2025年04月07日 星期一 首页   |    期刊介绍   |    编 委 会   |    投稿指南   |    期刊订阅   |    统合信息   |    联系我们
计量学报  2022, Vol. 43 Issue (3): 325-330    DOI: 10.3969/j.issn.1000-1158.2022.03.05
  光学计量 本期目录 | 过刊浏览 | 高级检索 |
融合配准的多站室外大场景激光点云分割
徐鹏,徐方勇,陈辉
上海电力大学 自动化工程学院,上海 200090
Large Scene Segmentation of Outdoor Laser Point Cloud Based on Fusion and Registration
XU Peng,XU Fang-yong,CHEN Hui
College of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China
全文: PDF (4410 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 针对室外场景范围广、分割难度大、识别效果不显著等问题,提出了一种融合多站点云配准的室外大场景分割方法。首先,根据室外场景视野大、点云数据量庞大特点,选取多个视角下重叠区域较多的建筑场景点集,结合SAC-IA和ICP方法进行点云自动配准,从而构建出点云密度相对均匀的室外大场景完整结构;然后,选用公共数据集Semantic3D训练基于PointNet++的室外点云分割模型,并在测试集上验证其算法效果;最终,调用该模型分割已构建的室外点云大场景。实验效果证明:多视角配准的点云场景能够解决点云场景的非均匀采样问题,从而使得基于深度学习的语义分割模型对其有更好的识别效果。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
徐鹏
徐方勇
陈辉
关键词 计量学激光点云场景分割融合配准非均匀采样深度学习PointNet++    
Abstract:Aiming at the problem caused by the sparseness of outdoor laser point cloud scenes for semantic segmentation, a point cloud segmentation method based on deep learning is proposed. First, the laser point cloud scenes collected from five perspectives are processed, and parts of buildings with higher overlapping areas are selected in turn, and each group is registered by SAC-IA and ICP-based point cloud automatic registration methods. In order to construct a large outdoor scene with relatively uniform point cloud density, the public data set Semantic3D is used to train an outdoor point cloud segmentation model based on PointNet++, and the algorithm effect is verified on the test set. Finally, this model is used to segment the outdoor scene that has been constructed scenes and experimental results prove that point cloud scenes with multi-view registration can solve the problem of non-uniform sampling of point cloud scenes, so that the deep segmentation-based semantic segmentation model has a better recognition effect.
Key wordsmetrology    laser point cloud    scene segmentation    fusion    registration    non-uniform sampling    deep learning    PointNet++
收稿日期: 2021-01-14      发布日期: 2022-03-23
PACS:  TB96  
  TB92  
基金资助:国家自然科学基金(51705304);上海市自然科学基金 (20ZR1421300)
通讯作者: 陈辉(1982-),女,辽宁兴城人,上海电力大学副教授,博士,硕士生导师,主要从事机器视觉、图像处理、机器人导航等方面研究。Email: chenhui@shiep.edu.cn     E-mail: chenhui@shiep.edu.cn
作者简介: 徐鹏(1995-),男,湖北孝感人,上海电力大学硕士生,研究方向为点云分割、深度学习等。Email: 260587141@qq.com
引用本文:   
徐鹏,徐方勇,陈辉. 融合配准的多站室外大场景激光点云分割[J]. 计量学报, 2022, 43(3): 325-330.
XU Peng,XU Fang-yong,CHEN Hui. Large Scene Segmentation of Outdoor Laser Point Cloud Based on Fusion and Registration. Acta Metrologica Sinica, 2022, 43(3): 325-330.
链接本文:  
http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2022.03.05     或     http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2022/V43/I3/325
京ICP备:14006989号-1
版权所有 © 《计量学报》编辑部
地址:北三环东路18号(北京1413信箱)  邮编:100029 电话:(010)64271480
本系统由北京玛格泰克科技发展有限公司设计开发  技术支持:support@magtech.com.cn