Please wait a minute...
Remote Sensing for Land & Resources    2020, Vol. 32 Issue (2) : 54-62     DOI: 10.6046/gtzyyg.2020.02.08
River extraction from GF-1 satellite images combining stroke width transform and a geometric feature set
Zhuhong ZHANG, Baoyun WANG(), Yumei SUN, Caidong LI, Xianchen SUN, Lingli ZHANG
School of Information Science and Technology, Yunnan Normal University, Kunmin 650500, China
Download: PDF(6419 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    

Extracting rivers from high-resolution satellite images has many important implications. At present, most methods are devoted to extracting rivers from the spectral characteristics or texture analysis of rivers. But for the image which is with the phenomenon of the same object with different spectra or different objects with the same spectra, or has serious noise, or is hard to determine the scale of texture analysis, the method based on water spectrum analysis or texture analysis is not very suitable. The rivers in high-resolution satellite images are generally irregular in structure, and it is more likely that the rivers have different spectral features and texture features due to various reasons. However, in some satellite images, rivers may have approximately uniform width over a wide range. In view of such a situation, a river extraction method combining stroke width transform and geometric feature set is proposed innovatively. Firstly, the Canny edge detector is used to extract the edge of the image, and the edge map is used as the input of the stroke width transform algorithm to obtain the stroke width map. Then, the connected pixels are grouped by using the connected component algorithm, and next, the connected components obtained after the grouping are filtered according to the geometric feature set, and finally the remaining connected components experience the process for filling holes. Experiments using the GF-1 satellite images show that the method can suppress the noise well while extracting the target river. At the same time, compared with the Multiplicative Duda operator and the region growing algorithm, the proposed method has obvious advantages in the aspects of extraction effect and algorithm stability.

Keywords GF-1      river extraction      stroke width transform      geometric feature set     
:  P237  
Corresponding Authors: Baoyun WANG     E-mail:
Issue Date: 18 June 2020
E-mail this article
E-mail Alert
Articles by authors
Zhuhong ZHANG
Baoyun WANG
Yumei SUN
Caidong LI
Xianchen SUN
Lingli ZHANG
Cite this article:   
Zhuhong ZHANG,Baoyun WANG,Yumei SUN, et al. River extraction from GF-1 satellite images combining stroke width transform and a geometric feature set[J]. Remote Sensing for Land & Resources, 2020, 32(2): 54-62.
URL:     OR
Fig.1  Four bands of GF-1
Fig.2  Flowchart of a river extraction method combining SWT and GFS
Fig.3  Schematic diagram of each step of the proposed method
Fig.4  Illustration of algorithm step to SWT
Fig.5  Examples of circumcircle
Fig.6  Examples of external rectangle
Tab.1  Proposed method compard with MDRO and RGA
Fig.7  Illustration of the quantitative analysis metric
方法 s1 s2 s3
Com Cor Qua Com Cor Qua Com Cor Qua
MDRO 90 81.6 71.2 90.8 68.5 64.1 87.2 49.8 46.4
MDRO+GFS 83.6 100 83.6 89.8 100 89.7 86 99.5 85.7
RGA(生长阈值50) 54.6 98.8 54.2 74.5 100 74.5 65.6 100 65.6
RGA(生长阈值130) 提取失败 100 71.7 71.7 100 64.3 64.3
本文方法 99.1 96.9 96 97.7 95.5 93.3 99.4 98 97.5
方法 s4 s5 s6
Com Cor Qua Com Cor Qua Com Cor Qua
MDRO 91.2 56.5 53.6 95.5 3.3 3.3 97 6 6
MDRO+GFS 87.2 100 87.2 82.4 96.4 80 94.1 99.4 93.6
RGA(生长阈值50) 44.1 100 44.1 79.6 100 79.6 77.8 100 77.8
RGA(生长阈值130) 提取失败 96.7 59 57.8 提取失败
本文方法 96.8 95.3 92.4 98.3 95.2 93.7 99.3 99.1 98.4
Tab.2  Results ontained using the quantitative analysis metric(%)
[1] 冷凯群. 基于PLFT及图像融合的卫星河流识别[J]. 计算机工程与设计, 2018,39(12):170-174.
[1] Leng K Q. PLFT and images fusion-based satellite rivers detection[J]. Computer Engineering and Design, 2018,39(12):170-174.
[2] Zhang Y. A method for continuous extraction of multispectrally classified urban rivers[J]. Photogrammetric Engineering and Remote Sensing, 2000,66:991-999.
[3] Rani G M D, Viswanath K. Extraction of river from satellite images [C]// 2nd International Conference on Recent Trends in Electronics,Information & Communication Technology(RTEICT 2017).IEEE, 2017: 226-230.
[4] Matgen P, Hostache R, Schumann G, et al. Towards an automated SAR-based flood monitoring system:Lessons learned from two case studies[J]. Physics & Chemistry of the Earth, 2011,36(7):241-252.
[5] 姜浩, 冯敏, 肖桐, 等. 基于线状特征增强的TM遥感影像细小河流提取方法[J].测绘学报, 2014(7):705-710.
[5] Jiang H, Feng M, Xiao T, et al. A narrow river extraction method based on linear feature enhancement in TM image[J].Acta Geodaetica et Cartographica Sinica, 2014(7):705-710.
[6] Dillabaugh C R, Niemann K O, Richardson D E. Semi-Automated extraction of rivers from digital imagery[J]. GeoInformatica, 2002,6(3):263-284.
doi: 10.1023/A:1019718019825 url:
[7] 王民, 卞琼, 高路. 高分辨率遥感卫星影像的河流提取方法研究[J]. 计算机工程与应用, 2014,50(18):193-196.
[7] Wang M, Bian Q, Gao L. High resolution satellite remote sensing images’ rivers extraction method[J]. Computer Engineering and Application, 2014,50(18):193-196.
[8] Molina R E. River extraction from high resolution satellite images [C]// International Congress on Image & Signal Processing.IEEE, 2012: 697-700.
[9] Sghaier M O, Foucher S, Lepage R. River extraction from high-resolution SAR images combining a structural feature set and mathematical morphology[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017,10(3):1025-1038.
[10] Huang X, Zhang L, Li P. Classification and extraction of spatial features in urban areas using high-resolution multispectral imagery[J]. IEEE Geoscience & Remote Sensing Letters, 2007,4(2):260-264.
[11] He X, Wu Y. Texture feature extraction method combining nonsubsampled contour transformation with gray level co-occurrence matrix[J]. Journal of Multimedia, 2013,8(6):675-684.
[12] Sghaier M O, Foucher S, Lepage R, et al. A multiscale based approach for river extraction from SAR images using attribute filters [C]// International Geoscience and Remote Sensing Symposium(IGARSS 2018).IEEE, 2018: 9245-9248.
[13] Jameson J. Extraction of arbitrary text in natural scene image based on stroke width transform [C]// 14th International Conference on Intelligent Systems Design and Applications(ISDA 2014).IEEE, 2014: 124-128.
[14] 张国和, 黄凯, 张斌, 等. 最大稳定极值区域与笔画宽度变换的自然场景文本提取方法[J]. 西安交通大学学报, 2017,51(1):135-140.
[14] Zhang G H, Huang K, Zhang B, et al. A natural scene text extration method based on the maximum stable extremal region and stroke width transform[J]. Journal of Xi’an Jiaotong University, 2017,51(1):135-140.
[15] Epshtein B, Ofek E, Wexler Y. Detecting text in natural scenes with stroke width transform [C]// Computer Society Conference on Computer Vision and Pattern Recognition(CVPR 2010).IEEE, 2010: 2963-2970.
[16] 童庆禧, 张兵, 郑兰芬. 高光谱遥感:原理、技术与应用[M]. 北京: 高等教育出版社, 2006: 26.
[16] Tong Q X, Zhang B, Zhang L F. Hyperspectral remote sensing:Theory,technology and applications[M]. Beijing: Higher Education Press, 2006: 26.
[17] 张仁华. 定量热红外遥感模型及地面实验基础[M]. 北京: 科学出版社, 2009: 74-76.
[17] Zhang R H. Quantitative thermal infrared remote sensing model and ground experimental basis[M]. Beijing: Science Press, 2009: 74-76.
[18] Sghaier M O, Hammami I, Foucher S, et al. Stroke width transform for linear structure detection:Application to river and road extraction from high-resolution satellite images [C]// International Conference Image Analysis and Recognition(ICIAR 2017), 2017: 605-613.
[19] Canny J. A computational approach to edge detection[M]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986,8(6):679-698.
[20] Dillencourt M B, Samet H, Tamminen M. A general approach to connected-component labeling for arbitrary image representations[J]. Journal of the ACM, 1992,39(2):253-280.
[21] Geling G, Ionescu D. An edge detection operator for SAR images [C]// Conference on Electrical & Computer Engineering.IEEE, 1993: 707-709.
[22] 张蕾.红外图像中铁轨识别技术的研究[D].成都:电子科技大学, 2012.
[22] Zhang L. The research on identification of rail from infrared image[D]. Chengdu:University of Electronic Science and Technology of China, 2012.
[23] Hu J, Razdan A, Femiani J C, et al. Road Network Extraction and Intersection Detection From Aerial Images by Tracking Road Footprints[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007,45(12):4144-4157.
doi: 10.1109/TGRS.2007.906107 url:
[1] WANG Rong, ZHAO Hongli, JIANG Yunzhong, HE Yi, DUAN Hao. Application and analyses of texture features based on GF-1 WFV images in monthly information extraction of crops[J]. Remote Sensing for Natural Resources, 2021, 33(3): 72-79.
[2] LI Xusheng, LIU Yufeng, CHEN Donghua, LIU Saisai, LI Hu. Cloud detection based on support vector machine with image features for GF-1 data[J]. Remote Sensing for Land & Resources, 2020, 32(3): 55-62.
[3] Yizhe WANG, Guo LIU, Li GUO, Shihu ZHAO, Xueli ZHANG. Research on ortho-rectification and true color synthesis technique of GF-1 WFV data in China-Pakistan Economic Corridor[J]. Remote Sensing for Land & Resources, 2020, 32(2): 213-218.
[4] Ning WANG, Jiahua CHENG, Hanye ZHANG, Hongjie CAO, Jun LIU. Application of U-net model to water extraction with high resolution remote sensing data[J]. Remote Sensing for Land & Resources, 2020, 32(1): 35-42.
[5] Hui YUAN, Qiming QIN, Yuanheng SUN. Validation of LAI retrieval results of winter wheat in Yancheng, Luohe area of Henan Province[J]. Remote Sensing for Land & Resources, 2020, 32(1): 162-168.
[6] Jida PENG, Chungui ZHANG. Remote sensing monitoring of vegetation coverage by GF-1 satellite: A case study in Xiamen City[J]. Remote Sensing for Land & Resources, 2019, 31(4): 137-142.
[7] Xiaotong LI, Xianlin QIN, Shuchao LIU, Guifen SUN, Qian LIU. Estimation of forest leaf area index based on GF-1 WFV data[J]. Remote Sensing for Land & Resources, 2019, 31(3): 80-86.
[8] Chen GAO, Jian XU, Dan GAO, Lili WANG, Yeqiao WANG. Retrieval of concentration of total suspended matter from GF-1 satellite and field measured spectral data during flood period in Poyang Lake[J]. Remote Sensing for Land & Resources, 2019, 31(1): 101-109.
[9] Yilin JIA, Wen ZHANG, Lingkui MENG. A study of selection method of NDWI segmentation threshold for GF-1 image[J]. Remote Sensing for Land & Resources, 2019, 31(1): 95-100.
[10] Guifen SUN, Xianlin QIN, Shuchao LIU, Xiaotong LI, Xiaozhong CHEN, Xiangqing ZHONG. Potential analysis of typical vegetation index for identifying burned area[J]. Remote Sensing for Land & Resources, 2019, 31(1): 204-211.
[11] Jian LIAO, Xingfa GU, Yulin ZHAN, Yazhou ZHANG, Xinyu REN, Shuaiyi SHI. A method based on harmonic model for generating synthetic GF-1 images[J]. Remote Sensing for Land & Resources, 2018, 30(3): 106-112.
[12] Ruijun WANG, Bokun YAN, Mingsong LI, Shuangfa DONG, Yongbin SUN, Bing WANG. Remote sensing interpretation of important ore-controlling geological units in Hongshan Region of Gansu Province using GF-1 image and its application[J]. Remote Sensing for Land & Resources, 2018, 30(2): 162-170.
[13] Lingyu YIN, Xianlin QIN, Guifen SUN, Shuchao LIU, Xiaofeng ZU, Xiaozhong CHEN. The method for detecting forest cover change in GF-1images by using KPCA[J]. Remote Sensing for Land & Resources, 2018, 30(1): 95-101.
[14] CHENG Yang, TANG Jiansheng, SU Chuntian, YANG Yang, LUO Fei. Application of the GF-1 data to karst hydrogeological survey[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(s1): 58-66.
[15] ZHANG Ce, JIE Wenhui, FU Lihua, WEI Benzan. Remote sensing image and distribution characteristics of landslide disasters in Xinyuan County, Xinjiang[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(s1): 81-84.
Full text



Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech