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

Abuse Potential and Neurotoxic Effects of the Synthetic Cannabinoid 4F-ABUTINACA Self-Administration in Adult Male Rats.

Addiction biology·2026
Same author

Prediction of Zonisamide Concentration in Pediatric Patients With Epilepsy: A Machine Learning Approach.

CNS neuroscience & therapeutics·2026
Same author

Methamphetamine hijacks chaperone-mediated autophagy to degrade GPX4, driving ferroptosis-precipitated cognitive decline and addictive pathogenesis.

Acta neuropathologica communications·2026
Same author

Reinforcing and discriminative stimulus effects of 4-fluorobutyrfentanyl, 4-fluoroisobutyrfentanyl, and isobutyrfentanyl in male rats.

European journal of pharmacology·2026
Same author

Study on the effects of different fermentation methods on fermented mustard microbial community composition and metabolite profile.

Food chemistry: X·2026
Same author

Construction and interpretability evaluation of a prediction model for radiographic pneumonia in children at outpatient and emergency departments.

International journal of medical informatics·2026

相关实验视频

Updated: Jun 22, 2025

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

515

高精度物体检测网络用于自动采摘梨.

Peirui Zhao1, Wenhua Zhou2, Li Na3

  • 1College of Food Science and Engineering, Central South University of Forestry and Technology, Changsha, 410004, China.

Scientific reports
|June 28, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了HDMNet,这是一个高精度的对象检测网络,用于自动采摘梨. 它通过减少背景噪音和处理果实遮来提高准确性,这对农业机器人至关重要.

关键词:
农业情报 农业情报深度学习是一种深度学习.非最大的抑制抑制.对象检测检测对象检测对象检测这就是YOLOv8的意义.

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

9.0K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

相关实验视频

Last Updated: Jun 22, 2025

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

515
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

9.0K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

科学领域:

  • 农业工程 农业工程
  • 计算机视觉 计算机视觉
  • 机器人技术 机器人技术 机器人技术

背景情况:

  • 增加农业产量和劳动力短缺需要农业智能.
  • 现有的深度学习对象检测方法与背景杂乱和梨花园中的水果遮作斗争.
  • 目前的方法缺乏复杂的自动化梨摘任务所需的精度.

研究的目的:

  • 提出一个高精度的物体检测网络,用于自动梨.
  • 通过解决背景冗余和果实封闭问题来提高检测准确度.
  • 开发一个满足复杂自动化农业任务需求的系统.

主要方法:

  • 开发了基于YOLOv8.8的高层变形感知网络与多对象搜索NMS (HDMNet),基于YOLOv8.
  • 整合了一个高级语义集中注意力机制来过背景信息.
  • 利用变形感知特征的金字塔网络来改进远处和小水果的检测.
  • 实现了多对象搜索非最大抑制,以实现有效的多对子检测.

主要成果:

  • HDMNet的平均平均精度 (mAP) 为75.7%,mAP50的平均精度为93.6%.
  • 该网络表现出高效率,每秒73.0 (FPS) 和低计算成本 (41.1 GFLOPs).
  • HDMNet具有较低的参数数量 (12.9M),在实时检测,精度和定位方面表现优于最先进的方法.

结论:

  • HDMNet在对象检测方面提供了显著的进步,用于自动化梨收获.
  • 网络的设计有效地应对了背景噪音和水果封闭等挑战.
  • HDMNet为农业机器人提供了计算效率高和高度准确的解决方案.