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

Ancient DNA reveals 4000 years of grapevine diversity, viticulture and clonal propagation in France.

Nature communications·2026
Same author

Curriculum-Based Reinforcement Learning for Autonomous UAV Navigation in Unknown Curved Tubular Conduits.

Sensors (Basel, Switzerland)·2026
Same author

Calcifying plankton: From biomineralization to global change.

Science (New York, N.Y.)·2025
Same author

8,000 years of wild and domestic animal body size data reveal long-term synchrony and recent divergence due to intensified human impact.

Proceedings of the National Academy of Sciences of the United States of America·2025
Same author

The origins and spread of the opium poppy (<i>Papaver somniferum</i> L.) revealed by genomics and seed morphometrics.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2025
Same author

Roots of domestication: unveiling the dynamics of domestication through trait-based analysis of olive trees in northern Morocco.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2025

Related Experiment Video

Updated: Jun 25, 2025

Author Spotlight: A High-Resolution, Single-Grain, In Vivo Pollen Hydration Bioassay for Arabidopsis thaliana
07:07

Author Spotlight: A High-Resolution, Single-Grain, In Vivo Pollen Hydration Bioassay for Arabidopsis thaliana

Published on: June 30, 2023

2.4K

A user-friendly method to get automated pollen analysis from environmental samples.

Betty Gimenez1, Sébastien Joannin1,2, Jérôme Pasquet3,4

  • 1ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France.

The New Phytologist
|May 29, 2024
PubMed
Summary
This summary is machine-generated.

Automated pollen detection using YOLOv5 is efficient for environmental samples. This method optimizes workload and performance, improving the accuracy of pollen analysis in scientific studies.

Keywords:
Mediterranean vegetation monitoringYOLOv5artificial intelligenceautomated pollen analysisdeep learningdetection errorsenvironmental real‐world samplesguidelines

More Related Videos

Collection and Identification of Pollen from Honey Bee Colonies
08:11

Collection and Identification of Pollen from Honey Bee Colonies

Published on: January 19, 2021

7.2K
Determination of Self- and Inter-incompatibility Relationships in Apricot Combining Hand-Pollination, Microscopy and Genetic Analyses
08:08

Determination of Self- and Inter-incompatibility Relationships in Apricot Combining Hand-Pollination, Microscopy and Genetic Analyses

Published on: June 16, 2020

7.3K

Related Experiment Videos

Last Updated: Jun 25, 2025

Author Spotlight: A High-Resolution, Single-Grain, In Vivo Pollen Hydration Bioassay for Arabidopsis thaliana
07:07

Author Spotlight: A High-Resolution, Single-Grain, In Vivo Pollen Hydration Bioassay for Arabidopsis thaliana

Published on: June 30, 2023

2.4K
Collection and Identification of Pollen from Honey Bee Colonies
08:11

Collection and Identification of Pollen from Honey Bee Colonies

Published on: January 19, 2021

7.2K
Determination of Self- and Inter-incompatibility Relationships in Apricot Combining Hand-Pollination, Microscopy and Genetic Analyses
08:08

Determination of Self- and Inter-incompatibility Relationships in Apricot Combining Hand-Pollination, Microscopy and Genetic Analyses

Published on: June 16, 2020

7.3K

Area of Science:

  • Palynology
  • Computational Biology
  • Environmental Science

Background:

  • Automated pollen analysis faces challenges with environmental samples due to high pollen diversity and debris.
  • Pollen detection, the initial step in analysis, is often overlooked but critical for accuracy.

Purpose of the Study:

  • To develop and optimize an efficient automated pollen detection method for environmental samples.
  • To evaluate the performance and workload implications of different annotation strategies.

Main Methods:

  • Applied the YOLOv5 algorithm to environmental samples with diverse pollen taxa and debris.
  • Designed and tested various annotation strategies to optimize detection performance.
  • Analyzed detection errors, including undetected pollen and misclassified debris.

Main Results:

  • Achieved efficient pollen detection with approximately 5% undetected pollen and 5% false positives (debris).
  • Detection accuracy was maintained on unseen samples, irrespective of taxonomic detail.
  • Single-taxon detection was efficient only for morphologically distinct pollen types.

Conclusions:

  • The YOLOv5-based method provides an efficient and replicable approach for automated pollen detection in environmental samples.
  • Guidelines are offered for plant scientists to effectively implement automated pollen detection using user-friendly tools.
  • This work enhances the efficiency and reliability of pollen-based scientific studies.