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

Osmoregulation in Fishes02:32

Osmoregulation in Fishes

52.7K
When cells are placed in a hypotonic (low-salt) fluid, they can swell and burst. Meanwhile, cells in a hypertonic solution—with a higher salt concentration—can shrivel and die. How do fish cells avoid these gruesome fates in hypotonic freshwater or hypertonic seawater environments?
52.7K

You might also read

Related Articles

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

Sort by
Same author

Lipidomic and Transcriptomic Insights into Hepatic Lipid Remodeling Induced by Peony Seed Oil.

Journal of agricultural and food chemistry·2026
Same author

Identifying hot-spot pathways in fishery science and technology innovation through temporal heterogeneous graph neural networks.

Scientific reports·2026
Same author

A scaffold-degradable single-rivet ASD occluder with amplatzer-like design: a multicenter randomized controlled trial.

Cardiovascular intervention and therapeutics·2026
Same author

Dynamic-weighing grain mass flow sensing for reliable in-field yield monitoring in combine harvesters.

Frontiers in plant science·2026
Same author

Exploring the Research Progress of Vascular Dementia and Key Regulatory Molecules: E2F1.

International journal of molecular sciences·2026
Same author

Defect 3D reconstruction with integrated bright-field and dark-field structured illumination microscopy based on Att-PU-Net.

Applied optics·2026

Related Experiment Video

Updated: Jan 10, 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

13.0K

Underwater fish image recognition based on knowledge graphs and semi-supervised learning feature enhancement.

FengWei Zhang1, Jing Hu1, YingZe Sun2

  • 1Information Technology Research Center, Chinese Academy of Fishery Sciences, Beijing, 100141, China.

Scientific Reports
|November 25, 2025
PubMed
Summary

Accurate fish identification in aquaculture is improved by a new knowledge-augmented framework. This system uses a Fish Multimodal Knowledge Graph (FM-KG) to enhance underwater image recognition, boosting precision feeding and automation.

More Related Videos

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

1.4K
Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools
09:32

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

9.7K

Related Experiment Videos

Last Updated: Jan 10, 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

13.0K
Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

1.4K
Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools
09:32

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

9.7K

Area of Science:

  • Aquatic computer vision
  • Automated aquaculture systems
  • Bio-inspired AI

Background:

  • High-accuracy fish identification is crucial for precision feeding in automated aquaculture.
  • Underwater image degradation (light fluctuation, turbidity, occlusion) severely impacts biomass and count accuracy.
  • Conventional methods struggle with degraded images due to a lack of biological context.

Purpose of the Study:

  • To develop a knowledge-augmented framework for robust fish-species identification in degraded underwater environments.
  • To overcome limitations of existing methods by integrating biological knowledge with deep visual recognition.
  • To improve accuracy in automated polyculture systems through enhanced fish recognition.

Main Methods:

  • Proposed a framework integrating a Fish Multimodal Knowledge Graph (FM-KG) with deep visual recognition.
  • FM-KG fuses multi-source biological and environmental data for species-specific semantics.
  • Developed a Semantically-Guided Denoising Module (SGDM) and Knowledge-Driven Attention Dynamic Modulation Layer (K-ADML) to restore images and refine attention mechanisms.

Main Results:

  • The proposed framework significantly outperformed state-of-the-art underwater image enhancement and recognition methods.
  • Performance gains were particularly notable under low signal-to-noise ratios and severe blur conditions.
  • Demonstrated consistent improvements in fish-species identification accuracy on aquaculture datasets.

Conclusions:

  • The knowledge-augmented framework provides a semantically grounded approach to mitigate information loss in aquatic vision.
  • This paradigm enhances robustness for intelligent aquaculture automation.
  • Establishes a foundation for more accurate and reliable automated fish monitoring and management.