Automatic road extraction from high-resolution remote sensing images assisted by vector data

Lei DING; Baoming ZHANG; Haitao GUO; Jun LU

doi:10.11834/jrs.20175306

Views : 0 下载量: 918 CSCD: 13

PDF
Export
Share
Collection
Album

Automatic road extraction from high-resolution remote sensing images assisted by vector data
Vol. 21, Issue 1, Pages: 84-95(2017)
Received：08 January 2016，

Published：2017-01
DOI： 10.11834/jrs.20175306
稿件说明：

移动端阅览

DOI：

Lei DING, Baoming ZHANG, Haitao GUO, et al. Automatic road extraction from high-resolution remote sensing images assisted by vector data[J]. Journal of Remote Sensing, 2017, 21(1): 84-95. DOI： 10.11834/jrs.20175306.

摘要

高分辨率遥感影像上细节信息繁杂、干扰物普遍存在，对其进行自动化道路识别与提取的相关研究仍处在探索阶段。在道路提取过程中引入矢量数据辅助，可解决初始信息获取的困难，得到可靠性较强的训练样本。为此，提出一种矢量数据辅助下的道路提取方法，能够筛选出矢量数据中包含的有效信息，引导实现对高分辨率遥感影像的道路自动提取。利用Mean-shift滤波对图像进行预处理后，首先从矢量数据获取候选种子点，并通过提炼同质区域的形状特征剔除错误候选点；然后，自动获取负样本点以进行朴素贝叶斯分类，并采用邻域质心投票算法从分类影像提取道路中心线；最后，结合像素跟踪与方向判断矢量化道路中心线，并提出一种基于矢量几何分析的断线连接与毛刺剔除方法，对提取结果进行信息修复与规整、优化。实验结果显示，该算法的提取质量达到80%以上，且具备较强的稳健性，能够适应具有不同道路辐射和分布特征的高分辨率遥感影像。

Abstract

Considering the existence of both detailed information and interfering objects

research on recognition and extraction of roads from high-resolution remote sensing images remains in the exploration phase. The assistance of vector data during road extraction solves the difficulty of obtaining initial information. Thus

reliable training data can be selected. Therefore

a road extraction method that is supported by vector data is proposed

which effectively provides information that is included in the vector data and extract roads automatically from high-resolution remote sensing images. After the use of the mean shift filter to preprocess images

candidate seed points are acquired from vector data

among which false candidate points are later excluded via shape features of homogeneous areas. Then

negative sample points are selected for the conduct of Bayesian classification. After which

Neighborhood Centroid Voting is adopted to extract road centerlines from classified images. Finally

road centerlines are transformed into vector data by using a method that combines pixel tracking and direction estimation

and a segment linking and burr removing method is proposed based on geometric analysis of vectors. Experiments are conducted on a collection of high-resolution images in which roads have diverse types and distribution features. For an ideal case with clear and continuous roads

the extraction quality is up to 97.35%. For images with occlusions and interferences

the extraction quality stays above 80%

thereby indicating the effectiveness and robustness of the proposed method. A road extraction method that is supported by vector data has been proposed in this study. This method uses the information concluded based on vector data to guide the road extraction process

thus free of manual operation. Experimental results suggest that this method can automatically extract roads from high-resolution remote sensing images with accuracy and robustness

thereby being able to adapt to roads with diverse radiation and distribution features.

关键词

Keywords

references

Arthur D and Vassilvitskii S. 2007. k-means++: the advantages of careful seeding // Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms. Philadelphia, PA, USA: Society for Industrial and Applied Mathematics: 1027–1035

丁磊, 姚红, 郭海涛, 刘志青. 2015. 利用邻域质心投票从分类后影像提取道路中心线. 中国图象图形学报, 20(11): 1526–1534

Ding L, Yao H, Guo H T and Liu Z Q. 2015. Using neighborhood centroid voting to extract road centerline from classifred image. Journal of Image and Graphics, 20(11): 1526–1534

董明, 张海涛, 祝晓坤, 陈春希. 2009. 基于遥感影像的地图道路网数据变化检测研究. 武汉大学学报(信息科学版), 34(2): 178–182

Dong M, Zhang H T, Zhu X K and Chen C X. 2009. Change detection of road networks based on remote sensing image. Geomatics and Information Science of Wuhan University, 34(2): 178–182

段晶. 2011. 朴素贝叶斯分类及其应用研究. 大连: 大连海事大学 Duan J. 2011. Research on Naïve Bayesian Classification and its Application. Dalian: Dalian Maritime University

Guo D H, Weeks A and Klee H. 2004. Segmentations of road area in high resolution images // Proceedings of the 2004 IEEE International Geoscience and Remote Sensing Symposium. Anchorage, AK: IEEE: 3810–3813 [DOI: 10.1109/IGARSS.2004.1369953]

Guo D, Weeks A and Klee H. 2007. Robust approach for suburban road segmentation in high-resolution aerial images. International Journal of Remote Sensing, 28(2): 307–318

冀峰, 高新波, 谢松云. 2012. Mean-shift滤波和直方图增强的图像弱边缘提取. 中国图象图形学报, 17(6): 651–656

Ji F, Gao X B and Xie S Y. 2012. Weak edge detection using Mean-shift filtering and histogram enhancement. Journal of Image and Graphics, 17(6): 651–656

Kumagai J, Zhao H J, Nakagawa M and Shibasaki R. 2001. Road extraction from high-resolution commercial satellite data // Paper presented at the 22nd Asian Conference on Remote Sensing. Singapore: [s.n.]

李光耀, 胡阳. 2008. 高分辨率遥感影像道路提取技术研究与展望. 遥感信息, (1): 91–95

Li G Y and Hu Y. 2008. Road feature extraction from high resolution remote sensing images: review and prospects. Remote Sensing Information, (1): 91–95

刘朋飞. 2010. 基于矢量数据的中低分辨率影像道路提取和变化检测研究. 武汉: 武汉大学 Liu P F. 2010. Research on Road Extraction and Change Detection from Medium or Low Resolution Images with Vector Data. Wuhan: Wuhan University

Maillard P and Cavayas F. 1989. Automatic map-guided extraction of roads from SPOT imagery for cartographic database updating. International Journal of Remote Sensing, 10(11): 1775–1787

Mena J B and Malpica J A. 2005. An automatic method for road extraction in rural and semi-urban areas starting from high resolution satellite imagery. Pattern Recognition Letters, 26(9): 1201–1220

Miao Z L, Shi W Z, Zhang H and Wang X X. 2013. Road centerline extraction from high-resolution imagery based on shape features and multivariate adaptive regression splines. IEEE Geoscience and Remote Sensing Letters, 10(3): 583–587

Sui H G, Li D R and Gong J Y. 2003. Automatic change detection for road networks from images based on GIS. Geo-spatial Information Science, 6(4): 44–50

王国才. 2010. 朴素贝叶斯分类器的研究与应用. 重庆: 重庆交通大学 Wang G C. 2010. Research and Application of Naïve Bayesian Classifier. Chongqing: Chongqing Jiaotong University

王双. 2014. 高分辨率遥感影像道路提取方法研究. 南京: 南京理工大学 Wang S. 2014. Research on Road Extraction from High Resolution Remote Sensing Images. Nanjing: Nanjing University of Science and Technology

王潇晨, 付冬梅, 李晓刚, 刘燕. 2009. 基于meanshift 滤波和蚁群聚类的复杂红外目标分割. 红外技术, 31(9): 545–548

Wang X C, Fu D M, Li X G and Liu Y. 2009. Complex infrared objects segmentation based on mean-shift filtering and ant colony clustering. Infrared Technology, 31(9): 545–548

Wiedemann C, Heipke C, Mayer H and Jamet O. 1998. Empirical evaluation of automatically extracted road axes // Bowyer K W and Jonathon P, eds. Phillips Empirical Evaluation Techniques in Computer Vision. Los Alamitos, CA, USA: Wiley-IEEE Computer Society Press: 172–187

吴晓燕, 车登科, 戴芬. 2010. 影像与矢量结合的道路自动提取及变化检测. 矿山测量, (1): 62–64

Wu X Y, Che D K and Dai F. 2010. Automatic road extraction and change detection based on image and vector. Mine Surveying, (1): 62–64

杨振亚, 王勇, 杨振东, 王成道. 2009. 一种新的RGB色差度量公式. 计算机应用, 29(2): 465–467

Yang Z Y, Wang Y, Yang Z D and Wang C D. 2009. A new color difference formula in RGB color space. Journal of Computer Application, 29(2): 465–467

叶发茂, 苏林, 李树楷, 汤江龙. 2006. 高分辨率遥感影像提取道路的方法综述与思考. 国土资源遥感, 18(1): 12–17

Ye F M, Su L, Li S K and Tang J L. 2006. Review and thought of road extraction from high resolution remote sensing images. Remote Sensing for Land and Resources, 18(1): 12–17

张剑清, 刘朋飞, 王华, 刘永亮. 2010. 利用Meanshift进行道路提取. 武汉大学学报(信息科学版), 35(6): 719–722

Zhang J Q, Liu P F, Wang H and Liu Y L. 2010. Semi-automatic Road Extraction with Meanshift Algorithm. Geomatics and Information Science of Wuhan University, 35(6): 719–722

周丽娟, 王慧, 王文伯, 张宁. 2012. 面向海量数据的并行KMeans算法. 华中科技大学学报(自然科学版), (S1): 150–152

Zhou L J, Wang H, Wang W B and Zhang N. 2012. Parallel KMeans algorithm for massive data. Journal of Huazhong University of Science and Technology (Natural Science Edition), (S1): 150–152

Alert me when the article has been cited

提交

Road extraction method of high-resolution remote sensing image on the basis of the spatial information perception semantic segmentation model

Development and prospect of road extraction method for optical remote sensing image

Automatic sampling of remote sensing image change detection samples based on prior information of vector data

Road extraction method for high resolution optical remote sensing images with multiple feature constraints

SAMSNet： A Remote Sensing Road Extraction Network Integrating Decentralized Attention and Multi-scale Channel Attention