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

Expert consensus on surgical management of unilateral Wilms tumor (2025).

World journal of pediatric surgery·2026
Same author

Development of an Interpretable Machine Learning Model for Predicting Clavien-Dindo Grade ≥2 Complications after Unilateral Minimally Invasive Pyeloplasty in UPJO: A Retrospective Cohort Study.

Journal of endourology·2026
Same author

Dual metabolic intervention nanoplatform co-delivering BAY-876 and L-cystine for Wilms tumor therapy via disulfidptosis-associated cytoskeletal collapse.

Journal of nanobiotechnology·2026
Same author

Recovery of ureteral dilation following laparoscopic Lich-Gregoir anti-reflux surgery for moderate/severe vesicoureteral reflux in children.

Journal of pediatric urology·2026
Same author

Clinical Trajectory and Predictors of Conservative Management Failure in Primary Vesicoureteral Reflux With a History of Urinary Tract Infection: A Retrospective Cohort Study and Nomogram Development.

Urology·2026
Same author

Factors affecting the spontaneous resolution of pediatric primary hydrocele: a cohort study of children aged 0-12 years and development of a clinical prediction model.

BMC pediatrics·2026

相关实验视频

Updated: Jun 13, 2025

HPLC Coupled with Chemical Fingerprinting for Multi-Pattern Recognition for Identifying the Authenticity of Clematidis Armandii Caulis
07:29

HPLC Coupled with Chemical Fingerprinting for Multi-Pattern Recognition for Identifying the Authenticity of Clematidis Armandii Caulis

Published on: November 11, 2022

2.0K

一种基于多域多尺度特征融合算法的高质量新鲜四川胡分类方法.

Pengjun Xiang1,2, Fei Pan1,2, Xuliang Duan1,2

  • 1College of Information Engineering, Sichuan Agricultural University, Ya'an 625014, China.

Foods (Basel, Switzerland)
|September 14, 2024
PubMed
概括

这项研究引入了一种新的多域YOLOv8模型,用于高效的四川胡收获后的选择. 先进的算法准确地细分和分类胡的质量,提高加工效率和生产商的利.

关键词:
四川胡分类 四川胡分类实例细分 实例细分 实例细分机器视觉 机器视觉 机器视觉期限分类 期限分类 期限分类 期限分类智能农业 智能农业

更多相关视频

Analysis of Effect of Compound Salt Stress on Seed Germination and Salt Tolerance Analysis of Pepper Capsicum annuum L.
08:27

Analysis of Effect of Compound Salt Stress on Seed Germination and Salt Tolerance Analysis of Pepper Capsicum annuum L.

Published on: November 30, 2022

4.3K
Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.8K

相关实验视频

Last Updated: Jun 13, 2025

HPLC Coupled with Chemical Fingerprinting for Multi-Pattern Recognition for Identifying the Authenticity of Clematidis Armandii Caulis
07:29

HPLC Coupled with Chemical Fingerprinting for Multi-Pattern Recognition for Identifying the Authenticity of Clematidis Armandii Caulis

Published on: November 11, 2022

2.0K
Analysis of Effect of Compound Salt Stress on Seed Germination and Salt Tolerance Analysis of Pepper Capsicum annuum L.
08:27

Analysis of Effect of Compound Salt Stress on Seed Germination and Salt Tolerance Analysis of Pepper Capsicum annuum L.

Published on: November 30, 2022

4.3K
Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.8K

科学领域:

  • 农业工程 农业工程
  • 计算机视觉 计算机视觉
  • 食品科学 食品科学 食品科学

背景情况:

  • 收获后选择高质量的四川胡对于农业生产至关重要.
  • 现有的方法在不同的胡姿势和成熟度水平上扎.
  • 需要准确的视觉分析才能有效地进行分类.

研究的目的:

  • 开发一个自动化的视觉系统,用于高质量的四川胡选择.
  • 提高收获后加工的准确性和效率.
  • 通过更好的质量控制,提高生产者的利能力.

主要方法:

  • 拟议的多级频域特征融合模块 (MSF3M) 和多级双域特征融合模块 (MS-DFFM).
  • 开发了一个多域YOLOv8网络,用于四川胡的细分和分类.
  • 实施了基于平均本地像素值差异的选择方法.

主要成果:

  • 多域YOLOv8-seg实现了新鲜四川胡细分的88.8%mAP50 (5.84 MB模型大小).
  • 多域YOLOv8-cls在四川胡成熟度分类中达到98.34%的准确性.
  • 多域YOLOv8模型表现出比基线YOLOv8.8更高的准确性和更轻的结构.

结论:

  • 多域YOLOv8模型显著提高了四川胡的收获后加工效率.
  • 开发的系统有效地减少了质量选择中的错误判断.
  • 这项技术为农业应用和生产商利带来了巨大的好处.