Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Mental workload recognition from EEG signals via semi-supervised autoencoders.

Computer methods in biomechanics and biomedical engineering·2025
Same author

A LiDAR-Camera Joint Calibration Algorithm Based on Deep Learning.

Sensors (Basel, Switzerland)·2024
Same author

Real time object detection using LiDAR and camera fusion for autonomous driving.

Scientific reports·2023
Same author

A comparative study to determine the effects of breed and feed restriction on glucose metabolism of chickens.

Animal nutrition (Zhongguo xu mu shou yi xue hui)·2023
Same author

A Review of Microinjection Moulding of Polymeric Micro Devices.

Micromachines·2022
Same author

Cross-attention-map-based regularization for adversarial domain adaptation.

Neural networks : the official journal of the International Neural Network Society·2021

相关实验视频

Updated: Jun 3, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

765

基于DBSCAN集群和自适应细分的机器人本地化强大和快速点云注册.

Haibin Liu1, Yanglei Tang2, Huanjie Wang1

  • 1College of Mechanical and Energy Engineering, Beijing University of Technology, Beijing 100124, China.

Sensors (Basel, Switzerland)
|January 8, 2025
PubMed
概括
此摘要是机器生成的。

本研究介绍了聚类和细分正常分布转换 (CSNDT) 对于增强的点云注册. 通过使用自适应集群和细分,CSNDT提高了稳定性和效率,优于传统方法.

关键词:
集群和细分是指集群和细分.基于密度的噪声应用的空间聚类 (DBSCAN)正常分布转换 (NDT) 是指正常分布转换.点云注册点云注册是什么意思机器人本地化 机器人本地化

更多相关视频

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

47.8K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

相关实验视频

Last Updated: Jun 3, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

765
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

47.8K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

科学领域:

  • 计算机视觉 计算机视觉
  • 几何计算几何计算
  • 3D数据处理 3D数据处理

背景情况:

  • 传统的正常分布转换 (NDT) 算法在初始化方面遇到了困难,导致本地特征丢失和映射错误.
  • 点云注册对于3D数据分析至关重要,但通常受到范围和效率的限制.

研究的目的:

  • 提出一种新的点云注册方法,即聚类和细分正常分布转换 (CSNDT),以提高注册范围和效率.
  • 解决传统的NDT算法在处理本地特征和初始化方面的局限性.

主要方法:

  • 通过将自适应细胞分区策略集成到点云注册中,开发了CSNDT.
  • 将基于标准偏差和相关系数的判断机制纳入DBSCAN,以改进自适应集群.
  • 实现了直线点云集群与自适应网格细胞和基于细胞长度的细胞细分.

主要成果:

  • 拟议的CSNDT算法在点云注册中表现出卓越的稳定性和精度.
  • 与Iterative Closest Point (ICP) 和标准的NDT算法相比,CSNDT提供了更好的匹配效率.
  • 适应性细胞分区和细分有效地扩大了注册范围并提高了准确性.

结论:

  • CSNDT为点云注册挑战提供了更强大,更有效的解决方案.
  • 适应性聚类和细分技术显著提高了基于NDT的注册的性能.
  • 这种方法为需要精确的3D点云对齐的应用提供了有前途的进步.