Enhancing pollinator conservation: monitoring of bees through object recognition

Alex, AJ, Barnes, CM, Machado, P ORCID: https://orcid.org/0000-0003-1760-3871, Ihianle, I ORCID: https://orcid.org/0000-0001-7445-8573, Markó, G, Bencsik, M ORCID: https://orcid.org/0000-0002-6278-0378 and Bird, JJ ORCID: https://orcid.org/0000-0002-9858-1231, 2025. Enhancing pollinator conservation: monitoring of bees through object recognition. Computers and Electronics in Agriculture, 228: 109665. ISSN 0168-1699

Preview

Text 2304960_Bird.pdf - Published version Download (4MB) | Preview

Abstract

In an era of rapid climate change and its adverse effects on food production, technological intervention to monitor pollinator conservation is of paramount importance for environmental monitoring and conservation for global food security. The survival of the human species depends on the conservation of pollinators. This article explores the use of Computer Vision and Object Recognition to autonomously track and report bee behaviour from images. A novel dataset of 9664 images containing bees is extracted from video streams and annotated with bounding boxes. With training, validation and testing sets (6722, 1915, and 997 images, respectively), the results of the COCO-based YOLO model fine-tuning approaches show that YOLOv5 m is the most effective approach in terms of recognition accuracy. However, YOLOv5s was shown to be the most optimal for real-time bee detection with an average processing and inference time of 5.1 ms per video frame at the cost of slightly lower ability. The trained model is then packaged within an explainable AI interface, which converts detection events into timestamped reports and charts, with the aim of facilitating use by non-technical users such as expert stakeholders from the apiculture industry towards informing responsible consumption and production.

Item Type:	Journal article
Publication Title:	Computers and Electronics in Agriculture
Creators:	Alex, A.J., Barnes, C.M., Machado, P., Ihianle, I., Markó, G., Bencsik, M. and Bird, J.J.
Publisher:	Elsevier
Date:	January 2025
Volume:	228
ISSN:	0168-1699
Identifiers:	Number Type 10.1016/j.compag.2024.109665 DOI S0168169924010561 Publisher Item Identifier 2304960 Other
Rights:	© 2024 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Divisions:	Schools > School of Science and Technology
Record created by:	Melissa Cornwell
Date Added:	20 Mar 2025 16:07
Last Modified:	20 Mar 2025 16:07
URI:	https://irep.ntu.ac.uk/id/eprint/53274

Actions (login required)

Edit View

Statistics

Views

Downloads