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

Multi-Sensor Fusion for Wheel-Inertial-Visual Systems Using a Fuzzification-Assisted Iterated Error State Kalman Filter.

Sensors (Basel, Switzerland)·2024
Same author

Microscopical Observation and Transcriptome Analysis Reveal the Effects of High-Altitude Ecosystem in the Qualities of Different Genetic Varieties <i>Brassica napus</i> Resources.

Ecology and evolution·2024
Same author

Characterization of occult hepatitis B virus infection from blood donors in China.

Journal of clinical microbiology·2011
Same author

Cardioprotective effects of Glycyrrhiza uralensis extract against doxorubicin-induced toxicity.

International journal of toxicology·2011
Same author

Nanoscale Kirkendall effect for the synthesis of Bi2MoO6 boxes via a facile solution-phase method.

Nanoscale·2011
Same author

p62/SQSTM1 involved in cisplatin resistance in human ovarian cancer cells by clearing ubiquitinated proteins.

European journal of cancer (Oxford, England : 1990)·2011

相关实验视频

Updated: Sep 16, 2025

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.4K

一种动态卡尔曼选方法,用于复杂果园中的多对象果实跟踪和计数.

Yaning Zhai1, Ling Zhang1, Xin Hu2

  • 1Guangxi Technological College of Machinery and Electricity, Nanning 530007, China.

Sensors (Basel, Switzerland)
|July 12, 2025
PubMed
概括

这项研究引入了一种新的方法,用于跟踪和计数果园中的水果,使用改进的YOLO物体检测和卡尔曼波器. 该方法通过在动态视频场景中实现准确,连续的水果监控来增强精密农业.

关键词:
卡尔曼过器可以过.果实计数计数的果实智能果园是一个聪明的果园.多对象跟踪多对象跟踪目标检测 目标检测 目标检测

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

9.1K
SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

8.3K

相关实验视频

Last Updated: Sep 16, 2025

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.4K
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

9.1K
SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

8.3K

科学领域:

  • 农业情报 农业情报
  • 计算机视觉 计算机视觉 计算机视觉
  • 精准农业 精准农业 精准农业

背景情况:

  • 深度学习模型与动态果园场景作斗争,以检测和计数水果.
  • 现有的方法仅限于静态的,单图像处理.
  • 优化果园管理需要先进的自动监控解决方案.

研究的目的:

  • 为动态果园环境开发一个强大的多对象水果跟踪和计数方法.
  • 为了提高水果检测和计数在视频序列中的准确性和稳定性.
  • 通过智能自动化水果监测,推进精准农业.

主要方法:

  • 整合了改进的YOLO物体检测算法,以实现高质量的初始检测.
  • 应用动态优化的卡尔曼波器,具有可变的遗忘因子,用于自适应跟踪.
  • 使用一个联合的交叉在联盟 (IoU) 和重新识别 (Re-ID) 战略,以准确的目标关联.

主要成果:

  • 实现了强大且连续的果实跟踪,多重对象跟踪精度 (MOTA) 为95.0%,高阶跟踪精度 (HOTA) 为82.4%.
  • 在果子计数方面表现出高精度和稳定性,确定系数为0.85,平方根平均误差 (RMSE) 为1.57.
  • 在复杂的果园环境中使用视频序列验证了该方法的有效性.

结论:

  • 提出的方法有效地解决了用于水果监测的静态图像分析的局限性.
  • 整合了改进的YOLO和卡尔曼过,提供了准确而稳定的水果检测,跟踪和计数.
  • 这项技术为优化果园管理和推进精准农业做出了重大贡献.