首页 > 论文 > 激光与光电子学进展 > 55卷 > 4期(pp:42803--1)

融合光谱特征和几何特征的建筑物提取算法

Building Extraction Algorithm by Fusing Spectral and Geometrical Features

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

摘要

机载LiDAR点云系统由于获取三维立体信息方便、快捷, 已被广泛应用到城区目标的提取与识别中, 但LiDAR点云数据缺乏光谱特征, 对建筑物提取识别时常在植被茂密的树冠处出现错检现象。针对这一问题, 提出了融合航空影像光谱特征与LiDAR点云几何特征的建筑物提取算法。通过LiDAR点云数据与航空影像数据的配准, 实现了点云数据光谱信息的提取; 通过改进传统的张量投票机制, 融合光谱特征与空间几何特征形成了新的融合分类特征; 运用随机森林算法实现了建筑物点的提取。仿真实验基于ISPRS提供的测试数据集进行, 通过对比融合光谱特征前后的实验结果可知, 所提算法的精度明显提高, 提取质量达到94.26%, 证明了融合光谱特征对于建筑物提取精度提升的重要作用。

Abstract

Airborne LiDAR systems are widely used in urban objects extraction and recognition because of the advantages in obtaining 3D information conveniently and rapidly. However, it considers geometrical features regardless of buildings and vegetation spectral features and error rate is high in the dense canopy. Aiming at this problem, an algorithm of building extraction by fusing spectral features in aerial images and geometrical features in LiDAR data is proposed. Firstly, the spectrum information can be obtained by registering with LiDAR data. Then, the new feature which fuses spectral and geometrical information is formed by improved tensor voting. Finally, building extraction is achieved by random forests algorithm. Simulation test datasets are provided by ISPRS. Through the comparison of results before and after fusing spectral features, the accuracy of the proposed algorithm is obviously high and the extraction quality of proposed algorithm reaches to 94.26%. The simulation results prove the importance of fusing spectral features in building extraction.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP751

DOI:10.3788/lop55.042803

所属栏目:遥感与传感器

基金项目:国家自然科学基金(41601436)、陕西省自然科学基金(2015JM6346)

收稿日期:2017-10-09

修改稿日期:2017-11-06

网络出版日期:--

作者单位    点击查看

何曼芸:空军工程大学信息与导航学院, 陕西 西安 710077
程英蕾:空军工程大学信息与导航学院, 陕西 西安 710077
廖湘江:294816部队, 福建 福州 350002
赵中阳:空军工程大学信息与导航学院, 陕西 西安 710077

联系人作者:程英蕾(ylcheng718@163.com)

备注:何曼芸(1993—), 女, 硕士研究生, 主要从事机载LiDAR数据处理方面的研究。myhe93@163.com

【1】Hui Z Y, Hu Y J. Review on morphological filtering algorithms based on LiDAR digital elevation model construction[J]. Laser & Optoelectronics Progress, 2016, 53(8): 080001.
惠振阳, 胡友健. 基于LiDAR数字高程模型构建的数学形态学滤波方法综述[J]. 激光与光电子学进展, 2016, 53(8): 080001.

【2】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.

【3】Mordohai P, Medioni G. Tensor voting: A perceptual organization approach to computer vision and machine learning[C]. Synthesis Lectures on Image Video & Multimedia Processing, 2006, 2(1): 1-136.

【4】Lin H B, Shao Y C, Wang W. The 2D analytical tensor voting algorithm[J]. Acta Automatica Sinica, 2016, 42(3): 472-480.
林洪彬, 邵艳川, 王伟. 二维解析张量投票算法研究[J]. 自动化学报, 2016, 42(3): 472-480.

【5】Yang W, Wan Y C, He P P. Automated detection of building region from airborne LiDAR data based on tensor voting[J]. Science of Surveying and Mapping, 2016, 41(9): 7-10.
杨威, 万幼川, 何培培. 张量投票的机载LiDAR数据建筑物自动提取[J]. 测绘科学, 2016, 41(9): 7-10.

【6】Zhan Q M, Liang Y B, Wei C, et al. Ground object recognitions using combined high resolution airborne images and DSM[C]. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012, XXXIX-B3: 573-577.

【7】Zeng N H, Yue Y C, Huang C. Fusion of airborne LiDAR and aerial DOM for road extraction[J]. Science of Surveying and Mapping, 2016, 41(5): 96-99
曾妮红, 岳迎春, 黄迟. 融合机载雷达和航空正射影像的道路提取[J]. 测绘科学, 2016, 41(5): 96-99

【8】Cheng X J, Cheng X L, Hu M J, et al. Building 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】Rottensteiner F, Sohn G, Jung J, et al. The ISPRS benchmark on urban object classification and 3D building reconstruction[C]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012, 1/2/3: 293-298.

【10】Guan H Y. Research on objects classification and simple buildings reconstruction based on digital images and LiDAR[D]. Wuhan: Wuhan University, 2009: 85-86.
管海燕. LiDAR与影像结合的地物分类及房屋重建研究[D]. 武汉: 武汉大学, 2009: 85-86.

【11】Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.

【12】Sun J, Lai Z L. Airborne LiDAR feature selection for urban classification using random forests[J]. Geomatics and Information Science of Wuhan University, 2014, 39(11): 1310-1313.
孙杰, 赖祖龙. 利用随机森林的城区机载LiDAR数据特征选择与分类[J]. 武汉大学学报(信息科学版), 2014, 39(11): 1310-1313.

【13】Li D W, Yang F B, Wang X X. Multisource remote sensing classification based on random forest and adaptive weighted D-S evidence synthesis[J]. Laser & Optoelectronics Progress, 2016, 53(3): 031001.
李大威, 杨风暴, 王肖霞. 基于随机森林与D-S证据合成的多源遥感分类研究[J]. 激光与光电子学进展, 2016, 53(3): 031001.

【14】Yao D J, Yang J, Zhan X J. Feature selection algorithm based on random forest[J]. Journal of Jilin University (Engineering and Technology Edition), 2014, 44(1): 137-141.
姚登举, 杨静, 詹晓娟. 基于随机森林的特征选择算法[J]. 吉林大学学报(工学版), 2014, 44(1): 137-141.

【15】Zhang A W, Xiao T, Duan Y H. A method of adaptive selecting for airborne LiDAR point cloud classification[J]. Laser & Optoelectronics Progress, 2016, 53(8): 082802.
张爱武, 肖涛, 段乙好. 一种机载LiDAR点云分类的自适应特征选择方法[J]. 激光与光电子学进展, 2016, 53(8): 082802.

【16】Rottensteiner F, Sohn G, Gerke M, et al. ISPRS test project on urban classification and 3D building reconstruction[EB/OL]. [2017-09-29]. http://www2.isprs.org/commission/comm3/wg4/tests.html.

【17】Sithole G, Vosselman G. ISPRS test on extracting DEMs from point clouds: A comparison of existing automatic filters[EB/OL]. (2003-08-05) [2017-09-29]. http://www.itc.nl/isprswgIII-3/filtertest/.

【18】Niemeyer J, Rottensteiner F, Soergel U. Conditional random fields for LIDAR point cloud classification in complex urban areas[C]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012, 1(3): 263-268.

引用该论文

He Manyun,Cheng Yinglei,Liao Xiangjiang,Zhao Zhongyang. Building Extraction Algorithm by Fusing Spectral and Geometrical Features[J]. Laser & Optoelectronics Progress, 2018, 55(4): 042803

何曼芸,程英蕾,廖湘江,赵中阳. 融合光谱特征和几何特征的建筑物提取算法[J]. 激光与光电子学进展, 2018, 55(4): 042803

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