Building outline vectorization from high spatial resolution imagery

Jinyan SUN; Zuoji HUANG; Shaoguang ZHOU; Nan XU; Haiming QIAN; Chunlin WANG

doi:10.11834/jrs.20176127

Views : 0 下载量: 101 CSCD: 12 更多指标

PDF
Export
Share
Collection
Album

Building outline vectorization from high spatial resolution imagery
Vol. 21, Issue 3, Pages: 396-405(2017)
Published： 2017-5 ，

Accepted： 11 January 2017
DOI： 10.11834/jrs.20176127

扫描看全文

Jinyan SUN, Zuoji HUANG, Shaoguang ZHOU, et al. Building outline vectorization from high spatial resolution imagery. [J]. Journal of Remote Sensing 21(3):396-405(2017)
DOI：

Jinyan SUN, Zuoji HUANG, Shaoguang ZHOU, et al. Building outline vectorization from high spatial resolution imagery. [J]. Journal of Remote Sensing 21(3):396-405(2017) DOI： 10.11834/jrs.20176127.

摘要

针对高分辨率遥感影像的特点，提出了基于多类分割与模板匹配的建筑物轮廓矢量化方法：首先对影像进行多尺度SVM分割获取建筑物候选点；然后在Radon变换结合主轴分析获取建筑物主方向的基础上，引入多类分割思想，构建用于分割的能量函数，基于α-扩展算法解算能量函数，将轮廓线分割为3类边缘线段；接着构建形状先验的边缘模板，进行精确定位以获取边缘线的实际位置，去除锯齿状变形，降低提取结果的影响；最后相邻边缘线相正交得到拐角点，依次连接每一个拐角点，得到规则化的建筑物轮廓。相比于同类其他方法，此方法考虑了边缘点的方向信息和相邻边缘点趋于同一类的先验知识，可得到近似全局最优的边缘线段分割结果，避免了规则化过程中选择初始点和处理顺序的麻烦和不利影响，同时充分利用了影像特征，对边缘线段进行精确定位，减弱建筑物提取结果误差的影响。对不同影像的实验结果证明此方法可得到规则化的建筑物外轮廓线，不考虑提取过程中遗漏的建筑物，矢量化结果平均准确度为89%、完整度98%、几何形状相似性87%、整体质量85%。

Abstract

The extraction of building outlines from high spatial resolution imagery is a key element of numerous geospatial applications and has been addressed by various approaches. However

the final extraction results are always irregular or inaccurate owing to the boundary regularization algorithm and variability of building shape. This paper proposes a new method for the regularization and vectorization of two dimensional building outlines from high spatial resolution imagery. To accomplish this task

we utilize image segmentation to detect the two main orientations (

and

+90°) of the building blobs. To effectively refine boundaries

we then divide the boundary points

which were obtained clockwise

into the first principal

second principal

and unknown orientation classes. Then

we use least square template matching to precisely position the edge to reduce accuracy loss. Finally

the building outlines are generated by connecting the corner points with intersecting adjacent lines. In addition to the omission buildings

experimental results confirm the ability of the presented system to effectively and steadily extract building outlines with an overall average correctness of 89%

completeness of 98%

shape accuracy of 87%

and quality of 85%. This method can be widely used in various applications. Specifically

our method can work with a relatively low-accuracy image segmentation. Therefore

it can be applied for the vector quantization of large-area building outlines. However

our method only focuses on building outlines and does not consider the internal structure of the building. In the future

more attention should be givento solve this issue.

关键词

遥感影像建筑物矢量化建筑物外轮廓α-扩展模板匹配规则化

Keywords

remote sensing imagebuilding vectorizationbuilding outlineα-expansiontemplate matchingregularization

references

Boykov Y, Veksler O and Zabih R. 2001. Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(11): 1222–1239

Boykov Y and Kolmogorov V. 2004. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(9): 1124–1137

Chaudhuri D and Samal A. 2007. A simple method for fitting of bounding rectangle to closed regions. Pattern Recognition, 40(7): 1981–1989

Cote M and Saeedi P. 2013. Automatic rooftop extraction in nadir aerial imagery of suburban regions using corners and variational level set evolution. IEEE Transactions on Geoscience and Remote Sensing, 51(1): 313–328

Dutter M. 2007. Generalization of building footprints derived from high resolution remote sensing data. Pennsylvania State:The Pennsylvania State University CiteSeerX Archives

Gruen A and Agouris P. 1994. Linear feature extraction by least squares template matching constrained by internal shape forces//Proceedings of SPIE 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision. Munich, Federal Republic of Germany: SPIE:316[DOI: 10.1117/12.182860]

Hu X Y, Zhang Z X and Li J. 2009. Linear feature extraction using adaptive least-squares template matching and a scalable slope edge model. International Journal of Remote Sensing, 30(13): 3393–3407

Li Z B, Liu Z Z and Shi W Z. 2014. A fast level set algorithm for building roof recognition from high spatial resolution panchromatic images. IEEE Geoscience and Remote Sensing Letters, 11(4): 743–747

陆见微. 2006. 高分辨率遥感图像中建筑物外形自动提取方法研究. 北京: 中国科学院研究生院

Lu J W. 2006. A Study of Building Extraction from High Resolution Remote Sensing Images.Beijing: University of Chinese Academy of Sciences

Maas H G and Vosselman G. 1999. Two algorithms for extracting building models from raw laser altimetry data. ISPRS Journal of Photogrammetry and Remote Sensing, 54(2/3): 153–163

孟亚宾. 2007. 高分辨率卫星影像建筑物轮廓提取方法研究. 阜新: 辽宁工程技术大学

Meng Y B. 2007. Study on the building contour extraction from high resolution satellite image. Fuxin: Liaoning Technical University

OkAO. 2013. Automated detection of buildings from single VHR multispectral images using shadow information and graph cuts. ISPRS Journal of Photogrammetry and Remote Sensing, 86:21–40

Rau J Y and Chen L C. 2003. Fast straight lines detection using Hough transform with principal axis analysis. Journal of Photogrammetry and Remote Sensing, 8(1): 15–34

Sampath A and Shan J. 2007. Building boundary tracing and regularization from airborne lidar point clouds. Photogrammetric Engineering and Remote Sensing, 73(7): 805–812

沈蔚, 李京, 陈云浩, 邓磊, 彭光雄. 2008. 基于LIDAR数据的建筑轮廓线提取及规则化算法研究. 遥感学报, 12(5): 692–698

Shen W, Li J, Chen Y H, Deng L and Peng G X. 2008. Algorithms study of building boundary extraction and normalization based on lidar data. Journal of Remote Sensing, 12(5): 692–698

吴秀芸. 2011. 基于高分辨率遥感影像的建筑物提取及轮廓矢量化研究. 南京: 南京大学

Wu X Y. 2011. Research on Extraction and Contour Vectorizationof Buildings from High-Resolution Remote Sensed Images. Nanjing: Nanjing University

杨化超, 邓喀中, 张书毕. 2006. 基于Hough变换的航空影像建筑物半自动提取. 测绘科学, 31(6): 93–94, 97

Yang H C, Deng K Z and Zhang S B. 2006. Semi-automated extraction from aerial image using improved Hough transformation. Science of Surveying and Mapping, 31(6): 93–94, 97

Zeng C Q, Wang J F and Lehrbass B. 2013. An evaluation system for building footprint extraction from remotely sensed data. IEEE Journal ofSelected Topics in Applied Earth Observations and Remote Sensing, 6(3): 1640–1652

Zhang K, Yan J and Chen S C. 2006. Automatic construction of building footprints from airborne LIDAR data. IEEE Transactions on Geoscience and Remote Sensing, 44(9): 2523–2533

周绍光, 孙金彦, 凡莉, 向晶, 陈超. 2015. 高分辨率遥感影像的建筑物轮廓信息提取方法. 国土资源遥感, 27(3): 52–58

Zhou S G, Sun J Y, Fan L, Xiang J and Chen C. 2015. Extraction of building contour from high resolution images. Remote Sensing for Land and Resources, 27(3): 52–58

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

Review of deep learning in optical and SAR image fusion

Extracting glacier information from remote sensing imageries by automatic threshold method of Gaussian mixture model

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

Scene classification of remote sensing image using ensemble convolutional neural network