基于Duda算子的多尺度SAR道路提取方法

doi:10.12305/j.issn.1001-506X.2023.10.10

摘要/Abstract

摘要：

针对合成孔径雷达(synthetic aperture radar, SAR)图像中不同等级道路兼顾提取的问题, 提出了一种有效的、由粗渐精的层进式SAR道路多尺度提取方法。基于Duda检测算子, 通过对SAR图像中道路目标的多尺度提取和结果整合, 提升了对图像中不同等级道路的提取几率, 增加了对潜在道路片段的链接概率。在此基础上, 通过结合尺度滤波、形态滤波和片段链接的层进式设计, 实现了对SAR图像道路的有效提取。所提方法在实际的SAR图像上进行了试验, 获取了连续、完整的SAR道路提取结果, 验证了该方法的有效性。

关键词: 合成孔径雷达, 多尺度, 形态学, 道路提取

Abstract:

Aiming at the problem of extracting different levels of roads in synthetic aperture radar (SAR) images, an effective multi-scale extraction method for SAR roads from coarse to fine is proposed. Based on Duda operator, the method improves the extraction probability of different levels of roads and increases the link probability of potential road segments through multi-scale extraction and results, integration of road in SAR images. On this basis, the effective extraction of roads in SAR images is realized by combing the hierarchical design of scale filtering, morphological filtering, and fragment linking. The proposed method is tested on real SAR images, and the effectiveness of the method is verified by continuous and complete extraction results of road in SAR images.

Key words: synthetic aperture radar (SAR), multi-scale, morphology, road extraction

中图分类号:

TP391.4

金国栋, 谭力宁, 王小龙, 赵建伟. 基于Duda算子的多尺度SAR道路提取方法[J]. 系统工程与电子技术, 2023, 45(10): 3076-3082.

Guodong JIN, Lining TAN, Xiaolong WANG, Jianwei ZHAO. Multi-scale SAR road extraction method based on Duda operator[J]. Systems Engineering and Electronics, 2023, 45(10): 3076-3082.

图/表 6

图1

图2

图3

图4

图5

表1

参考文献 30

1	XIAN K Y , YANG L P , ZHOU R B , et al. Road semantic segmentation method for substation inspection robot and its application[J]. Science Technology and Engineering, 2020, 20 (15): 6151- 6157. doi: 10.3969/j.issn.1671-1815.2020.15.038
2	GIGLI L , KIRAN B R , PAUL T , et al. Road segmentation on low resolution Lidar point clouds for autonomous vehicles[J]. ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences, 2020, 2, 335- 342.
3	WANG W X , YANG N , ZHANG Y , et al. A review of road extraction from remote sensing images[J]. Journal of Traffic and Transportation Engineering, 2016, 3 (3): 271- 282.
4	张永宏, 何静, 阚希, 等. 遥感图像道路提取方法综述[J]. 计算机工程与应用, 2018, 54 (13): 1- 10. doi: 10.3778/j.issn.1002-8331.1804-0271
	ZHANG Y H , HE J , KAN X , et al. Summary of road extraction methods for remote sensing images[J]. Computer Engineering and Application, 2018, 54 (13): 1- 10. doi: 10.3778/j.issn.1002-8331.1804-0271
5	周岳勇, 程江华, 刘通, 等. 高分辨率SAR图像道路提取综述[J]. 计算机科学, 2020, 47 (1): 130- 141.
	ZHOU Y Y , CHENG J H , LIU T , et al. Review of road extraction for high-resolution SAR images[J]. Computer Science, 2020, 47 (1): 130- 141.
6	贾建鑫, 孙海彬, 蒋长辉, 等. 多源遥感数据的道路提取技术研究现状及展望[J]. 光学精密工程, 2021, 29 (2): 430- 442.
	JIA J X , SUN H B , JIANG C H , et al. Road extraction technology based on multi-source remote sensing data: review and prospects[J]. Optics and Precision Engineering, 2021, 29 (2): 430- 442.
7	PAILLOU N, THIRION-LEFEVRE L, GUINVARCH R. Characterization and extraction of roads using polarimetry me-thods in L-band SAR images[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2021: 327-330.
8	BENTABET L , JODOUIN S , ZIOU D , et al. Road vectors update using SAR imagery: a snake-based method[J]. IEEE Trans. on Geoscience and Remote Sensing, 2003, 41 (8): 1785- 1803. doi: 10.1109/TGRS.2003.813850
9	WEI Q R , FENG D Z . Extraction of line feature in SAR images through image edge fields[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13 (4): 540- 544. doi: 10.1109/LGRS.2016.2523560
10	肖红光, 文俊, 张立福, 等. 一种新的高分辨率SAR图像道路提取算法[J]. 计算机工程与应用, 2016, 52 (15): 198- 202. doi: 10.3778/j.issn.1002-8331.1409-0375
	XIAO H G , WEN J , ZHANG L F , et al. New road extraction algorithm of high resolution SAR image[J]. Computer Engineering and Application, 2016, 52 (15): 198- 202. doi: 10.3778/j.issn.1002-8331.1409-0375
11	朱昌盛, 周伟, 关键. 基于平行线对检测的SAR图像主干道提取算法[J]. 中国图象图形学报, 2011, 16 (10): 1908- 1917.
	ZHU C S , ZHOU W , GUAN J . Main roads extraction from SAR imagery based on parallel pairs detection[J]. Journal of Image and Graphics, 2011, 16 (10): 1908- 1917.
12	LUO Y X , AN D X , WANG W , et al. Improved ROEWA SAR image edge detector based on curvilinear structures extraction[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17 (4): 631- 635. doi: 10.1109/LGRS.2019.2926428
13	LIAN R B , WANG W X , MUSTAFA N , et al. Road extraction methods in high-resolution remote sensing images: a comprehensive review[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13, 5489- 5507. doi: 10.1109/JSTARS.2020.3023549
14	ZHANG Q Q , KONG Q L , ZHANG C , 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. doi: 10.1080/22797254.2019.1694447
15	LIU H F , HAN X F , LI X R , et al. Deep representation learning for road detection through Siamese network[J]. Multimedia Tools and Applications, 2019, 78 (17): 24269- 24283. doi: 10.1007/s11042-018-6986-1
16	WEI X C , LV X L , ZHANG K Y . Road extraction in SAR images using ordinal regression and road-topology loss[J]. Remote Sensing, 2021, 13 (11): 2080. doi: 10.3390/rs13112080
17	HE W J , SONG H J , YAO Y Y , 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. doi: 10.3390/rs13081476
18	SUN Z G, GENG H, JIA B. Road segmentation algorithm based on simplified mask R-CNN for GF-3 SAR images[C]//Proc. of the SAR in Big Data Era, 2021.
19	GE Z J , ZHAO Y L , WANG J , et al. Deep feature-review transmit network of contour-enhanced road extraction from remote sensing images[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19, 3001805.
20	SUN Z G , GENG H , LU Z , et al. Review of road segmentation for SAR images[J]. Remote Sensing, 2021, 13 (5): 1011. doi: 10.3390/rs13051011
21	ZHOU G Y , CUI Y , CHEN Y L , et al. SAR image edge detection using curvelet transform and Duda operator[J]. Electronics letters, 2010, 46 (2): 167- 169.
22	ABDOLLAHI A , PRADHAN B , SHUKLA N , et al. Deep learning approaches applied to remote sensing datasets for road extraction: a state-of-the-art review[J]. Remote Sensing, 2020, 12 (9): 1444.
23	陈尹刚. 基于数学形态学图像处理算法研究[J]. 信息通信, 2019, (12): 67- 68.
	CHEN Y G . Research on image processing algorithms based on mathematical morphology[J]. Information & Communications, 2019, (12): 67- 68.
24	VERA E , LUCIO D , FERNANDES L , et al. Hough transform for real-time plane detection in depth images[J]. Pattern Recognition Letters, 2018, 103, 8- 15.
25	BERGUES G J, SCHURRER C, BRAMBILLA N. Straight line detection through sub-pixel Hough transform[C]//Proc. of the Conference on Advances in Intelligent Systems and Computing, Intelligent Computing, 2019, 998: 1129-1137.
26	沈夏炯, 张汇东, 韩道军. 一种面向SAR图像的多窗口道路边缘检测算法[J]. 计算机工程与应用, 2018, 54 (19): 164- 171.
	SHEN X J , ZHANG H D , HAN D J . Method for SAR image road edge detection based on multi-window fusion[J]. Computer Engineering and Applications, 2018, 54 (19): 164- 171.
27	SUN Z G , ZHAO M M , JIA B . A GF-3 SAR image dataset of road segmentation[J]. Information Technology and Control, 2021, 50 (1): 89- 101.
28	徐欢, 任沂斌. 基于混合损失U-Net的SAR图像渤海海冰检测研究[J]. 海洋学报, 2021, 43 (6): 157- 170.
	XU H , REN Y B . Detecting sea ice of Bohai Sea using SAR image based on a hybrid loss U-Net model[J]. Acta Oenological Sinica, 2021, 43 (6): 157- 170.
29	RADHAKRISHNAN K , SCOTT K , CLAUSI D . Sea ice concentration estimation: using passive microwave and SAR data with a U-Net and curriculum learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14, 5339- 5351.
30	VAN-ETTEN A, SHERMEYER J, HOGAN D, et al. Road network and travel time extraction from multiple look angles with spacenet data[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2020: 3920-3923.

方法	提取率/%	正确率/%	提取品质
Mask R-CNN方法	74.80	97.50	0.72
U-Net方法	76.60	94.70	0.73
WLE方法	85.60	59.80	0.54
本文方法	94.10	81.84	0.79

[1]	刘鸣谦, 徐仲秋, 陈天成, 张冰尘, 吴一戎. 基于L₁ & TV正则化的低过采样Staggered SAR成像方法[J]. 系统工程与电子技术, 2023, 45(9): 2718-2726.
[2]	王中宝, 尹奎英. 基于联合域滤波的无人机载SAR图像块效应抑制方法[J]. 系统工程与电子技术, 2023, 45(9): 2768-2776.
[3]	寇鹏, 刘永祥, 张弛, 李玮杰, 张双辉, 霍凯. 序列ISAR像复杂结构航天器在轨姿态估计[J]. 系统工程与电子技术, 2023, 45(8): 2438-2445.
[4]	王宁, 贺鹏超, 卢景月, 刘曦. 基于DOA估计的前视多通道SAR成像方法[J]. 系统工程与电子技术, 2023, 45(8): 2471-2478.
[5]	王鹏飞, 詹珩艺, 孙洪忠. 双基前视雷达二维空变补偿频域成像方法[J]. 系统工程与电子技术, 2023, 45(7): 1990-2001.
[6]	朱瀚神, 胡文华, 郭宝锋, 焦丽婷, 朱晓秀, 朱常安. 双基地ISAR稀疏孔径机动目标MTRC补偿成像算法[J]. 系统工程与电子技术, 2023, 45(7): 2022-2030.
[7]	董思强, 邓年茂, 刘琰. 基于多尺度特征的像素位姿定位优化方法[J]. 系统工程与电子技术, 2023, 45(7): 2203-2210.
[8]	汪俊澎, 邢世其, 李永祯, 黄大通, 宋少秋. 基于时频交叉乘积的调频连续波SAR干扰方法研究[J]. 系统工程与电子技术, 2023, 45(6): 1651-1657.
[9]	杨磊, 夏亚波, 廖仙华, 毛欣瑶, 窦宇宸, 杨桓. 双层稀疏贝叶斯学习ISAR超分辨成像算法[J]. 系统工程与电子技术, 2023, 45(5): 1371-1379.
[10]	吴其华, 赵锋, 王俊杰, 徐志明, 肖顺平. 基于编码相位调制的ISAR图像特征控制方法[J]. 系统工程与电子技术, 2023, 45(4): 1000-1007.
[11]	张冬冬, 王春平, 付强. 基于特征增强网络的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2023, 45(4): 1032-1039.
[12]	李相海, 杨志伟, 贺顺, 廖桂生, 韩超垒, 姜岩. 基于路网信息辅助的多星编队系统SAR-GMTI动目标径向速度估计与重定位方法[J]. 系统工程与电子技术, 2023, 45(3): 629-637.
[13]	朱晓秀, 刘利民, 胡文华, 郭宝锋, 史林, 朱瀚神. 基于GTD模型的多视角多频带ISAR融合成像[J]. 系统工程与电子技术, 2023, 45(3): 726-735.
[14]	黄艳堃, 邓玉辉, 孙光才, 邢孟道. 基于时间信息加权的ViSAR目标阴影跟踪算法[J]. 系统工程与电子技术, 2023, 45(10): 3065-3075.
[15]	李瑞泽, 张双辉, 刘永祥. 基于卷积ADMM网络的高效结构化稀疏ISAR成像方法[J]. 系统工程与电子技术, 2023, 45(1): 56-70.