV R,PETKOV P Z,YORDANOV R,et al. Study of global navigation satellite system receivers' accuracy for unmanned vehicles[J]. Sensors,2024,24(18):5909. [4] BANKS D E,PASCHKE M,GHONASGI R,et al. Benefits and challenges of geographic information systems (GIS)for data-driven outreach in black communities experiencing overdose disparities:results of a stakeholder focus group[J]. BMC Public Health,2024,24(1):2103. [5] 陈立福,刘燕芝,张鹏,等. 基于Multi-Path RefineNet的多特征高分辨率SAR图像道路提取算法[J]. 计算机科学,2020,47(3):156-161. [6] ZHOU Yueyong,CHENG Jianghua,LIU Tong,et al. GPU-based SAR image lee filtering[C] //Proceedings of 2019 IEEE International Conference on Computer Science and Network Technology (ICCSNT). Dalian:IEEE,2019:17-21. [7] CHEN Yilun,GU Yuantao,GU Jing,et al. Particle filter based road detection in SAR image[C] //Proceedings of 2005 IEEE International Symposium on Microwave,Antenna,Propagation and EMC Technologies for Wireless Communications. Beijing:IEEE,2005:301-305. [8] CHEN Yilun,YANG Qiong,GU Yuantao,et al. Detection of roads in SAR images using particle filter[C] //Proceedings of 2006 International Conference on Image Processing. Atlanta:IEEE,2006:2337-2340. [9] KASS M,WITKIN A,TERZOPOULOS D. Snakes:active contour models[J]. International Journal of Computer Vision,1988,1(4):321-331. [10] 陈卫东,朱奇光. 基于模糊算法的移动机器人路径规划[J]. 电子学报,2011,39(4):971-974,980. [11] 谢巍. 形态学分析方法及在图像特征提取中的应用[D]. 哈尔滨:哈尔滨工程大学,2014. [12] XIAO Fanghong,TONG Ling,LUO Shiyu. A method for road network extraction from high-resolution SAR imagery using direction grouping and curve fitting[J]. Remote Sensing,2019,11(23):2733. [13] HE Wenjing,SONG Hongjun,YAO Yuanyuan,et al. A multiscale method for road network extraction from high-resolution SAR images based on directional decomposition and regional quality evaluation[J]. Remote Sensing,2021,13(8):1476. [14] CHANDLER H E,GIESECKE W. Technical writer's handbook[J]. IEEE Transactions on Professional Communication,1983,PC-26(2):90. [15] 王彦敏,林小竹,杜天苍,等. 一种基于分水岭变换的图像分割方法[J]. 北京石油化工学院学报,2005,13(4):40-44. [16] HU X,FUXIN L,SANARAS D,et al. Topology-preserving deep image segmentation[EB/OL]. [2025-02-15]. https://arxiv.org/abs/1906.05404. [17] SUN Na,FENG Yongjiu,TONG Xiaohua,et al. Road network extraction from SAR images with the support of angular texture signature and POIs[J]. Remote Sensing,2022,14(19):4832. [18] LIU Junyi,SUI Haigang,TAO Mingming,et al. Road extraction from SAR imagery based on an improved particle filtering and snake model[J]. International Journal of Remote Sensing,2013,34(22):8199-8214. [19] SAATI M,AMINI J,MABOUDI M. A method for automatic road extraction of high resolution SAR imagery[J]. Journal of the Indian Society of Remote Sensing,2015,43(4):697-707. [20] 韩李涛,周丽娟,郭佳,等. 基于建筑平面图的室内空间拓扑模型自动生成算法[J]. 测绘通报,2021(3):75-80,86. [21] GELING G,IONESCU D. An edge detection operator for SAR images[C] //Proceedings of Canadian Conference on Electrical and Computer Engineering. Vancouver,BC:IEEE,1993:707-709. [22] LI Guangting,ZHANG Xin,NIE Shikang,et al. Road extraction in SAR image based on the image dynamics and watershed transformation[C] //Proceedings of 2021 IEEE/ACIS International Fall Conference on Computer and Information Science (ICIS Fall). Xi'an:IEEE,2021:311-316. [23] WEI Xiaochen,LV Xiaolei,ZHANG Kaiyu. Road extraction in SAR images using ordinal regression and road-topology loss[J]. Remote Sensing,2021,13(11):2080. [24] LIU Hongrong,LIU Minghua,SONG Shuhua,et al. ECGNet:edge and class guided semantic segmentation network for remote sensing urban scene images[J]. Journal of Applied Remote Sensing,2024,18:034518. [25] 周得水. 基于模糊连接度的图像分割算法的研究[D]. 无锡:江南大学,2014. [26] 张鹏. Markov随机场在图像处理中应用的研究[D]. 武汉:华中科技大学,2005. [27] 符喜优,张风丽,王国军,等. 基于模糊连接度的高分辨率SAR图像道路自动提取[J]. 计算机应用,2015,35(2):523-527. [28] BO Yanchen,WANG Jinfeng,ZHU Caiying,et al. A wavelet-based filter for SAR speckle reduction and the comparative evaluation on its performance[J]. National Remote Sensing Bulletin,2003(5):393-399. [29] 吴禹昊,陈天泽,粟毅. 基于方向ROEWA算子的高分辨率SAR图像道路提取[J]. 计算机工程与科学,2010,32(8):71-74. [30] BEZDEK J C,EHRLICH R,FULL W. FCM:The fuzzy c-means clustering algorithm[J]. Computers & Geosciences,1984,10(2/3):191-203. [31] XU Rui,HE Chu,LIU Xinlong,et al. Bayesian fusion of multi-scale detectors for road extraction from SAR images[J]. ISPRS International Journal of Geo-Information,2017,6(1):26. [32] LAMPLE G,BALLESTEROS M,SUBRAMANIAN S,et al. Neural architectures for named entity recognition[C] //Proceedings of 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. San Diego:Association for Computational Linguistics,2016:260-270. [33] SHU Weitong,BIE Yuxuan,ZHANG Ruigang,et al. High-resolution SAR image road extraction based on MRF model[C] //Proceedings of the 4th China International SAR Symposium (CISS). Xi'an:IEEE,2023:1-6. [34] 万智萍. 一种高效的小波Contourlet变换阈值去噪算法[J]. 激光与红外,2013,43(7):831-836. [35] 商景辉. 基于Canny算子的边缘检测算法研究[J]. 信息与电脑,2020,32(2):39-41. [36] JIA Jianxin,SUN Haibin,JIANG Changhui,et al. Review on active and passive remote sensing techniques for road extraction[J]. Remote Sensing,2021,13(21):4235. [37] KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM,2017,60(6):84-90. [38] LONG J,SHELHAMER E and DARRELL T. Fully convolutional networks for semantic segmentation[EB/OL]. [2025-02-15]. https://arxiv.org/abs/1411.4038. [39] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C] //Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas:IEEE,2015. [40] WEI Xiaochen,FU Xikai,YUN Ye,et al. Multiscale and multitemporal road detection from high resolution SAR images using attention mechanism[J]. Remote Sensing,2021,13(16):3149. [41] GAO Fei,TU Jun,WANG Jun,et al. RoadSeg-CD:a network with connectivity array and direction map for road extraction from SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:3992-4003. [42] LI Han,WANG Yikuang,WAN Cheng,et al. MAU-Net:a retinal vessels segmentation method[C] //Proceedings of 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Montreal:IEEE,2020:1958-1961. [43] 覃熠. 基于分割网络的SAR图像道路提取方法研究[D]. 成都:电子科技大学,2023. [44] LI Yue,ZHANG Rong,WU Yunfei. Road network extraction in high-resolution SAR images based CNN features[C] //Proceedings of 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Fort Worth:IEEE,2017:1664-1667. [45] [ZHANG Qianqian,KONG Qingling,ZHANG Chao,et al. A new road extraction method using Sentinel-1 SAR images based on the deep fully convolutional neural network[J]. European Journal of Remote Sensing,2019,52(1):572-582. [46] HENRY C,AZIMI S M,MERKLE N. Road segmentation in SAR satellite images with deep fully convolutional neural networks[J]. IEEE Geoscience and Remote Sensing Letters,2018,15(12):1867-1871. [47] 熊炜,管来福,童磊,等. 基于残差神经网络的道路提取算法研究[J]. 光电子技术,2020,40(1):6-12. [48] YU F,KOLTUN V. Multi-scale context aggregation by dilated convolutions [EB/OL]. [2025-02-15]. https://arxiv.org/abs/1511.07122. [49] YU Jiangfeng,SUN Lin,SONG Shuhua,et al. BAIDet:remote sensing image object detector based on background and angle information[J]. Signal,Image and Video Processing,2024,18(12):9295-9304. [50] LIN G,MILAN A,SHEN C,et al. RefineNet:multi-path refinement networks for high-resolution semantic segmentation [EB/OL]. [2025-02-15]. https://arxiv.org/abs/1611.06612. [51] 薛玉利. 基于Gabor变换的特征提取及其应用[D]. 济南:山东大学,2007. [52] 肖达,王润民,邹孝,等. 基于Gabor变换和灰度梯度共生矩阵的超声无损测温研究[J]. 传感技术学报,2017,30(11):1684-1688. [53] 蒋源,张欢,朱高峰,等. 融合多尺度特征的残差车道线检测网络[J]. 测绘通报,2024(10):71-76. [54] 任雪美. 基于深度学习的高分辨率SAR图像道路提取研究[D]. 成都:电子科技大学,2022. [55] 刘宝宏,黄柯棣. 多分辨率建模的研究现状与发展[J]. 系统仿真学报,2004,16(6):1150-1154. [56] 林报嘉,刘晓东,杨川. 基于深度学习的高分影像道路提取方法研究[J]. 公路,2020,65(8):268-276. [57] CHEN Hao,LI Zhenghong,WU Jiangjiang,et al. SemiRoadExNet:a semi-supervised network for road extraction from remote sensing imagery via adversarial learning[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2023,198:169-183.