首页 > 论文 > 激光与光电子学进展 > 55卷 > 8期(pp:82803--1)

决策树约束的建筑点云提取方法

Building Point Clouds Extraction from Airborne LiDAR Data Based on Decision Tree Method

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

摘要

作为城市主体,建筑物信息的提取一直是国内外学者研究的热点。针对目前机载激光点云数据量大、建筑点云提取不完整等难题,提出一种面向对象构建决策树的建筑点云高精度提取方法。决策树可以同时处理多种数据属性,并且对缺失值不敏感,利用点云中每个对象属性与对应各个特征值之间的映射关系,结合每个激光脚点与其邻域关系、高程均值等特征,为决策树每个内部节点生成建筑物点的判定条件,然后比较所有分类特征对应的点集不确定性(熵),确定最优特征及最优候选值,有监督地从样本数据中学习得到正确的分类器,进而完成待处理点云中建筑物点的高精度提取。实验结果表明,本文方法能够从机载激光点云数据中有效提取建筑物点,准确率可达96%。

Abstract

As an urban subject, the extraction of buildings has been a hot topic for scholars. Airborne laser scanning data collected in urban areas have a huge data volume and numerous objects with complex and incomplete structures which raise a great challenge for automatic extraction of buildings. To address this challenge, we propose an algorithm based on object-oriented decision tree to extract buildings with high precision. It can handle multiple attributes simultaneously and be unaffected by missed points. First, combined with mean elevation and neighbor within each laser point, judging criteria in each internal node are determined to generate building points by using the relationship between each object attribute and its corresponding eigenvalues. Next, through comparing the entropy from all dataset features, an optimal feature and value candidate are chosen to get a correct classifier with supervised learning to apply to the dataset to be processed. The experimental results show that the proposed method is capable of extracting building points from the airborne laser scanning data with a high accuracy of above 96%.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:P237

DOI:10.3788/lop55.082803

所属栏目:“激光雷达”专题

基金项目:国家重大科学仪器设备开发专项(2013YQ120343)

收稿日期:2018-03-19

修改稿日期:2018-05-02

网络出版日期:2018-05-25

作者单位    点击查看

雷钊:中国科学院遥感与数字地球研究所数字地球重点实验室, 北京 100094中国科学院大学, 北京 100049
习晓环:中国科学院遥感与数字地球研究所数字地球重点实验室, 北京 100094
王成:中国科学院遥感与数字地球研究所数字地球重点实验室, 北京 100094
王濮:中国科学院遥感与数字地球研究所数字地球重点实验室, 北京 100094
王永星:南京大学中国南海协同创新中心, 江苏 南京 210023中国海监南海航空支队, 广东 广州 510310
尹国清:中国海监南海航空支队, 广东 广州 510310

联系人作者:习晓环(xixh@radi.ac.cn); 雷钊(leizhao@radi.ac.cn);

【1】Yang B S, Liang F X, Huang R G. Progress,challenges and perspectives of 3D LiDAR point cloud processing[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10): 1509-1516.
杨必胜, 梁福逊, 黄荣刚. 三维激光扫描点云数据处理研究进展、挑战与趋势[J]. 测绘学报, 2017, 46(10): 1509-1516.

【2】Zhang J X, Lin X G, Liang X L. Advances and prospects of information extraction from point clouds[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10): 1460-1469.
张继贤, 林祥国, 梁欣廉. 点云信息提取研究进展和展望[J]. 测绘学报, 2017, 46(10): 1460-1469.

【3】Sun M L, Li Y S, Chen Q, et al. A filtering method for LiDAR cloud points in urban areas based on serial morphological operators[J]. Journal of Southwest Jiaotong University, 2013, 48(6): 1038-1044.
孙美玲, 李永树, 陈强, 等. 融合序列形态学算子的城区LiDAR滤波方法[J]. 西南交通大学学报, 2013, 48(6): 1038-1044.

【4】Zhang J X, Lin X G. Filtering airborne LiDAR data by embedding smoothness-constrained segmentation in progressive TIN densification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 81: 44-59.

【5】Zhao Z Z, Zhang Y J. Building extraction from airborne laser point cloud using NDVI constrained watershed algorithm[J]. Acta Optica Sinica, 2016, 36(10): 1028002.
赵宗泽, 张永军. 基于植被指数限制分水岭算法的机载激光点云建筑物提取[J]. 光学学报, 2016, 36(10): 1028002.

【6】Huang Z W, Liu F, Hu G W. Improved method for LiDAR point cloud data filtering based on hierarchical pseudo-grid[J]. Acta Optica Sinica, 2017, 37(8): 0828004.
黄作维, 刘峰, 胡光伟. 基于多尺度虚拟格网的LiDAR点云数据滤波改进方法[J]. 光学学报, 2017, 37(8): 0828004.

【7】Yi C, Zhang Y, Wu Q Y, et al. Urban building reconstruction from raw LiDAR point data[J]. Computer-Aided Design, 2017, 93: 1-14.

【8】Cheng X J, Cheng X L, Hu M J, 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.
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.

【9】Awrangjeb M, Fraser S C. Automatic segmentation of raw LiDAR data for extraction of building roofs[J]. Remote Sensing, 2014, 6(5): 3716-3751.

【10】Chehata N, Guo L, Mallet C. Airborne LiDAR feature selection for urban classification using random forest[J]. Laser Scanning, IAPRS, 2009, 38(3): 207-212.

【11】Sun C L, Su W, Wu H G, et al. Improved hierarchical moving curved filtering method of LiDAR data[J]. Infrared and Laser Engineering, 2013, 42(2): 349-354.
孙崇利, 苏伟, 武红敢, 等. 改进的多级移动曲面拟合激光雷达数据滤波方法[J]. 红外与激光工程, 2013, 42(2): 349-354.

【12】Wang F J, Xi X H, Wan Y P, et al. Analysis on digitization and 3D-reconstruction of large building based on terrestrial laser scanning data[J]. Remote Sensing Technology and Application, 2014, 29(1): 144-150.
王方建, 习晓环, 万怡平, 等. 大型建筑物数字化及三维建模关键技术分析[J]. 遥感技术与应用, 2014, 29(1): 144-150.

【13】Ge P, Peng M J. The optimization and application of the decision tree algorithm in the classification prediction[J]. Journal of Shandong Agricultural University (Natural Science Edition), 2016, 47(6): 936-939.
葛朋, 彭梦晶. 决策树算法在分类预测中的应用与优化[J]. 山东农业大学学报(自然科学版), 2016, 47(6): 936-939.

【14】Li L, Wang C, Li S H, et al. Building roof point extraction based on airborne LiDAR data[J]. Journal of University of Chinese Academy of Sciences, 2016, 33(4): 537-541.
李亮, 王成, 李世华, 等. 基于机载LiDAR数据的建筑屋顶点云提取方法[J]. 中国科学院大学学报, 2016, 33(4): 537-541.

引用该论文

Lei Zhao,Xi Xiaohuan,Wang Cheng,Wang Pu,Wang Yongxing,Yin Guoqing. Building Point Clouds Extraction from Airborne LiDAR Data Based on Decision Tree Method[J]. Laser & Optoelectronics Progress, 2018, 55(8): 082803

雷钊,习晓环,王成,王濮,王永星,尹国清. 决策树约束的建筑点云提取方法[J]. 激光与光电子学进展, 2018, 55(8): 082803

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