Search research articles

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

Proof-of-concept of harvest peak control using a strawberry cultivation emulator with artificial weather chambers.

Scientific reports·2026

Same author

Identification of ADAMTS5 as APP-Cleaving Enzyme at the APP669 Site.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026

Same author

Evaluating UAV and Handheld LiDAR Point Clouds for Radiative Transfer Modeling Using a Voxel-Based Point Density Proxy.

Sensors (Basel, Switzerland)·2026

Same author

Biomarkers.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025

Same author

Fruit size prediction of tomato cultivars using machine learning algorithms.

Frontiers in plant science·2025

Same author

Electromyography of Flight Muscles in Free-Flying Chestnut Tiger Butterfly, <i>Parantica sita</i>.

Zoological science·2024

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Feb 28, 2026

Radio Frequency Identification and Motion-sensitive Video Efficiently Automate Recording of Unrewarded Choice Behavior by Bumblebees

Radio Frequency Identification and Motion-sensitive Video Efficiently Automate Recording of Unrewarded Choice Behavior by Bumblebees

Published on: November 15, 2014

Detection of bumblebee behaviour around a nest box using AI-based image analysis.

Katsumi Ohyama¹, Hiroki Naito², Norio Hirai³

¹Graduate School of Sustainable System Sciences, Osaka Metropolitan University, 1-1 Gakuencho, Sakai, Osaka 599-8531, Japan.

|February 26, 2026

Summary

This study developed an automated method using computer vision to monitor bumblebee activity in greenhouses. The new technique accurately counts bumblebee entries and exits, improving pollinator behavior analysis.

Keywords:

Algorithm Industrial camera Pollinator Strawberry YOLO

More Related Videos

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.

Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.

Published on: December 12, 2012

Related Experiment Videos

Last Updated: Feb 28, 2026

Radio Frequency Identification and Motion-sensitive Video Efficiently Automate Recording of Unrewarded Choice Behavior by Bumblebees

Radio Frequency Identification and Motion-sensitive Video Efficiently Automate Recording of Unrewarded Choice Behavior by Bumblebees

Published on: November 15, 2014

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.

Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.

Published on: December 12, 2012

Area of Science:

Agricultural Science
Entomology
Computer Vision

Background:

Bumblebees are vital for greenhouse pollination, particularly in strawberry cultivation.
Monitoring pollinator behavior is crucial for optimizing crop yields and understanding colony health.
Current methods for tracking insect activity can be labor-intensive and prone to error.

Purpose of the Study:

To develop and validate an automated system for monitoring bumblebee nest box entry and exit behavior.
To compare the performance of a novel algorithm-based detection method with a standard object detection model (YOLO).
To enhance the accuracy and efficiency of pollinator behavior analysis in controlled agricultural environments.

Main Methods:

Industrial cameras captured video footage of bumblebee activity at nest box entrances.
A virtual cube-shaped frame was implemented at the nest box entrance for tracking.
Bumblebee detection and counting were performed using YOLO, with a comparison between YOLO-only and YOLO with a simple algorithm for classifying entries/exits based on frame crossings.

Main Results:

The algorithm-based method significantly improved accuracy, precision, and F1 scores compared to the YOLO-only approach.
Automated counting of bumblebee entries and exits was successfully achieved.
The proposed method demonstrated superior performance in distinguishing true entries/exits from hesitations or re-entries.

Conclusions:

The developed automated method effectively supports the monitoring of bumblebee behavior in strawberry greenhouses.
This computer vision approach offers a more accurate and efficient alternative to manual observation for pollinator studies.
The findings contribute to improved management strategies for bumblebee pollination in protected agriculture.