一种大场景有序点云的快速、准确分割方法

朱晓鑫; 谢翔; 李国林

Chinese

您当前的位置：

首页 >

文章列表页 >

一种大场景有序点云的快速、准确分割方法

更新时间：2026-09-04

- 一种大场景有序点云的快速、准确分割方法
- A Fast and Accurate Segmentation Method for Ordered Point Cloud of Large-Scale Scenes
- 微电子学与计算机 2016年33卷第11期页码：45-49
- 作者机构：
  
  1. 清华大学微电子与纳电子学系,北京,100084
  2. 清华大学电子工程系,北京,100084
- 作者简介：
- 基金信息：
  
  深圳市科技计划 JCYJ20150331151358146清华大学自主科研计划 2013089223
- DOI：
  中图分类号：
- 纸质出版：2016
- 稿件说明：
移动端阅览
朱晓鑫, 谢翔, 李国林. 一种大场景有序点云的快速、准确分割方法[J]. 微电子学与计算机, 2016, 33(11): 45-49.

ZHU Xiao-xin, XIE Xiang, LI Guo-lin. A Fast and Accurate Segmentation Method for Ordered Point Cloud of Large-Scale Scenes[J]. 2016, 33(11): 45-49.
朱晓鑫, 谢翔, 李国林. 一种大场景有序点云的快速、准确分割方法[J]. 微电子学与计算机, 2016, 33(11): 45-49. DOI：

ZHU Xiao-xin, XIE Xiang, LI Guo-lin. A Fast and Accurate Segmentation Method for Ordered Point Cloud of Large-Scale Scenes[J]. 2016, 33(11): 45-49. DOI：

摘要

针对复杂大场景的点云分割问题

提出了一种快速、准确的分割方法.采用基于扫描线的分割算法

利用点云的有序性和地面几何特征提取地面点

在坡路等复杂地面情况下也能正确分割地面; 基于扫描系统的性能确定初始阈值

实现了对非地面点的逐点快速分割; 提出了基于体量的自适应算法对过分割的点云进行合并.实验结果表明

在复杂场景下

该分割方法的准确率在90%以上

并且运算复杂度低

逐点处理速度为平均每个点用时14.5s

可在点云数据采集过程中进行实时处理.

Abstract

A fast and accurate segmentation method for point cloud of large-scale scenes is proposed. A scan-line-based ground filter algorithm is designed based on the ordering of point cloud and the geometrical characteristic of the ground

complex ground conditions such as slopes can be handled. Non-ground points are fast segmented point-by-point based on the initial threshold which takes the performance of the scanning system into consideration. Then over-segmented points are merged through the volume-based adaptive algorithm. The accuracy rate of the proposed method is over 90% and the point-by-point processing speed is 14.5 s per point

real-time processing can be achieved.

关键词

Keywords

references

Rusu R B, Cousins S. 3D is here: point cloud library (pcl)[C]//Robotics and Automation (ICRA), 2011 IEEE International Conference on. China, Shanghai, IEEE, 2011: 1-4.

Rusu R B. Semantic 3D object maps for everyday manipulation in human living environments[J]. KI-Künstliche Intelligenz, 2010, 24(4): 345-348. DOI: 345

Chen J, Chen B. Architectural modeling from sparsely scanned range data[J]. International Journal of Computer Vision, 2008, 78(2/3): 223-236. DOI: 223

Huang J, Menq C H. Automatic data segmentation for geometric feature extraction from unorganized 3-D coordinate points[J]. Robotics and Automation, IEEE Transactions on, 2001, 17(3): 268-279. DOI: 268

Schnabel R, Wahl R, Klein R. Efficient RANSAC for point-cloud shape detection[C]//Computer graphics forum. Blackwell Publishing Ltd, 2007, 26(2): 214-226.

Tarabalka Y, Benediktsson J A, Chanussot J, et al. Multiple spectral-spatial classification approach for hyperspectral data[J]. Geoscience and Remote Sensing, IEEE Transactions on, 2010, 48(11): 4122-4132. DOI: 4122

Lin H, Gao J, Zhou Y, et al. Semantic decomposition and reconstruction of residential scenes from lidar data[J]. ACM Transactions on Graphics (TOG), 2013, 32(4): 66-68. DOI: 66

Anguelov D, Taskarf B, Chatablashv, et al. Discriminative learning of markov random fields for segmentation of 3d scan data[C]//CVPR 2005. USA, San Diego, IEEE, 2005, DDI: 10. 1109/CVPR 2005, 133.

Musialski P, Wonka P, Aliaga D G, et al. A survey of urban reconstruction[J]. Computer graphics forum, 2013, 32(6): 146-177. DOI: 146

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于时空特征原型的视频场景图生成

复杂系统多因素估计函数分析及其应用

基于监控指标关联性的微服务异常检测

大模型发展综述：从BERT到Deepseek的技术演进

一种用于极低压boost系统的高效率电荷泵