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

Detection of nitrogen content in wheat leaves based on visible/near-infrared spectroscopy sensing.

Analytical methods : advancing methods and applications·2026
Same author

A Prospective Multicenter Assessment of the Accuracy and Safety of the Yuwell CT3 Real-Time Continuous Glucose Monitoring System in Patients With Diabetes Over 14 Days.

Journal of diabetes·2026
Same author

MoS<sub>2</sub> Nanosheet/ZnO Nanowire-Functionalized Optical Fiber LSPR Biosensor for Sensitive Detection of 2,4-D Herbicide Residues.

Nanomaterials (Basel, Switzerland)·2026
Same author

Terahertz Sensor for Trace Pb<sup>2+</sup> in Liquid Based on Weyl Semimetal Films with External Field Modulation.

ACS applied materials & interfaces·2026
Same author

Intraspecific variation pattern and adaptation mechanism of ephemeral plants root functional traits in arid region.

BMC plant biology·2026
Same author

Automated machine learning assisted fluorescent sensor array based on silver nanoclusters for detection of multiple heavy metal ions.

Mikrochimica acta·2026

相关实验视频

Updated: Jun 7, 2025

Tomato Analyzer: A Useful Software Application to Collect Accurate and Detailed Morphological and Colorimetric Data from Two-dimensional Objects
15:25

Tomato Analyzer: A Useful Software Application to Collect Accurate and Detailed Morphological and Colorimetric Data from Two-dimensional Objects

Published on: March 16, 2010

26.3K

基于优化的语义细分和障碍感知算法的无障碍番茄水果选择和位置.

Lingli Zhou1,2, Anqi Hu1,2, Yawen Cheng1,2

  • 1Institute of Agricultural Information, Jiangsu Academy of Agricultural Sciences, Nanjing, China.

Frontiers in plant science
|November 15, 2024
PubMed
概括

这项研究引入了一种改进的计算机视觉系统,用于收获机器人准确选择和定位非遮的水果,提高水果检测精度,并通过考虑诸如茎和电线等障碍物来减少位置错误.

关键词:
深度学习是一种深度学习.水果的选择,水果的选择.收获机器人收获机器人图像语义细分 图像语义细分障碍物感知障碍物的感知.定位定位 定位定位在这里,我们可以看到茄,番茄,番茄.

更多相关视频

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.9K
An Efficient Clearing Protocol for the Study of Seed Development in Tomato Solanum lycopersicum L.
06:26

An Efficient Clearing Protocol for the Study of Seed Development in Tomato Solanum lycopersicum L.

Published on: September 7, 2022

4.0K

相关实验视频

Last Updated: Jun 7, 2025

Tomato Analyzer: A Useful Software Application to Collect Accurate and Detailed Morphological and Colorimetric Data from Two-dimensional Objects
15:25

Tomato Analyzer: A Useful Software Application to Collect Accurate and Detailed Morphological and Colorimetric Data from Two-dimensional Objects

Published on: March 16, 2010

26.3K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.9K
An Efficient Clearing Protocol for the Study of Seed Development in Tomato Solanum lycopersicum L.
06:26

An Efficient Clearing Protocol for the Study of Seed Development in Tomato Solanum lycopersicum L.

Published on: September 7, 2022

4.0K

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
  • 农业技术 农业技术

背景情况:

  • 基于视觉的水果检测对于收获机器人至关重要.
  • 像茎和电线这样的障碍往往会掩盖水果,妨碍准确的识别.
  • 现有的方法缺乏强大的障碍物感知,用于精确的水果选择.

研究的目的:

  • 为收获机器人开发先进的水果目标选择和定位方法,其中包括障碍物感知.
  • 通过解决封闭问题,提高复杂温室环境中果实检测的准确性.

主要方法:

  • 使用3D模拟和语义细分生成了番茄收获的合成数据.
  • 设计了一个基于注意力的空间关系特征提取模块 (SFM),以改进DeepLab v3+对线性障碍物的细分.
  • 开发了适应式K-means集群用于水果实例细分和无障碍水果选择算法.

主要成果:

  • 改进的语义细分实现了96.75%的准确性,电线和茎的IOU分别增加了5.0%和2.3%.
  • 障碍物类型的识别达到了96.15%,封闭的水果被排除在外,有效率为86.67%.
  • 与Yolo v5.5.5相比,拟议的方法显示选择精度增加了18.9%,位置错误减少了1.3%.

结论:

  • 增强的语义细分和障碍感知算法有效地解决了树干和线索的果实阻塞问题.
  • 无障碍水果选择算法可靠地在复杂的环境中确定最佳的摘取目标.
  • 这种方法为水果收获机器人提供了更实用和更准确的解决方案,适用于各种作物.