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

Divergent filtration mechanisms of fibrous and non-fibrous microplastics in towing-net sampling toward a harmonized framework for abundance correction.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Revitalizing Fulleropyrrolidine via Nonionic Sidechain Engineering: An Ethanol-Processible Interlayer Enabling Efficient Organic Solar Cells.

Angewandte Chemie (International ed. in English)·2026
Same author

The Potential Role of Baseline FT3/FT4 Ratio as a Prognostic Biomarker for Patients With Ischemic Non-Obstructive Coronary Artery Disease.

Clinical cardiology·2026
Same author

A first quantitative assessment of seabed litter collection efficiency using bottom otter trawls and fishery depletion models.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Prediction of Neurological Functional Recovery after Carotid Endarterectomy Using Machine Learning and Carotid Computed Tomography Angiography Radiomics.

World neurosurgery·2026
Same author

Application of an IEW-CRITIC-CoCoSo method based on interval-valued T-spherical fuzzy for optimizing process parameters of 3D printed recycled polypropylene composites.

Scientific reports·2026

相关实验视频

Updated: Mar 15, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.1K

边部署的鱼类养状态量化和识别通过框架对运动编码和高效养网.

Yuchen Xiao1, Weijia Ren1, Yining Wang1

  • 1College of Fisheries, Ocean University of China, Qingdao 266003, China.

Animals : an open access journal from MDPI
|March 14, 2026
PubMed
概括

本研究引入了一种高效的边缘部署框架,用于监测水产养殖中的鱼类养状态. 该系统使用光流和轻量级网络来准确识别养行为,使数据驱动的决策能够改善农场管理.

关键词:
水产养殖监测水产养殖的监测鱼的养状态 鱼的养状态鱼类福利 鱼类福利光学流的光学流量实时识别 实时识别

更多相关视频

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.3K
High-fat Feeding Paradigm for Larval Zebrafish: Feeding, Live Imaging, and Quantification of Food Intake
11:30

High-fat Feeding Paradigm for Larval Zebrafish: Feeding, Live Imaging, and Quantification of Food Intake

Published on: October 27, 2016

11.2K

相关实验视频

Last Updated: Mar 15, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.1K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.3K
High-fat Feeding Paradigm for Larval Zebrafish: Feeding, Live Imaging, and Quantification of Food Intake
11:30

High-fat Feeding Paradigm for Larval Zebrafish: Feeding, Live Imaging, and Quantification of Food Intake

Published on: October 27, 2016

11.2K

科学领域:

  • 水产养殖技术 水产养殖技术
  • 计算机视觉 计算机视觉 计算机视觉
  • 动物行为分析 动物行为分析

背景情况:

  • 精确的养状态监测对于有效的水产养殖管理,减少浪费和确保鱼类福利至关重要.
  • 目前基于视觉的方法由于主观标记和高计算成本而面临限制,这阻碍了实际应用.

研究的目的:

  • 开发一个客观的,边缘部署的框架,用于实时量化和识别水产养殖中的养状态.
  • 通过自动化运动分析,实现及时,数据驱动的养决策.

主要方法:

  • 将对密集光流编码与轻量级神经网络 (EfficientFeedingNet) 的集成.
  • 使用光学流量衍生的运动强度信号 (V-Value) 来自动划分食间隔.
  • 使用可复制标签构建基于感知数据集 (感知数据集).

主要成果:

  • 在感知数据集上训练的模型实现了超过90%的测试准确性,超过了在观察者标记数据上训练的模型.
  • 在边缘硬件 (Jetson Orin NX) 上,EfficientFeedingNet 实现了 96.53% 的测试准确率,并以 143.24 fps 运行.
  • 该框架展示了实时,运动驱动的养状态量化的实际基础.

结论:

  • 拟议的框架为水产养殖中客观,实时的养状态监测提供了一个实际的解决方案.
  • EfficientFeedingNet的轻量级设计使边缘部署更容易,支持精确的水产养殖实践.
  • 这项技术可以显著改善料管理,减少料浪费,提高鱼类福利.