%0 Journal Article
%T 基于前背景图割的点云分类优化及地物提取<br>Optimized Point Clouds Classification and Objects Extraction Using S-T Graph Cut
%A 左筱涵
%J Geomatics Science and Technology
%P 139-147
%@ 2329-7239
%D 2020
%I Hans Publishing
%R 10.12677/GST.2020.84017
%X 随着激光雷达技术的发展及广泛应用，点云数据的地物分类及场景理解成为了当前的研究热点。由于在机器学习提取局部特征过程中，不可避免地出现过分割或者欠分割的情况，分类结果存在局部误差。针对此现象，研究引入了前背景图割的方法，通过实际的激光扫描点云数据分类实验，得到了精细优化后的分类结果，提高了原来的分类精度并验证了该方法的有效性。<br />
With the development and extensive application of LiDAR technology, the classification of ground objects and scene understanding of point cloud data have become the current research hotspot. Due to over-segmentation or under-segmentation inevitable in the process of machine learning to extract local features, there are local errors in the classification results. Aiming at this phenomenon, the method of cutting the front background image is introduced in the study. Through the actual laser scanning point cloud data classification experiment, the fine optimized classification results are obtained; the original classification accuracy is improved and the effectiveness of the method is verified.
%K LiDAR，点云分类，JointBoost，前背景图割，地物提取<br>LiDAR
%K Point Cloud Classification
%K JointBoost
%K S-T Graph Cut
%K Object Extraction
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=38124