Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Spatially heterogeneous T1w/T2w ratio alterations in relapsing-remitting multiple sclerosis: associations with cognitive impairment.

Multiple sclerosis and related disorders·2026
Same author

Gastrointestinal bleeding in patients on venoarterial extracorporeal membrane oxygenation: a multicenter observational study.

BMC gastroenterology·2026
Same author

The effects of 10 months of exercise on circulating ketone body concentration among children.

Pediatric research·2026
Same author

An approach for diagnosis of diarrhea in neonatal piglets based on the core gut microbiota and machine learning.

Frontiers in microbiology·2026
Same author

Transcriptome, Proteome, and Metabolome Features in Diarrhea Challenge of Preweaning Piglets via Multi-Omics Integration Analyses.

Animals : an open access journal from MDPI·2026
Same author

Correction to "High-Accuracy and Resolution Fluorescence Intensity Ratio Thermometer for Real-Time Temperature Monitoring in a Lithium-Ion Battery".

Inorganic chemistry·2026

Related Experiment Video

Updated: Jun 9, 2025

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

12.5K

An integrated three-stream network model for discriminating fish feeding intensity using multi-feature analysis and

Yanbin Dong1,2, Shilong Zhao1,2, Yuqing Wang1,2

  • 1College of Marine Technology and Environment, Dalian Ocean University, Dalian, Liaoning Province, China.

Plos One
|October 21, 2024
PubMed
Summary

This study introduces a novel three-stream network using computer vision and Convolutional Neural Networks (CNNs) to accurately assess fish feeding intensity. This intelligent system minimizes feed waste and pollution in aquaculture.

More Related Videos

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
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

475

Related Experiment Videos

Last Updated: Jun 9, 2025

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

12.5K
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
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

475

Area of Science:

  • Aquaculture Technology
  • Computer Vision
  • Machine Learning

Background:

  • Feed costs are a major expense in aquaculture, with current practices often leading to inefficiency and environmental issues.
  • Existing computer vision methods for assessing fish feeding intensity are limited by reliance on single features and manual thresholds.
  • There is a need for practical, accurate methods to determine fish feeding states for precision aquaculture.

Purpose of the Study:

  • To develop an integrated computer vision and Convolutional Neural Network (CNN) approach for assessing fish feeding intensity.
  • To overcome limitations of existing methods by incorporating temporal, spatial, and statistical features.
  • To provide a scientific basis for intelligent fish feeding systems in aquaculture.

Main Methods:

  • Utilized computer vision to preprocess feeding images of pearl gentian grouper.
  • Extracted temporal features using optical flow, spatial features via binarization, and statistical features using the gray-level co-occurrence matrix.
  • Developed a three-stream network fusing classification results from specific feature discrimination networks for feeding intensity assessment.

Main Results:

  • The proposed three-stream network achieved 99.3% accuracy in distinguishing fish feeding intensity.
  • The model accurately categorizes feeding states into none, weak, and strong.
  • Demonstrated a comprehensive evaluation of feeding intensity by integrating multiple feature types.

Conclusions:

  • The developed model offers a practical and highly accurate solution for intelligent fish feeding in aquaculture.
  • This advancement can significantly reduce feed wastage and environmental pollution.
  • Promotes sustainable development within the aquaculture industry through optimized feeding strategies.