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

相关实验视频

Updated: Sep 13, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

8.5K

运动状态驱动的小猪跟踪方法,用于监测小猪在播种位变化下的运动模式.

Aqing Yang1, Shimei Li2, Shuqin Tu3

  • 1College of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China.

Veterinary sciences
|July 25, 2025
PubMed
概括

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

A parallel resnet-transformer and cross-modal attention network for identification of rice blast resistance using UAV-based visible-infrared imagery.

Plant phenomics (Washington, D.C.)·2026
Same author

Pig Health Assessment Framework Based on Behavioural Analysis.

Animals : an open access journal from MDPI·2025
Same author

Muscle Fibers, Free Amino Acids, and Enhanced Mitochondrial Function Explain the Unique Meat Quality of Tibetan Pigs.

Foods (Basel, Switzerland)·2025
Same author

Self-calibrated acceleration and detail preserving for semantic segmentation of lactating sows and piglets under low-light conditions.

Scientific reports·2025
Same author

Collaborative Optimization of Model Pruning and Knowledge Distillation for Efficient and Lightweight Multi-Behavior Recognition in Piglets.

Animals : an open access journal from MDPI·2025
Same author

Prognostic factors in children and adolescents with differentiated thyroid cancer treated with total thyroidectomy and radioiodine therapy: a retrospective two-center study from China.

Frontiers in endocrinology·2024

一个新的MSHMTracker系统准确地监控猪母猪周围的小猪运动,提高了安全性和农场生产率. 这种自动跟踪有助于防止小猪粉碎,并提供了关于母猪和小猪相互作用的见解.

科学领域:

  • 动物科学动物科学
  • 计算机视觉 计算机视觉
  • 农业工程 农业工程

背景情况:

  • 小猪的安全和健康成长取决于了解它们在姿势变化期间在母猪周围的运动.
  • 自动化监控系统可以减少农场劳动力,防止小猪粉碎事件.
  • 现有的基于联合检测和跟踪 (JDT) 的方法面临着因封闭和拥挤而导致小猪错误识别和跟踪损失的挑战.

研究的目的:

  • 开发一个先进的小猪追踪系统,MSHMTracker,以克服当前方法的局限性.
  • 提高在生猪场环境中自动监测的准确性和可靠性.
  • 分析小猪的行为和应激反应与母猪姿势的变化有关.

主要方法:

  • 开发了MSHMTracker,具有运动状态层次结构和得分和时间驱动的层次匹配机制 (STHM).
  • 利用基于小猪运动状态的时空关联的STHM来增强跟踪的稳定性.
  • 使用追踪轨迹数据来识别小猪聚合和分散行为,以应对母猪姿势的变化.

主要成果:

  • 在超过3万张图像上,MSHMTracker实现了93.8%的跟踪精度 (MOTA) 和92.9%的身份一致性 (IDF1).
  • 该系统在性能方面超过了六个受欢迎的跟踪系统.
关键词:
行为模式 行为模式一个层次的匹配机制.多对象跟踪多对象跟踪社会关系社会关系.压力行为识别 压力行为识别

更多相关视频

Noninvasive EEG Recordings from Freely Moving Piglets
04:05

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

7.5K
Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

12.7K

相关实验视频

Last Updated: Sep 13, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

8.5K
Noninvasive EEG Recordings from Freely Moving Piglets
04:05

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

7.5K
Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

12.7K
  • 行为识别准确度达到87.5%的平均值,在小猪压力和母猪姿势变化之间发现了显著的相关性 (0.6和0.82).

    • 结论:

    • 在复杂的农场环境中,MSHMTracker显著提高了小猪跟踪的准确性和可靠性.
    • 这项研究提供了关于母猪和小猪关系以及小猪应激反应的宝贵见解.
    • 这项技术有可能提高畜牧业的生产率,并降低农民的劳动力成本.