首页 > 论文 > 激光与光电子学进展 > 57卷 > 2期(pp:22801--1)

高分辨率影像分类提取建筑物轮廓的优化方法

Optimization of Building Contours by Classifying High-Resolution Images

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

分类法提取建筑物因易受到错误检测的影响而存在边缘锯齿、形状不规则等问题。提出了一种利用符合建筑物轮廓及轴向的最佳外接矩形和Hausdorff距离综合优化建筑物轮廓的方法。首先利用偏移阴影分割分类方法提取建筑物,对建筑物边界进行多边形拟合;然后用获取拟合结果的最小外接矩形判断建筑物轴向,以选择最佳的外接矩形,并将最佳外接矩形和建筑物轮廓进行逐段等分,计算线段之间的Hausdorff距离,并根据替换规则选择性地用外接矩形边线段进行边界替代,以进一步进行规整优化,最终提高了边缘表达的准确度和提取精度。对多幅遥感影像进行实验,并与其他提取方法进行对比,结果表明:所提方法的总体精度均不同程度地优于参照方法,建筑物边缘的准确性、规整程度及最终精度均得到了有效改善,更真实、准确地反映了建筑物的真实形状。

Abstract

The contours of buildings extracted using the image classification method are commonly irregular and involve serration issues that are primarily caused by incorrect recognition. Therefore, this paper proposes a building contour optimization method that combines Hausdorff distance and a suitable circumscribed rectangle that conforms to the contour and axial direction of buildings. Firstly, initial results of buildings are extracted using the shifted shadow segmentation and classification principle. For each building, a corresponding fitting polygon is acquired by applying a fitting principle to its building edge. Subsequently, the building axis is assessed using the minimum circumscribed rectangle of the building polygon-fitting result. Based on the axis, a suitable circumscribed rectangle is selected. Furthermore, the building contour and its suitable circumscribed rectangle are respectively divided into equal segments. Meanwhile, the Hausdorff distance between two kinds of segmentations is calculated. If the distance satisfies the substitution rules, building contour segments are replaced with circumscribed rectangular edge segmentation to optimize building regularization. Thus, the proposed method helps in improving the accuracy of building boundary and in promoting building extraction precision. It is tested on several remote sensing images. Compared with other building extraction methods, the results show that the overall accuracy of the proposed method is better than that of the other two reference methods. Moreover, the accuracy and regularization of building contours and the overall precision of building extraction results have been effectively improved. As a result, building shape is more accurately reflected.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP753

DOI:10.3788/LOP57.022801

所属栏目:遥感与传感器

基金项目:武汉大学测绘遥感信息工程国家重点实验室开放基金、地理国情监测国家测绘地理信息局重点实验室开放基金、湖北省教育厅科学研究计划;

收稿日期:2019-06-04

修改稿日期:2019-07-05

网络出版日期:2020-01-01

作者单位    点击查看

王双喜:长江大学地球科学学院, 湖北 武汉 430100
杨元维:长江大学地球科学学院, 湖北 武汉 430100武汉大学测绘遥感信息工程国家重点实验室, 湖北 武汉 430079
常京新:长江大学地球科学学院, 湖北 武汉 430100
高贤君:长江大学地球科学学院, 湖北 武汉 430100武汉大学测绘遥感信息工程国家重点实验室, 湖北 武汉 430079

联系人作者:杨元维(yyw_08@163.com)

备注:武汉大学测绘遥感信息工程国家重点实验室开放基金、地理国情监测国家测绘地理信息局重点实验室开放基金、湖北省教育厅科学研究计划;

【1】Wu W, Luo J C, Shen Z F, et al. Building extraction from high resolution remote sensing imagery based on spatial-spectral method [J]. Geomatics and Information Science of Wuhan University. 2012, 37(7): 800-805.
吴炜, 骆剑承, 沈占锋, 等. 光谱和形状特征相结合的高分辨率遥感图像的建筑物提取方法 [J]. 武汉大学学报(信息科学版). 2012, 37(7): 800-805.

【2】Tan Q L. Urban building extraction from VHR multi-spectral images using object-based classification [J]. Acta Geodaetica et Cartographica Sinica. 2010, 39(6): 618-623.
谭衢霖. 高分辨率多光谱影像城区建筑物提取研究 [J]. 测绘学报. 2010, 39(6): 618-623.

【3】Sun J Y, Huang Z J, Zhou S G, et al. Building outline vectorization from high spatial resolution imagery [J]. Journal of Remote Sensing. 2017, 21(3): 396-405.
孙金彦, 黄祚继, 周绍光, 等. 高分辨率遥感影像中建筑物轮廓信息矢量化 [J]. 遥感学报. 2017, 21(3): 396-405.

【4】Simonetto E, Oriot H, Garello R. Rectangular building extraction from stereoscopic airborne radar images [J]. IEEE Transactions on Geoscience and Remote Sensing. 2005, 43(10): 2386-2395.

【5】Turker M, Koc-San D. Building extraction from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping [J]. International Journal of Applied Earth Observation and Geoinformation. 2015, 34: 58-69.

【6】Qiao C, Luo J C, Wu Q Y, et al. Object-oriented method based urban building extraction from high resolution remote sensing image [J]. Geography and Geo-Information Science. 2008, 24(5): 36-39.
乔程, 骆剑承, 吴泉源, 等. 面向对象的高分辨率影像城市建筑物提取 [J]. 地理与地理信息科学. 2008, 24(5): 36-39.

【7】Lin Y Z, Zhang B M, Xu J F, et al. Building extraction from high resolution remote sensing imagery with multi-feature and multi-scale Bulletin of Surveying and Mapping[J]. 0, 2017(12): 53-57.
林雨准, 张保明, 徐俊峰, 等. 多特征多尺度相结合的高分辨率遥感影像建筑物提取 测绘通报[J]. 0, 2017(12): 53-57.

【8】Wang Y G, Ma C X, Liu H P. Building outline information extraction based on mathematical morphology [J]. Remote Sensing for Land & Resources. 2010, 22(1): 49-54.
王永刚, 马彩霞, 刘慧平. 基于数学形态学的建筑物轮廓信息提取 [J]. 国土资源遥感. 2010, 22(1): 49-54.

【9】Lin X G, Zhang J X. Object-based morphological building index for building extraction from high resolution remote sensing imagery [J]. Acta Geodaetica et Cartographica Sinica. 2017, 46(6): 724-733.
林祥国, 张继贤. 面向对象的形态学建筑物指数及其高分辨率遥感影像建筑物提取应用 [J]. 测绘学报. 2017, 46(6): 724-733.

【10】Hu R M, Huang X B, Huang Y C. An enhanced morphological building index for building extraction from high-resolution images [J]. Acta Geodaetica et Cartographica Sinica. 2014, 43(5): 514-520.
胡荣明, 黄小兵, 黄远程. 增强形态学建筑物指数应用于高分辨率遥感影像中建筑物提取 [J]. 测绘学报. 2014, 43(5): 514-520.

【11】Huang B Y, Zuo X Q, Tang L N, et al. A study of extracting building height from IKONOS remote sensing image based on mathematical morphology [J]. Remote Sensing Information. 2014, 29(2): 68-71, 76.
黄贝莹, 左小清, 唐立娜, 等. 基于数学形态学的IKONOS影像提取建筑物高度方法研究 [J]. 遥感信息. 2014, 29(2): 68-71, 76.

【12】Lin X G, Ning X G. Extraction of human settlements from high resolution remote sensing imagery by fusing features of right angle corners and right angle sides [J]. Acta Geodaetica et Cartographica Sinica. 2017, 46(1): 83-89.
林祥国, 宁晓刚. 融合直角点和直角边特征的高分辨率遥感影像居民点提取方法 [J]. 测绘学报. 2017, 46(1): 83-89.

【13】Tao C, Zou Z R, Ding X L. Residential area detection from high-resolution remote sensing imagery using corner distribution [J]. Acta Geodaetica et Cartographica Sinica. 2014, 43(2): 164-169, 192.
陶超, 邹峥嵘, 丁晓利. 利用角点进行高分辨率遥感影像居民地检测方法 [J]. 测绘学报. 2014, 43(2): 164-169, 192.

【14】Wang H L, Wu F, Wang B S, et al. Improved algorithm for extracting skeleton line of polygon based on mathematical morphology [J]. Science of Surveying and Mapping. 2006, 31(1): 29-32, 3.
王辉连, 武芳, 王宝山, 等. 利用数学形态学提取骨架线的改进算法 [J]. 测绘科学. 2006, 31(1): 29-32, 3.

【15】Tao C, Tan Y H, Cai H J, et al. Object-oriented method of hierarchical urban building extraction from high-resolution remote-sensing imagery [J]. Acta Geodaetica et Cartographica Sinica. 2010, 39(1): 39-45.
陶超, 谭毅华, 蔡华杰, 等. 面向对象的高分辨率遥感影像城区建筑物分级提取方法 [J]. 测绘学报. 2010, 39(1): 39-45.

【16】Liu D D, Liu J, Zhang Y J, et al. Research on the extracting buildings from the high spatial resolution images based on the object-oriented and multi-scale method [J]. Geomatics & Spatial Information Technology. 2016, 39(6): 17-20.
刘丹丹, 刘江, 张玉娟, 等. 面向对象的多尺度高分影像建筑物提取方法研究 [J]. 测绘与空间地理信息. 2016, 39(6): 17-20.

【17】Qi Y J, Pei L, Ye G F, et al. Study on building extraction method of high resolution remote sensing image [J]. Geomatics & Spatial Information Technology. 2018, 41(2): 119-123.
齐永菊, 裴亮, 叶国凤, 等. 高分辨率遥感影像建筑物提取方法研究 [J]. 测绘与空间地理信息. 2018, 41(2): 119-123.

【18】Gao X J, Zheng X D, Liu Z X, et al. Automatic building extraction from high resolution visible images based on shifted shadow analysis [J]. Acta Optica Sinica. 2017, 37(4): 0428002.
高贤君, 郑学东, 刘子潇, 等. 基于偏移阴影分析的高分辨率可见光影像建筑物自动提取 [J]. 光学学报. 2017, 37(4): 0428002.

【19】Yang Q S, You Z S, Zhang X Y. Fast multi-face detection algorithm based on Hausdorff distance [J]. Journal of University of Electronic Science and Technology of China. 2004, 33(4): 407-409.
杨清夙, 游志胜, 张先玉. 基于豪斯多夫距离的快速多人脸检测算法 [J]. 电子科技大学学报. 2004, 33(4): 407-409.

引用该论文

Wang Shuangxi,Yang Yuanwei,Chang Jingxin,Gao Xianjun. Optimization of Building Contours by Classifying High-Resolution Images[J]. Laser & Optoelectronics Progress, 2020, 57(2): 022801

王双喜,杨元维,常京新,高贤君. 高分辨率影像分类提取建筑物轮廓的优化方法[J]. 激光与光电子学进展, 2020, 57(2): 022801

被引情况

【1】常京新,王双喜,杨元维,高贤君. 高分遥感影像建筑物轮廓的逐级优化方法. 中国激光, 2020, 47(10): 1010002--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF