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

Cervical Lymph Node Metastasis Patterns and Diagnostic Accuracy of Preoperative Staging in Oral Squamous Cell Carcinoma.

Cancers·2026
Same author

A Prospective, International, Multicentre Registry of Patients Undergoing Segmental Mandibular Defect Reconstruction After Mandibular Resection for Tumours and Drug-Induced Osteonecrosis: A Study Protocol.

Craniomaxillofacial trauma & reconstruction·2026
Same author

Matrix Wave<sup>TM</sup> System for Mandibulo-Maxillary Fixation-Just Another Variation on the MMF Theme? Part I: A Review on the Provenance, Evolution and Properties of the System.

Craniomaxillofacial trauma & reconstruction·2025
Same author

Matrix Wave<sup>TM</sup> System for Mandibulo-Maxillary Fixation-Just Another Variation on the MMF Theme?-Part II: In Context to Self-Made Hybrid Erich Arch Bars and Commercial Hybrid MMF Systems-Literature Review and Analysis of Design Features.

Craniomaxillofacial trauma & reconstruction·2025
Same author

HybGrip: a synergistic hybrid gripper for enhanced robotic surgical instrument grasping.

International journal of computer assisted radiology and surgery·2024
Same author

Computer-assisted orbital and midfacial reconstruction.

Innovative surgical sciences·2023

相关实验视频

Updated: Jul 20, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.1K

改进机器人护士的仪器检测,使用多视图投票.

Jorge Badilla-Solórzano1, Sontje Ihler2, Nils-Claudius Gellrich3

  • 1Institute of Mechatronic Systems, Leibniz University Hannover, Garbsen, Germany. jorge.badilla@imes.uni-hannover.de.

International journal of computer assisted radiology and surgery
|August 2, 2023
PubMed
概括

将深度学习仪器探测器与多视图投票方案相结合,可以显著提高手术仪器检测的准确性. 这种实用方法通过减少在手术过程中识别手术工具的错误来增强机器人护士的能力.

关键词:
面具R-CNN是指一个R-CNN的面具.多个视角的推理推理.机器人辅助手术是一种机器人辅助的手术.机器人擦洗护士护士是一个机器人.手术仪器检测仪器检测器

更多相关视频

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

770
Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS
05:25

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

1.3K

相关实验视频

Last Updated: Jul 20, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.1K
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

770
Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS
05:25

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

1.3K

科学领域:

  • 机器人技术 机器人技术 机器人技术
  • 计算机视觉 计算机视觉
  • 手术技术 手术技术

背景情况:

  • 手术仪器检测对于机器人护士来说至关重要.
  • 深度学习模型表现有前途,但具有性能限制.
  • 现实世界的应用需要高精度和可靠性.

研究的目的:

  • 通过一种新的方法,提高手术仪器检测的准确性.
  • 证明将深度学习与基于多视图实例的投票相结合的有效性.
  • 为了提高机器人手术中仪器检测的可靠性.

主要方法:

  • 从多个视角收集RGB数据和点云,使用机器人护士设置.
  • 利用训练有素的Mask R-CNN模型从每个视图中获得预测.
  • 开发了基于预测实例的多视图投票方案,以结合数据并改进检测.

主要成果:

  • 与单视图方法相比,检测错误减少了82%以上.
  • 平均而言,五个视角足以准确推断仪器排列.
  • 提出的方法显著提高了仪器探测器的性能.

结论:

  • 多视图投票方案大大提高了仪器探测器的性能.
  • 该方法适用于实时手术,而不会破坏工作流程.
  • 实施和数据是公开可用于研究的.