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

VR-based automated suturing skill assessment in pediatric robotic surgery.

International journal of computer assisted radiology and surgery·2026
Same author

Sim-to-real domain adaptation based completion level recognition for autonomous micro-drilling in biomedical application.

Scientific reports·2025
Same author

Accelerating discovery in natural science laboratories with AI and robotics: Perspectives and challenges.

Science robotics·2025
Same author

A multimodal digital twin for autonomous micro-drilling in scientific exploration.

International journal of computer assisted radiology and surgery·2025
Same author

Evaluation of (Shared) Autonomy in Robot-Assisted Vitreoretinal Surgery Using a Surgical Model.

The international journal of medical robotics + computer assisted surgery : MRCAS·2025
Same author

PEg TRAnsfer Workflow recognition challenge report: Do multimodal data improve recognition?

Computer methods and programs in biomedicine·2023

相关实验视频

Updated: Sep 18, 2025

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

3.0K

使用合成数据增强卷积神经网络的单眼针姿势检测.

Yifan Wang1, Saul Alexis Heredia Perez2, Kanako Harada3,2

  • 1Graduate School of Engineering, The University of Tokyo, 7-chōme-3-1 Hongō, Bunkyo, Tokyo, 113-8656, Japan. wang-yifan971125@g.ecc.u-tokyo.ac.jp.

International journal of computer assisted radiology and surgery
|June 24, 2025
PubMed
概括
此摘要是机器生成的。

这项研究引入了一个卷积神经网络 (CNN) 来从单眼图像中估计针姿势,这对于机器人微手术至关重要. 该方法在合成和现实世界的数据中实现了高精度,有望提高外科手术精度.

关键词:
针头姿势估计估计神经网络的神经网络的神经网络机器人辅助的微型手术模拟器模拟器是一个模拟器

更多相关视频

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

975
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

650

相关实验视频

Last Updated: Sep 18, 2025

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

3.0K
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

975
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

650

科学领域:

  • 机器人和自动化 机器人和自动化
  • 计算机视觉 计算机视觉
  • 手术技术 手术技术

背景情况:

  • 机器人微手术需要高精度的精细程序.
  • 精确的针头姿势估计对于机器人微观定位和自主控制至关重要.
  • 单眼视觉对精确的针头位置估计提出了挑战.

研究的目的:

  • 提出一种基于卷积神经网络 (CNN) 的方法,用于使用单眼图像进行针姿势估计.
  • 通过优化插入轨迹和实现自主控制,提高机器人微观定位的准确性.

主要方法:

  • 一个CNN经过训练,可以从二维图像中检测针上的关键点 (尖端,中间,末端).
  • 现实世界和合成图像的混合数据集被用于模型训练.
  • 开发了一种算法来估计3D关键点位置和针方向.

主要成果:

  • 对合成数据的实验产生了较低的翻译误差 (0.0980.118毫米) 和定向误差 (12.75°15.55°).
  • 对真实数据的评估显示,平均2D翻译误差为0.0470.052毫米.
  • 在真实数据中,超过93%的检测到的关键点的误差低于4像素.

结论:

  • 这种基于CNN的方法有效地估计了针在单眼视觉中的姿势,利用合成数据增强.
  • 该方法在用于机器人微手术应用的真实世界数据上显示出有前途的性能.
  • 这种技术有可能用于自动化手术系统的实时姿势估计.