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

Evaluating inbreeding and assessing the risk of outbreeding depression in genetic rescue using whole-genome sequence data.

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

Keeping up with climate change: have Arctic arthropods reached their phenological limits?

Proceedings. Biological sciences·2025
Same author

Species' traits modulate rapid changes in flight time in high-Arctic muscid flies under climate change.

Proceedings. Biological sciences·2025
Same author

Plant diversity dynamics over space and time in a warming Arctic.

Nature·2025
Same author

Global impoverishment of natural vegetation revealed by dark diversity.

Nature·2025
Same author

Trap colour strongly affects the ability of deep learning models to recognize insect species in images of sticky traps.

Pest management science·2024

Related Experiment Video

Updated: Nov 22, 2025

Low-Cost Automated Flight Intercept Trap for the Temporal Sub-Sampling of Flying Insects Attracted to Artificial Light at Night
06:19

Low-Cost Automated Flight Intercept Trap for the Temporal Sub-Sampling of Flying Insects Attracted to Artificial Light at Night

Published on: December 29, 2021

2.9K

An Automated Light Trap to Monitor Moths (Lepidoptera) Using Computer Vision-Based Tracking and Deep Learning.

Kim Bjerge1, Jakob Bonde Nielsen1, Martin Videbæk Sepstrup1

  • 1School of Engineering, Aarhus University, Finlandsgade 22, 8200 Aarhus N, Denmark.

Sensors (Basel, Switzerland)
|January 9, 2021
PubMed
Summary

A new automated moth trap (AMT) uses computer vision and deep learning to identify and count live moths. This low-cost system offers non-destructive, real-time insect monitoring, improving ecological data accuracy.

Keywords:
CNNbiodiversitycomputer visiondeep learninginsectslight trapmothtracking

More Related Videos

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

7.1K
Visually Mediated Odor Tracking During Flight in Drosophila
08:50

Visually Mediated Odor Tracking During Flight in Drosophila

Published on: January 26, 2009

10.2K

Related Experiment Videos

Last Updated: Nov 22, 2025

Low-Cost Automated Flight Intercept Trap for the Temporal Sub-Sampling of Flying Insects Attracted to Artificial Light at Night
06:19

Low-Cost Automated Flight Intercept Trap for the Temporal Sub-Sampling of Flying Insects Attracted to Artificial Light at Night

Published on: December 29, 2021

2.9K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

7.1K
Visually Mediated Odor Tracking During Flight in Drosophila
08:50

Visually Mediated Odor Tracking During Flight in Drosophila

Published on: January 26, 2009

10.2K

Area of Science:

  • Ecology
  • Computer Science
  • Entomology

Background:

  • Traditional insect monitoring is labor-intensive and lacks temporal resolution.
  • Manual species identification and infrequent trap servicing hinder ecological interpretation.

Purpose of the Study:

  • To develop a portable computer vision system for automated, non-destructive insect monitoring.
  • To enable real-time detection, tracking, and species classification of moths.

Main Methods:

  • An Automated Moth Trap (AMT) equipped with lights and a camera was designed.
  • A deep learning algorithm, Moth Classification and Counting (MCC), was developed for image analysis.
  • A convolutional neural network was trained on labeled moth images for species identification.

Main Results:

  • The system captured over 250,000 images across 48 nights.
  • The trained neural network achieved a validation F1-score of 0.93 for moth classification.
  • The MCC algorithm demonstrated an average classification F1-score of 0.71 and a detection rate of 0.79.

Conclusions:

  • The proposed computer vision system provides a promising low-cost solution for automatic moth monitoring.
  • This technology enhances temporal resolution and accuracy in ecological studies.
  • Non-destructive monitoring of live insects is now more feasible.