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

Quantitative assessment of supraspinatus fatty infiltration on a novel MRI section: comparison with conventional methods.

BMC musculoskeletal disorders·2026
Same author

long-range underwater acoustic hyperbolic frequency modulation signal denoising based on lightweight neural networka).

The Journal of the Acoustical Society of America·2026
Same author

Outcomes of surgical repair of congenital vascular rings in children.

Journal of cardiothoracic surgery·2026
Same author

Associations of concomitant exposure to outdoor light at night, air pollution, and greenness with metabolic syndrome: A cohort study in China.

Environmental research·2025
Same author

The effects of music-based interventions on cognitive function in cognitively normal older adults: a systematic review and meta-analysis.

Frontiers in psychology·2025
Same author

Are older adults living with HIV more susceptible to omicron infection compared to their HIV-negative peers in China: a cross-sectional study.

Frontiers in public health·2025

Related Experiment Video

Updated: May 30, 2025

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

312

A three-dimensional marine plastic litter real-time detection embedded system based on deep learning.

Xiaoyu Yang1, Yunhao Chen1, Yuehai Zhou1

  • 1College of Ocean and Earth Sciences, Xiamen University, Xiamen 361005, China; National and Local Joint Engineering Research Center for Navigation and Location Service Technology, Xiamen University, Xiamen 361005, China.

Marine Pollution Bulletin
|January 31, 2025
PubMed
Summary

This study introduces a real-time marine plastic litter detection system using deep learning. The system enhances underwater image quality and optimizes models for embedded devices, improving detection accuracy for marine environmental protection.

Keywords:
Dataset optimizationDeep learningMarine plastic pollutionObject detectionUnderwater image enhancement

More Related Videos

Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis
10:16

Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis

Published on: December 16, 2016

49.4K
A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry
06:36

A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry

Published on: April 15, 2021

3.6K

Related Experiment Videos

Last Updated: May 30, 2025

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

312
Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis
10:16

Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis

Published on: December 16, 2016

49.4K
A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry
06:36

A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry

Published on: April 15, 2021

3.6K

Area of Science:

  • Environmental Science
  • Computer Science
  • Marine Biology

Background:

  • Marine plastic pollution poses a significant threat to global marine ecosystems.
  • Developing effective, real-time solutions for detecting and removing marine plastic is crucial.

Purpose of the Study:

  • To implement a three-dimensional marine plastic litter real-time detection (3D-MPLRD) system.
  • To enhance the efficacy of deep learning models for underwater plastic detection.

Main Methods:

  • Utilized deep learning techniques for marine plastic litter detection.
  • Applied image quality assessment and enhancement for underwater conditions.
  • Compressed and quantified the YOLOv5 model for embedded device deployment.

Main Results:

  • The 3D-MPLRD system demonstrated superior performance compared to models trained on original datasets.
  • Achieved higher precision, recall, F1-score, and mean average precision.
  • Successfully deployed the optimized model on embedded systems.

Conclusions:

  • The developed 3D-MPLRD system offers an effective, intelligence-based approach to marine environmental protection.
  • This system provides a foundational reference for future automated marine debris management.
  • The integration of image enhancement and model optimization is key for real-world application.