臧静,李永强,赵上斌,刘亚坤,杨亚伦

• 1:河南理工大学测绘与国土信息工程学院

摘要(Abstract)：

针对车载激光点云数据中杆状地物分类效果不理想以及单一分类算法具有局限性的问题，该文提出一种基于多重投票方式的改进引导聚集(Bagging)集成学习方法。根据地物点云特征值组成特征向量，利用样本集数据分别对多种机器学习算法进行训练并构建分类模型，获取每个分类器识别能力的先验知识；利用改进的Bagging集成分类算法对识别能力较强且可能存在互补信息的算法进行集成；采用多重投票方法实现杆状地物的自动分类。实验结果表明，该文算法对道路场景中杆状地物的分类精度可达98.58%,高于其他单分类器，对点云自动化分类具有一定的参考。

关键词(KeyWords)： 点云分类;改进Bagging集成;杆状地物;决策树;支持向量机

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41771491)

作者(Author): 臧静,李永强,赵上斌,刘亚坤,杨亚伦

DOI: 10.16251/j.cnki.1009-2307.2022.04.016

参考文献(References)：

• [1] 李德仁.移动测量技术及其应用[J].地理空间信息，2006,4(4):1-5.(LI Deren.Mobile mapping technology and its applications[J].Geospatial Information,2006,4(4):1-5.)
• [2] 杨洲，康志忠，杨俊涛，等.车载点云中杆状地物的形态分析与分类研究[J].测绘科学，2020,45(1):69-76.(YANG Zhou,KANG Zhizhong,YANG Juntao,et al.Research on morphological analysis and classification of pole-like objects from mobile LiDAR point clouds[J].Science of Surveying and Mapping,2020,45(1):69-76.)
• [3] 李海亭，肖建华，李艳红，等.机器学习在车载激光点云分类中的应用研究[J].华中师范大学学报(自然科学版),2015,49(3):460-464.(LI Haiting,XIAO Jianhua,LI Yanhong,et al.Application of machine learning in the vehicle-borne laser point cloud extraction[J].Journal of Central China Normal University (Natural Sciences),2015,49(3):460-464.)
• [4] 李鹏鹏，李永强，赵上斌，等.BP神经网络的道路场景杆状地物自动分类[J].测绘通报，2020(4):101-105.(LI Pengpeng,LI Yongqiang,ZHAO Shangbin,et al.Automatic classification of pole-like objects in road scene by back propagation neural network[J].Bulletin of Surveying and Mapping,2020(4):101-105.)
• [5] 项彬彬.基于深度学习的车载道路场景点云自动分类[D].武汉：武汉大学，2019.(XIANG Binbin.Point clouds classification in road environment based on deep learning[D].Wuhan:Wuhan University,2019.)
• [6] 陈珂.基于CRF模型的车载激光点云分类[D].武汉：武汉大学，2020.(CHEN Ke.Classification of on-board laser point cloud based on CRF model[D].Wuhan:Wuhan University,2020.)
• [7] SAOVANA N,YABUKI N,FUKUDA T.Automated point cloud classification using an image-based instance segmentation for structure from motion[J].Automation in Construction,2021,129:103804.
• [8] 方文，李朝奎，梁继，等.多分类器组合的遥感影像分类方法[J].测绘科学，2016,41(10):120-125.(FANG Wen,LI Chaokui,LIANG Ji,et al.Classification of remote sensing image based on the combination of multiple classifiers[J].Science of Surveying and Mapping,2016,41(10):120-125.)
• [9] 王清.集成学习中若干关键问题的研究[D].上海：复旦大学，2011.(WANG Qing.Research on several key problems of ensemble learning algorithms[D].Shanghai:Fudan University,2011.)
• [10] YANG Wenzhong,YUAN Tingting,WANG Liejun.Micro-blog sentiment classification method based on the personality and bagging algorithm[J].Future Internet,2020,12(4):75.
• [11] 柏延臣，王劲峰.结合多分类器的遥感数据专题分类方法研究[J].遥感学报，2005,9(5):555-563.(BO Yanchen,WANG Jinfeng.Combining multiple classifiers for thematic classification of remotely sensed data[J].Journal of Remote Sensing,2005,9(5):555-563.)
• [12] 薛豆豆，程英蕾，释小松，等.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):192-200.(XUE Doudou,CHENG Yinglei,SHI Xiaosong,et al.Point clouds classification algorithm based on cloth filtering algorithm and improved random forest[J].Laser & Optoelectronics Progress,2020,57(22):192-200.)
• [13] 许良凤，徐小兵，胡敏，等.基于多分类器融合的玉米叶部病害识别[J].农业工程学报，2015,31(14):194-201.(XU Liangfeng,XU Xiaobing,HU Min,et al.Corn leaf disease identification based on multiple classifiers fusion[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(14):194-201.)
• [14] 陈伟宏.基于分类器选择的集成学习算法研究[D].广州：华南理工大学，2020.(CHEN Weihong.Research on classifier-selection-based ensemble learning algorithm[D].Guangzhou:South China University of Technology,2020.)
• [15] 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.
• [16] 张西童，李永强，毛杰，等.车载LiDAR点云相连行道树精细分割[J].测绘科学，2016,41(8):111-115.(ZHANG Xitong,LI Yongqiang,MAO Jie,et al.Segmentation of connected street trees from mobile LiDAR data[J].Science of Surveying and Mapping,2016,41(8):111-115.)
• [17] 杨莎莎，李永强，李框宇，等.基于车载LiDAR数据的单株树提取[J].测绘工程，2014,23(8):23-27.(YANG Shasha,LI Yongqiang,LI Kuangyu,et al.Tree extraction from vehicle-borne LiDAR data[J].Engineering of Surveying and Mapping,2014,23(8):23-27.)
• [18] BREIMAN L.Bagging predictors[J].Machine Learning,1996,24(2):123-140.
• [19] 雷浩川.多分类器集成的遥感影像分类研究[D].北京：中国地质大学(北京),2018.(LEI Haochuan.Classification of remote sensing images with multiple classifier ensembles[D].Beijing:China University of Geosciences (Beijing),2018.)
• [20] 王洪礼，张瑞.基于SVM的内蒙古高新技术开发区创新能力研究[J].科学管理研究，2011,29(5):14-16.(WANG Hongli,ZHANG Rui.Calculating innovation capacity of high-tech development zones in Inner Mongolia intelligently based on SVM[J].Scientific Management Research,2011,29(5):14-16.)