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

Jiguang DAI; Yang DU; Xinxin FANG; Yang WANG; Zhipeng MIAO

doi:10.11834/jrs.20188055

Technology and Methodology | Views : 0 下载量: 84 CSCD: 6 更多指标

PDF
Export
Share
Collection
Album

Road extraction method for high resolution optical remote sensing images with multiple feature constraints
Vol. 22, Issue 5, Pages: 777-791(2018)
Published： 2018-9 ，

Accepted： 24 April 2018
DOI： 10.11834/jrs.20188055

扫描看全文

戴激光, 杜阳, 方鑫鑫, 王杨, 苗志鹏. 2018. 多特征约束的高分辨率光学遥感影像道路提取. 遥感学报, 22(5): 777–791

Dai J G, Du Y, Fang X X, Wang Y and Miao Z P. 2018. Road extraction method for high resolution optical remote sensing images with multiple feature constraints. Journal of Remote Sensing, 22(5): 777–791
戴激光, 杜阳, 方鑫鑫, 王杨, 苗志鹏. 2018. 多特征约束的高分辨率光学遥感影像道路提取. 遥感学报, 22(5): 777–791 DOI： 10.11834/jrs.20188055.

Dai J G, Du Y, Fang X X, Wang Y and Miao Z P. 2018. Road extraction method for high resolution optical remote sensing images with multiple feature constraints. Journal of Remote Sensing, 22(5): 777–791 DOI： 10.11834/jrs.20188055.

摘要

针对复杂场景中的遥感影像道路提取问题，论文提出了一种多特征约束的影像道路提取方法，并开展了论文方法可行性论证。该方法首先，根据道路宽度的先验知识以及道路的几何特征，提出一种改进的线段二次提取模型，利用线段长度和道路宽度确定候选道路种子点集；其次，输入道路结构信息，基于道路辐射特征对候选道路种子点进行整体匹配评价；再次，当候选道路种子无法符合辐射特征要求时，提出一种浅色机动车检测模型，以此将浅色机动车结果作为道路上下文特征，利用道路上下文特征对候选道路种子点进行分析；然后，构建道路拓扑分析模型，依据道路拓扑特征对候选道路种子点进行最终验证；最后，对提取道路种子点进行优化处理，并提出道路跟踪及拟合方法。通过不同复杂场景、不同分辨率高分辨率遥感影像下开展的不同方法实验结果对比分析表明，相对于其他商用软件ECognition和Erdas的方法，本方法自动化程度更高，运行效率高，适用于解决道路类型多样化、几何光谱噪声大的复杂场景道路提取问题。

Abstract

Based on the characteristics of road images

a road extraction method for high-resolution optical remote sensing images with multiple feature constraints is proposed in this paper. First

the road image features are analyzed. Second

the feasibility of extracting road images with different feature constraints is determined to emphasize the necessity of building a road feature detection model. This study provides specific methods and steps. First

an improved line segment secondary extraction model is presented based on road geometric characteristics. The model is composed of the aggregation constraint and line segment dynamic fitting. Meanwhile

a candidate road seed set is constructed based on the geometric relationship between the extracted maximum length of 100 lines and known road width. Second

road structure information is inputted. The road radiation characteristics of the candidate road seed set are determined through an entire evaluation

which is based on improved template matching in road value formula

and the overall matching step concrete is identified. Third

when the candidate road seed set cannot meet the requirements of radiation characteristics

road context features are used to evaluate the seeds. Therefore

a light vehicle detection model that includes vehicle image geometric parameter analysis

morphological processing

edge detection

vehicle closed radiation information analysis

and other steps is established. The detection result of light vehicles will be used as the one of the road’s context features. Fourth

the candidate seed points are verified according to the road topological feature. In this process

the road topological analysis model is constructed. The model uses the matching–tracking model and the contextual features to verify the road inspection points. The study proposes an improvement in the matching–tracking model and matching measure. Fifth

in road post-processing

the seed points of the extraction road are optimized

the false road seed points and the low precision road seed points are eliminated

and the road line fitting optimization method is proposed. This work starts by experimenting the secondary extraction method of the high-resolution remote sensing line segment. Results show that the secondary extraction line segment is relatively complete and that defining the geometric features of the road is easy. Then

an experiment of light vehicle extraction is performed by using the remotely sensed image to verify the feasibility of the proposed method. Furthermore

the results can be used to reflect motor vehicle road context characteristics. Different experiments are performed in different scenes and resolutions of high-resolution remote sensing images. In comparison with the mature software ERDAS and ECognition

the experimental results show that this method is relatively automated

efficient

and considerably suitable in performing road extraction in complex scenes with diversified road types and geometrical spectral noise.

关键词

信息提取道路种子点多特征约束道路提取高分辨率光学

Keywords

information extractionroad seed pointmultiple featureconstraintroad extractionhigh resolutionoptical

references

Akinlar C and Topal C. 2011. EDLines: a real-time line segment detector with a false detection control. Pattern Recognition Letters, 32(13): 1633–1642

Alshehhi R and Marpu P R. 2017. Hierarchical graph-based segmentation for extracting road networks from high-resolution satellite images. ISPRS Journal of Photogrammetry and Remote Sensing, 126: 245–260

曹帆之, 徐杨斌, 朱宝山, 李润生. 2015. 利用动态规划半自动提取高分辨率遥感影像道路中心线. 测绘科学技术学报, 32(6): 615–618, 625

Cao F Z, Xu Y B, Zhu B S and Li R S. 2015. Semi-automatic road centerline extraction from high-resolution remote sensing by image utilizing dynamic programming. Journal of Geomatics Science and Technology, 32(6): 615–618, 625 (

曹帆之, 朱述龙, 朱宝山, 李润生, 孟伟灿. 2016. 均值漂移与卡尔曼滤波相结合的遥感影像道路中心线追踪算法. 测绘学报, 45(2): 205–212

Cao F Z, Zhu S L, Zhu B S, Li R S and Meng W C. 2016. Tracking road centerlines from remotely sensed imagery using mean shift and Kalman filtering. Acta Geodaetica et Cartographica Sinica, 45(2): 205–212 (

曹天扬, 申莉. 2015. 应用光照模型的交通车辆识别定位的高分辨率遥感方法. 测绘学报, 44(1): 39–45

Cao T Y and Shen L. 2015. High resolution RS image processing method for vehicles recognition and location according to the illumination model. Acta Geodaetica et Cartographica Sinica, 44(1): 39–45 (

戴激光, 张力, 李晋威, 方鑫鑫. 2017a. 一种链码跟踪与相位验证相结合的直线提取方法. 测绘学报, 46(2): 218–227

Dai J G, Zhang L, Li J W and Fang X X. 2017a. A line extraction method for chain code tracking with phase verification. Acta Geodaetica et Cartographica Sinica, 46(2): 218–227 (

戴激光, 张力, 朱恩泽, 廖健驰, 方鑫鑫, 李晋威. 2017b. 遥感影像主特征线检测. 遥感学报, 21(2): 228–238

Dai J G, Zhang L, Zhu E Z, Liao J C, Fang X X and Li J W. 2017b. Principal line detection in remote sensing image. Journal of Remote Sensing, 21(2): 228–238 (

Fu G, Zhao H R, Li C and Shi L M. 2013. Road detection from optical remote sensing imagery using circular projection matching and tracking strategy. Journal of the Indian Society of Remote Sensing, 41(4): 819–831

傅罡, 赵红蕊, 李聪, 石丽梅. 2014. 曲折道路遥感影像圆投影匹配改进追踪法. 测绘学报, 43(7): 724–730

Fu G, Zhao H R, Li C and Shi L M. 2014. A method by improved circular projection matching of tracking twisty road from remote sensing imagery. Acta Geodaetica et Cartographica Sinica, 43(7): 724–730 (

Kumar M, Singh R K, Raju P L N and Krishnamurthy Y V N. 2014. Road network extraction from high resolution multispectral satellite imagery based on object oriented techniques. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, II-8: 107–110

Leitloff J, Hinz S and Stilla U. 2010. Vehicle detection in very high resolution satellite images of city areas. IEEE Transactions on Geoscience and Remote Sensing, 48(7): 2795–2806

李华胜, 黄平平, 苏莹. 2015. 一种提取遥感影像中道路信息的方法. 国土资源遥感, 27(2): 56–62

Li H S, Huang P P and Su Y. 2015. A method for road extraction from remote sensing imagery. Remote Sensing for Land and Resources, 27(2): 56–62 (

Nakaguro Y, Makhanov S S and Dailey M N. 2011. Numerical experiments with cooperating multiple quadratic snakes for road extraction. International Journal of Geographical Information Science, 25(5): 765–783

Pudaruth S. 2016. Extraction of roads from remotely sensed images using a multi-angled template matching technique//Proceedings of the 3rd International Symposium on Computer Vision and the Internet. Jaipur, India: ACM: 21–29 [DOI: 10.1145/2983402.2983412]

Rajeswari M, Gurumurthy K S, Omkar S N, Senthilnath J and Reddy L P. 2011. Automatic road extraction using high resolution satellite images based on level set and mean shift methods//Proceedings of the 3rd International Conference on Electronics Computer Technology (ICECT). Kanyakumari, India: IEEE: 424–428 [DOI: 10.1109/ICECTECH.2011.5941731]

Raziq A, Xu A G and Li Y. 2016. Automatic extraction of urban road centerlines from high-resolution satellite imagery using automatic thresholding and morphological operation method. Journal of Geographic Information System, 8(4): 517–525

Sarkar S. 2003. An introduction to perceptual organization//Proceedings of 2003 International Conference on Integration of Knowledge Intensive Multi-Agent Systems. Cambridge: IEEE: 330–335 [DOI: 10.1109/KIMAS.2003.1245066]

Sengupta S K, Lopez A S, Brase J M and Paglieroni D W. 2004. Phase-based road detection in multi-source images//Proceedings of 2004 IEEE International Geoscience and Remote Sensing Symposium. Anchorage, AK: IEEE, 6: 3833–3836 [DOI: 10.1109/IGARSS.2004.1369959]

Steger C, Glock C, Eckstein W, Mayer H and Radig B. 1995. Model-based road extraction from images//Gruen A, Kuebler O and Agouris P. Automatic Extraction of Man-Made Objects from Aerial and Space Images. Basel: Birkhäuser: 275–284 [DOI: 10.1007/978-3-0348-9242-1_26]

谭仁龙, 万幼川, 袁芳, 李刚. 2014. 基于圆形模板的高分辨率遥感影像道路半自动提取. 测绘通报(10): 63–66

Tan R L, Wan Y C, Yuan F and Li G. 2014. Semi-automatic road extraction of high resolution remote sensing images based on circular template. Bulletin of Surveying and Mapping(10): 63–66 (

von Gioi R G, Jakubowicz J, Morel J M and Randall G. 2010. LSD: a fast line segment detector with a false detection control. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(4): 722–732

Vosselman G and de Knecht J. 1995. Road tracing by profile matching and kaiman filtering//Gruen A, Kuebler O, Agouris P. Automatic Extraction of Man-made Objects from Aerial and Space Images. Basel: Birkhäuser: 265–274

王峰萍, 王卫星, 薛柏玉, 曹霆, 高婷. 2017. GVF Snake与显著特征相结合的高分辨率遥感图像道路提取. 测绘学报, 46(12): 1978–1985

Wang F P, Wang W X, Xue B Y, Cao T and Gao T. 2017. Road extraction from high-spatial-resolution remote sensing image by combining GVF Snake with salient features. Acta Geodaetica et Cartographica Sinica, 46(12): 1978–1985 (

王理政, 林祥国, 梁勇. 2017. 高分辨率遥感影像主干道路提取的感知编组方法. 测绘科学, 42(7): 127–131

Wang L Z, Lin X G and Liang Y. 2017. Automatic extraction of main roads from high resolution remote sensing imagery based on perceptual organization. Science of Surveying and Mapping, 42(7): 127–131 (

Wiedemann C, Ebner H. 2000. Automatic completion and evaluation of road networks//International Archives of Photogrammetry and Remote Sensing. Amsterdam: International Archives of Photogrammetry and Remote Sensing, 33: 979–986

吴学文, 徐涵秋. 2010. 一种基于水平集方法提取高分辨率遥感影像中主要道路信息的算法. 宇航学报, 31(5): 1495–1502

Wu X W and Xu H Q. 2010. Level set method major roads information extract from high-resolution remote-sensing imagery. Journal of Astronautics, 31(5): 1495–1502 (

Zhang J X, Lin X G, Liu Z J and Shen J. 2011. Semi-automatic road tracking by template matching and distance transformation in urban areas. International Journal of Remote Sensing, 32(23): 8331–8347

Alert me when the article has been cited

提交

MtSCCD： Land-use scene classification and change-detection dataset for deep learning

An algorithm for estimation of surface albedo in 16 m resolution from Chinese GF-1WFV image

Research progress and prospects of hyperspectral remote sensing for global wetland from 2010 to 2022

Verification and analysis of high spatial-temporal resolution vegetation index product based on GF-1 satellite data

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