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 Experiment Video

Updated: Mar 29, 2026

Automated Analysis of C. elegans Fluorescence Images using SegElegans
06:27

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Published on: October 10, 2025

760

End-to-End Segmentation and Classification of Zooplankton Using Shadowgraphy and Convolutional Neural Networks.

Andrew Capalbo1, Francis Letendre1, Alexander Langner1

  • 1Harbor Branch Oceanographic Institute, Florida Atlantic University, 5600 US-1N, Fort Pierce, FL 34946, USA.

Sensors (Basel, Switzerland)
|March 28, 2026
PubMed
Summary

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

Linking peak intensity of mechanically stimulated bioluminescence and cell surface area in dinoflagellates.

Biology open·2025
Same author

Neutral lines and model-measurement closure in oceanic polarized light fields.

Optics express·2025
Same author

Using bioluminescence as a tool for studying diversity in marine zooplankton and dinoflagellates: an initial assessment.

PeerJ·2024
Same author

The loss of crude oil droplets by filter feeders and the role of surfactants.

Marine pollution bulletin·2023
Same author

The capture of crude oil droplets by filter feeders at high and low Reynolds numbers.

The Journal of experimental biology·2022
Same author

Airborne and shipborne polarimetric measurements over open ocean and coastal waters: intercomparisons and implications for spaceborne observations.

Remote sensing of environment·2021

This study developed an automated algorithm using deep learning for marine zooplankton classification. The system accurately identifies and classifies zooplankton from in situ images, improving ecological monitoring.

Area of Science:

  • Marine biology
  • Computational ecology
  • Image analysis

Background:

  • In situ imaging systems are increasingly used for marine organism analysis.
  • Automated classification and biomass estimation are common, but reliable organism detection and classification remain challenging.
  • Existing methods often struggle with issues like over-segmentation and noise.

Purpose of the Study:

  • To develop an end-to-end classification algorithm for marine zooplankton using Convolutional Neural Networks (CNNs).
  • To address challenges in automated segmentation and classification, including over-segmentation, noise, and organism size.
  • To create a versatile, adaptable, scalable, and autonomous system for zooplankton analysis.

Main Methods:

  • Development of a CNN-based algorithm for marine zooplankton classification using the Ichthyoplankton Imaging System (ISIIS-DPI).
Keywords:
biodiversityclassificationin situ imagerymachine learningsegmentationshadowgraphyzooplankton

More Related Videos

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

1.3K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.3K

Related Experiment Videos

Last Updated: Mar 29, 2026

Automated Analysis of C. elegans Fluorescence Images using SegElegans
06:27

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Published on: October 10, 2025

760
Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

1.3K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.3K
  • Training four common network architectures (Resnet, Xception, GoogleNet, Darknet) on a segmented image dataset of 70,624 regions of interest.
  • Implementing a secondary classification level to further subdivide the 'Gelatinous' class into six groups.

    • Main Results:

    • Achieved high classification accuracies (95.94-96.09%) for four organism classes (Chaetognath, Crustacean, Gelatinous, Larvacean) and detritus in the initial training.
    • Demonstrated the algorithm's effectiveness across diverse water types and zooplankton communities (Florida Gulf coast, Trondheimsfjord, Sargasso Sea).
    • Attained secondary classification accuracies of 86.12-90.40% for subdividing the 'Gelatinous' class, enabling taxonomic classification to the order level.

    Conclusions:

    • The developed algorithm provides a versatile, adaptable, scalable, and autonomous solution for marine zooplankton segmentation and classification.
    • The use of niched networks mirroring taxonomy enhances classification capabilities.
    • The system, integrated into a publicly available MATLAB GUI, offers a valuable tool for ecological research and monitoring.