首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221017--1)

综合布料滤波与改进随机森林的点云分类算法

Point Clouds Classification Algorithm Based on Cloth Filtering Algorithm and Improved Random Forest

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

摘要

城区激光雷达点云建筑物提取技术是近年来发展的热点,如何准确区分植被、建筑物以及人造物,提高分类精度一直是研究难点。为此,针对分类精度较低的问题,提出一种基于随机森林的点云分类算法。首先使用改进布料滤波算法对点云数据进行地面滤波;其次,构建决策树并进行基于最大互信息系数的相关性分析,选出相关系数最小、精度最高的决策树,得到弱相关随机森林模型;最后,对决策结果进行加权投票处理,得到一种综合布料滤波和加权弱相关随机森林的点云分类算法,并通过Vaihingen城区数据集对算法进行验证。实验表明,与传统随机森林分类算法相比,本文算法提高了4.2%的分类精度,也提高了算法效率。

Abstract

Building extraction technology in urban areas has been a hot topic in recent years, but how to accurately distinguish vegetation, buildings, and man-made objects and improve classification accuracy has always been a difficult point. Aiming at the problem of low classification accuracy, we propose a point cloud classification algorithm based on random forest. First, the improved cloth filtering algorithm is used to perform ground filtering on the point cloud data. And a decision tree is constructed and the correlation analysis based on the largest mutual information coefficient is performed to select the decision tree with the smallest correlation coefficient and the highest accuracy to obtain a weakly correlated random forest model. The decision results are processed by weighted voting, and finally a point cloud classification algorithm combining cloth filtering and weighted weakly correlated random forest is obtained. Compared with the traditional random forest classification algorithm, the algorithm is verified by the Vaihingen urban dataset, and the classification accuracy is improved by 4.2%.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:P237

DOI:10.3788/LOP57.221017

所属栏目:图像处理

基金项目:国家自然科学基金;

收稿日期:2020-02-01

修改稿日期:2020-03-06

网络出版日期:2020-11-01

作者单位    点击查看

薛豆豆: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
释小松:空军工程大学信息与导航学院, 陕西 西安 710077
秦先详:空军工程大学信息与导航学院, 陕西 西安 710077
文沛:空军工程大学信息与导航学院, 陕西 西安 71007793575部队, 河北 承德, 067000

联系人作者:薛豆豆(1447551957@qq.com)

备注:国家自然科学基金;

【1】Zeng Q H, Mao J H, Li X H, et al. Application of the hierarchy classification to point cloud of airborne LIDAR [J]. Science of Surveying and Mapping. 2008, 33(1): 103-105, 249.
曾齐红, 毛建华, 李先华, 等. 机载激光雷达点云的阶层式分类 [J]. 测绘科学. 2008, 33(1): 103-105, 249.

【2】Niemeyer J, Mallet C, Rottensteiner F, Remote Sensing, Spatial Information Sciences, et al. XXXVIII- . 2012, 4/W19: 209-214.

【3】Niemeyer J, Rottensteiner F, Soergel U. Classification of urban LiDAR data using conditional random field and random forests[C]//Joint Urban Remote Sensing Event 2013. April 21-23, 2013, Sao Paulo, Brazil. New York: , 2013, 139-142.

【4】Vosselman G. Slope based filtering of laser altimetry data [J]. Remote Sensing. 2000, 33: 935-942.Vosselman G. Slope based filtering of laser altimetry data [J]. Remote Sensing. 2000, 33: 935-942.

【5】Vosselman G. Gorte B G H, Sithole G, et al. Recognising structure in laser scanner point clouds [M]. Thies M, Koch B, Spiecker H, et al, ISPRS 2004 : proceedings of the ISPRS working group VIII/2 : laser scanning for forest and landscape assessment, Freiburg, October 3-6, 2004. Freiburg: University of Freiburg. 2004, 33-38.

【6】Kilian J, Haala N, Englich M. Capture and evaluation of airborne laser scanner data [J]. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences. 1996, 31: 383-388.

【7】Sithole G, Vosselman G. Experimental comparison of filter algorithms for bare-Earth extraction from airborne laser scanning point clouds [J]. ISPRS Journal of Photogrammetry and Remote Sensing. 2004, 59(1/2): 85-101.

【8】Zhang W M, Qi J B, Wan P, et al. An easy-to-use airborne LiDAR data filtering method based on cloth simulation [J]. Remote Sensing. 2016, 8(6): 501.

【9】Meng X L, Wang L, Currit N. Morphology-based building detection from airborne lidar data [J]. Photogrammetric Engineering & Remote Sensing. 2009, 75(4): 437-442.

【10】Mallet C, Bretar F, Roux M, et al. Relevance assessment of full-waveform lidar data for urban area classification [J]. ISPRS Journal of Photogrammetry and Remote Sensing. 2011, 66(6): S71-S84.

【11】Guo L, Chehata N, Mallet C, et al. Relevance of airborne lidar and multispectral image data for urban scene classification using random forests [J]. ISPRS Journal of Photogrammetry and Remote Sensing. 2011, 66(1): 56-66.

【12】Coussement K, van den Poel D. Churn prediction in subscription services: an application of support vector machines while comparing two parameter-selection techniques [J]. Expert Systems with Applications. 2008, 34(1): 313-327.

【13】Battiti R. Using mutual information for selecting features in supervised neural net learning [J]. IEEE Transactions on Neural Networks. 1994, 5(4): 537-550.

【14】Amiri F, Rezaei Yousefi M, Lucas C, et al. Mutual information-based feature selection for intrusion detection systems [J]. Journal of Network and Computer Applications. 2011, 34(4): 1184-1199.

【15】Zhang R, Li G Y, Li M L, et al. Classification of LiDAR point clouds based on PCA-BP algorithm Bulletin of Surveying and Mapping[J]. 0, 2014(7): 23-26.
张蕊, 李广云, 李明磊, 等. 利用PCA-BP算法进行激光点云分类方法研究 测绘通报[J]. 0, 2014(7): 23-26.

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

【17】Mohd Salleh M R, Abd Rahman M Z, Ismail Z, et al. Revised progressive morphological method for ground point classification of airborne lidar data [J]. International Journal of Built Environment and Sustainability. 2019, 6(1/2): 31-38.

【18】Cao Q, Zhong Y F, Ma A L, et al. Urban land use/land cover classification based on feature fusion fusing hyperspectral image and lidar data[C]//IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium. July 22-27, 2018, Valencia, Spain. New York: , 2018, 8869-8872.

【19】García-Sopo M á, Cuartero A, Rodríguez P G, et al. Hyperspectral and lidar data integration and classification[C]//2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). July 26-31, 2015, Milan, Italy. New York: , 2015, 57-60.

引用该论文

Xue Doudou,Cheng Yinglei,Shi Xiaosong,Qin Xianxiang,Wen Pei. Point Clouds Classification Algorithm Based on Cloth Filtering Algorithm and Improved Random Forest[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221017

薛豆豆,程英蕾,释小松,秦先详,文沛. 综合布料滤波与改进随机森林的点云分类算法[J]. 激光与光电子学进展, 2020, 57(22): 221017

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