融合LiDAR点云与正射影像的建筑物图割优化提取方法

doi:10.11947/j.AGCS.2018.20160534

测绘学报 ›› 2018, Vol. 47 ›› Issue (4): 519-527.doi: 10.11947/j.AGCS.2018.20160534

融合LiDAR点云与正射影像的建筑物图割优化提取方法

杜守基¹, 邹峥嵘¹, 张云生¹, 何雪¹, 王竞雪²

1. 中南大学地球科学与信息物理学院, 湖南长沙 410083;
2. 辽宁工程技术大学测绘与地理科学学院, 辽宁阜新 123000

收稿日期:2016-10-25 修回日期:2017-07-12 出版日期:2018-04-20 发布日期:2018-05-02
通讯作者: 张云生 E-mail:zhangys@csu.edu.cn
作者简介:杜守基(1990-),男,工程硕士,研究方向为点云建筑物提取与三维变化检测。E-mail:dsjcug@163.com
基金资助:
国家重点研发计划（2016YFC0803108）；国家自然科学基金（41201472）；卫星测绘技术与应用国家测绘地理信息局重点实验室开放基金（KLSMTA-201505）

A Building Extraction Method via Graph Cuts Algorithm by Fusion of LiDAR Point Cloud and Orthoimage

DU Shouji¹, ZOU Zhengrong¹, ZHANG Yunsheng¹, HE Xue¹, WANG Jingxue²

1. School of Geosciences and Info-Physics, Central South University, Changsha 410083, China;
2. School of Geomatics, Liaoning Technical University, Fuxin 123000, China

Received:2016-10-25 Revised:2017-07-12 Online:2018-04-20 Published:2018-05-02
Supported by:
The National Key Research and Development Program of China(No. 2016YFC0803108);The National Natural Science Foundation of China (No. 41201472);The Open Research Fund of Key Laboratory of Satellite Mapping Technology and Application,National Administration of Surveying,Mapping and Geoinformation (No. KLSMTA-201505)

摘要/Abstract

摘要： 提出一种基于图割算法的建筑物LiDAR点云与正射影像融合提取方法。首先，利用LiDAR点云计算3个几何特征：平整度、法向量分布和高程纹理一致性。同时利用航空正射影像计算颜色特征——归一化植被指数（NDVI）。然后将两类特征联合构建能量函数数据项，综合数字表面模型（DSM）和NDVI构建平滑项，采用图割算法优化得到初始的建筑物区域。最后利用初始建筑物边缘一定范围内的正射影像颜色信息，采用前后景分割的思想进一步优化建筑物边缘。应用ISPRS Vaihingen测试数据进行试验，结果表明本文方法具有较高的建筑物提取精度。

关键词: 建筑物提取, 激光点云, 正射影像, 图割算法, 建筑物边缘优化

Abstract: An automatic building extraction method based on graph cuts algorithm fusing LiDAR point cloud and orthoimage is proposed.Firstly,three geometric features are computed from LiDAR points including flatness,distribution of normal vector and GLCM (grey level co-occurrence matrix) homogeneity of normalized height.NDVI is simultaneously calculated from orthoimage.After that,both kinds of features are combined to construct the data term of energy function,then DSM and NDVI is combined to construct smooth term.Thereafter,graph cuts algorithm is applied to obtain the initial building extraction results.Finally,foreground and background segmentation method is employed to optimize the building boundary based on the orthoimage color information in certain range of the initially detected building boundary.ISPRS Vaihingen dataset is used to evaluate the proposed method.The results reveal that the proposed method can obtain high accuracy of the detection building area.

Key words: building extraction, LiDAR point cloud, orthoimage, graph cuts algorithm, building boundary optimization

中图分类号:

P237

杜守基, 邹峥嵘, 张云生, 何雪, 王竞雪. 融合LiDAR点云与正射影像的建筑物图割优化提取方法[J]. 测绘学报, 2018, 47(4): 519-527.

DU Shouji, ZOU Zhengrong, ZHANG Yunsheng, HE Xue, WANG Jingxue. A Building Extraction Method via Graph Cuts Algorithm by Fusion of LiDAR Point Cloud and Orthoimage[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(4): 519-527.

参考文献

[1] KHOSHELHAM K, NARDINOCCHI C, FRONTONI E, et al. Performance Evaluation of Automated Approaches to Building Detection in Multi-source Aerial Data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2010, 65(1):123-133.
[2] TOMLJENOVIC I, HÖFLE B, TIEDE D, et al. Building Extraction from Airborne Laser Scanning Data:An Analysis of the State of the Art[J]. Remote Sensing, 2015, 7(4):3826-3862.
[3] NIEMEYER J, ROTTENSTEINER F, SOERGEL U. Contextual Classification of LiDAR Data and Building Object Detection in Urban Areas[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 87(2):152-165.
[4] MANNO-KOVACS A, SZIRANYI T. Orientation-selective Building Detection in Aerial Images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 108(1):94-112.
[5] HUANG Xin, ZHANG Liangpei. Morphological Building/Shadow Index for Building Extraction from High-resolution Imagery over Urban Areas[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(1):161-172.
[6] 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. DOI:10.13485/j.cnki.11-2089.2014.0084. HU Rongming, HUANG Xiaobing, HUANG Yuancheng. An Enhanced Morphological Building Index for Building Extraction from High-resolution Images[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(5):514-520. DOI:10.13485/j.cnki.11-2089.2014.0084.
[7] ZHANG Jixian, LIN Xiangguo, NING Xiaogang. SVM-based Classification of Segmented Airborne LiDAR Point Clouds in Urban Areas[J]. Remote Sensing, 2013, 5(8):3749-3775.
[8] 徐文学, 杨必胜, 魏征, 等. 多标记点过程的LiDAR点云数据建筑物和树冠提取[J]. 测绘学报, 2013, 42(1):51-58. XU Wenxue, YANG Bisheng, WEI Zheng, et al. Building and Tree Crown Extraction from LiDAR Point Cloud Data Based on Multi-marked Point Process[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(1):51-58.
[9] 徐文学, 杨必胜, 董震, 等. 标记点过程用于点云建筑物提取[J]. 武汉大学学报(信息科学版), 2014, 39(5):520-525. XU Wenxue, YANG Bisheng, DONG Zhen, et al. Building Extraction from Point Cloud Using Marked Point Process[J]. Geomatics and Information Science of Wuhan University, 2014, 39(5):520-525.
[10] MONGUS D, LUKAČ N, ŽALIK B. Ground and Building Extraction from LiDAR Data Based on Differential Morphological Profiles and Locally Fitted Surfaces[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 93(2):145-156.
[11] 管海燕, 邓非, 张剑清, 等. 面向对象的航空影像与LiDAR数据融合分类[J]. 武汉大学学报(信息科学版), 2009, 34(7):830-833. GUAN Haiyan, DENG Fei, ZHANG Jianqing, et al. Object-based Fusion and Classification of Airborne Laser Scanning Data and Aerial Images[J]. Geomatics and Information Science of Wuhan University, 2009, 34(7):830-833.
[12] 程效军, 程小龙, 胡敏捷, 等. 融合航空影像和LIDAR点云的建筑物探测及轮廓提取[J]. 中国激光, 2016, 43(5):0514002. CHENG Xiaojun, CHENG Xiaolong, HU Minjie, et al. Buildings Detection and Contour Extraction by Fusion of Aerial Images and LiDAR Point Cloud[J]. Chinese Journal of Lasers, 2016, 43(5):0514002.
[13] ZAREA A, MOHAMMADZADEH A. A Novel Building and Tree Detection Method from LiDAR Data and Aerial Images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(5):1864-1875.
[14] 程亮, 龚健雅. LiDAR辅助下利用超高分辨率影像提取建筑物轮廓方法[J]. 测绘学报, 2008, 37(3):391-393, 399. DOI:10.3321/j.issn:1001-1595.2008.03.021. CHENG Liang, GONG Jianya. Building Boundary Extraction Using Very High Resolution Images and LiDAR[J]. Acta Geodaetica et Cartographica Sinica, 2008, 37(3):391-393, 399. DOI:10.3321/j.issn:1001-1595.2008.03.021.
[15] GILANI S A N, AWRANGJEB M, LU Guojun. An Automatic Building Extraction and Regularization Technique Using LiDAR Point Cloud Data and Orthoimage[J]. Remote Sensing, 2016, 8(3):258.
[16] AWRANGJEB M, FRASER C S. Automatic Segmentation of Raw LiDAR Data for Extraction of Building Roofs[J]. Remote Sensing, 2014, 6(5):3716-3751.
[17] BOYKOV Y Y, JOLLY M P. Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images[C]//Proceedings of the 8th International Conference on Computer Vision. Vancouver:IEEE, 2001:105-112.
[18] FERRARI S, FERRIGNO G, PIURI V, et al. Reducing and Filtering Point Clouds with Enhanced Vector Quantization[J]. IEEE Transactions on Neural Networks, 2007, 18(1):161-177.
[19] HU Han, DING Yulin, ZHU Qing, et al. An Adaptive Surface Filter for Airborne Laser Scanning Point Clouds by Means of Regularization and Bending Energy[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 92:98-111.
[20] QIN Rongjun, FANG Wei. A Hierarchical Building Detection Method for Very High Resolution Remotely Sensed Images Combined with DSM Using Graph Cut Optimization[J]. Photogrammetric Engineering & Remote Sensing, 2014, 80(9):873-883.
[21] 帅滔, 张洪艳, 张良培. 面向对象的高分辨遥感影像阴影探测方法[J]. 光子学报, 2015, 44(12):1228002. SHUAI Tao, ZHANG Hongyan, ZHANG Liangpei. The Object-based Method of Shadow Detection in High-resolution Remote Sensing Imagery[J]. Acta Photonica Sinica, 2015, 44(12):1228002.
[22] ZHOU Qianyi, NEUMANN U. Fast and Extensible Building Modeling from Airborne LiDAR Data[C]//Proceedings of the 16th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Irvine:ACM, 2008:1-8.
[23] HARALICK R M, SHANMUGAM K, DINSTEIN I. Textural Features for Image Classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973, SMC-3(6):610-621.
[24] BOYKOV Y, KOLMOGOROV V. An Experimental Comparison of Min-cut/Max-flow Algorithms for Energy Minimization in Vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9):1124-1137.
[25] ROTTENSTEINER F, SOHN G, GERKE M, et al. Results of the ISPRS Benchmark on Urban Object Detection and 3D Building Reconstruction[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 93:256-271.

融合LiDAR点云与正射影像的建筑物图割优化提取方法

A Building Extraction Method via Graph Cuts Algorithm by Fusion of LiDAR Point Cloud and Orthoimage

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	何直蒙, 丁海勇, 安炳琪. 高分辨率遥感影像建筑物提取的空洞卷积E-Unet算法[J]. 测绘学报, 2022, 51(3): 457-467.
[2]	张玉鑫, 颜青松, 邓非. 高分辨率遥感影像建筑物提取多路径RSU网络法[J]. 测绘学报, 2022, 51(1): 135-144.
[3]	方莉娜, 王爽, 赵志远, 付化胜, 陈崇成. 车载激光点云中交通标线自动分类与矢量化[J]. 测绘学报, 2021, 50(9): 1251-1265.
[4]	巩丹超, 韩轶龙, 黄旭. 线特征约束的建筑物密集匹配边缘全局优化方法[J]. 测绘学报, 2021, 50(6): 833-846.
[5]	蒋腾平, 王永君, 张林淇, 梁冲, 孙剑. 融合CNN和MRF的激光点云层次化语义分割方法[J]. 测绘学报, 2021, 50(2): 215-225.
[6]	李彩林, 王志勇, 俞路路, 郭宝云. 最邻近曲面约束的近景光学影像与地面激光点云几何配准[J]. 测绘学报, 2020, 49(8): 1014-1022.
[7]	方莉娜, 卢丽靖, 赵志远, 王昀昀, 陈崇成. 车载激光点云道路边界提取的Snake方法[J]. 测绘学报, 2020, 49(11): 1438-1450.
[8]	方莉娜, 黄志文, 罗海峰, 陈崇成. 车载激光扫描数据中实线型交通标线提取[J]. 测绘学报, 2019, 48(8): 960-974.
[9]	季顺平, 魏世清. 遥感影像建筑物提取的卷积神经元网络与开源数据集方法[J]. 测绘学报, 2019, 48(4): 448-459.
[10]	陈驰, 杨必胜, 田茂, 李健平, 邹响红, 吴唯同, 宋易恒. 车载MMS激光点云与序列全景影像自动配准方法[J]. 测绘学报, 2018, 47(2): 215-224.
[11]	罗海峰, 方莉娜, 陈崇成, 黄志文. 基于DBN的车载激光点云路侧多目标提取[J]. 测绘学报, 2018, 47(2): 234-246.
[12]	何曼芸, 程英蕾, 邱浪波, 赵中阳. 一种改进顶帽变换与LBP高程纹理的城区建筑物提取算法[J]. 测绘学报, 2017, 46(9): 1116-1122.
[13]	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.
[14]	董震, 杨必胜. 车载激光扫描数据中多类目标的层次化提取方法[J]. 测绘学报, 2015, 44(9): 980-987.
[15]	袁修孝, 段梦梦, 曹金山. 正射影像镶嵌线自动搜索的视差图算法[J]. 测绘学报, 2015, 44(8): 877-883.