测绘通报 ›› 2022, Vol. 0 ›› Issue (12): 126-130.doi: 10.13474/j.cnki.11-2246.2022.0368

• 技术交流 • 上一篇    下一篇

一种改进的超体素与区域生长点云分割方法

韩英, 郑文武, 赵莎, 唐欲然   

  1. 衡阳师范学院, 湖南 衡阳 421002
  • 收稿日期:2021-11-15 出版日期:2022-12-25 发布日期:2023-01-05
  • 通讯作者: 郑文武。E-mail:zhwenwu@163.com
  • 作者简介:韩英(1997-),女,硕士生,主要研究方向为GIS技术应用。E-mail:1571210525@qq.com
  • 基金资助:
    湖南省研究生科研创新项目(CX20190985);传统村镇文化数字化保护与创意利用技术国家地方联合工程实验室开放基金项目(CTCZ19K02);湖南省社会科学规划项目(17ZDB052);湖南省研究生科研创新项目(CX20190981);湖南省研究生科研创新项目(CX20211255)

An improved method for segmentation of supervoxel and regional growing point clouds

HAN Ying, ZHENG Wenwu, ZHAO Sha, TANG Yuran   

  1. Hengyang Normal University, Hengyang 421002, China
  • Received:2021-11-15 Online:2022-12-25 Published:2023-01-05

摘要: 点云分割作为识别地理场景的空间特征、探索和记录空间信息的关键处理步骤,其分割精度直接影响后续三维场景重建、地物特征提取等应用的效果。针对传统区域生长点云分割算法的不稳定等问题,本文结合超体素和区域生长算法对点云数据进行分割,并利用点云自身的色彩信息进一步改进分割结果。试验结果表明,相较于传统的区域生长和已有的结合超体素与区域生长的分割算法,本文算法对点云数据分割的效果更好,且其精确率与召回率均有提高。

关键词: 超体素, 区域生长, 色彩信息, 点云分割

Abstract: Point cloud segmentation is a key processing step for identifying spatial features of geographic scenes, exploring and recording spatial information, and its segmentation accuracy directly affects the effects of subsequent 3D scene reconstruction and feature extraction. Aiming at the instability of traditional region-growing point cloud segmentation algorithms, this paper combines supervoxels and region-growing algorithms to segment point cloud data, and uses the color information of the point cloud itself to further improve the segmentation results. The experimental results show that compared to the traditional region growing and existing segmentation algorithms, combining supervoxels and region growing algorithm proposed in this paper has better effect on point cloud data segmentation, and its accuracy and recall rates are both improved.

Key words: supervoxel, region growth, color information, point cloud segmentation

中图分类号: