Edge-computing and Deep Learning Integration for Real-time, High-resolution Monitoring of Apis cerana cerana Fabricius Entrance Traffic
DOI:
https://doi.org/10.13102/sociobiology.v73i3.12729Keywords:
Video monitoring, object detection, multi-object tracking, precision apicultureAbstract
Continuous monitoring of honey bee (Apis cerana cerana Fabricius) entrance traffic is essential for evaluating colony health and foraging dynamics in precision apiculture. Existing vision-based systems struggle to balance high spatiotemporal resolution, real-time processing capabilities, and cost-effective field deployment. We developed a low-cost, standalone edge-computing framework that integrates a 60-fps global-shutter camera with an Orange Pi 5B single-board computer. Using a PP-YOLOE+ object detection model (mean Average Precision at IoU threshold 0.5 of 0.95) coupled with the ByteTrack algorithm, the system performs robust, real-time multi-object tracking and directional counting locally at 35 fps. A 30-day continuous field deployment across three colonies successfully processed over two million entry and exit events, yielding a Multiple Object Tracking Accuracy of 77.8%. Subsequent biological analysis of this dataset revealed synchronized bimodal diurnal foraging rhythms across multiple colonies, indicating that shared environmental factors strongly influenced foraging behaviors. By maintaining stable analytical accuracy on affordable hardware without relying on continuous cloud processing, this system provides a scalable, non-invasive solution for automated colony assessment and data-driven precision apiculture.
Downloads
References
Alex, A.J., Barnes, C.M., Machado, P., Ihianle, I., Markó, G., Bencsik, M. & Bird, J.J. (2025). Enhancing pollinator conservation: Monitoring of bees through object recognition. Computers and Electronics in Agriculture, 228: 109665.
Amin, S.U., Hussain, A., Kim, B. & Seo, S. (2023). Deep learning-based active learning technique for data annotation and improve the overall performance of classification models. Expert Systems with Applications, 228: 120391.
Borlinghaus, P., Odemer, R., Tausch, F., Schmidt, K. & Grothe, O. (2022). Honey bee counter evaluation – Introducing a novel protocol for measuring daily loss accuracy. Computers and Electronics in Agriculture, 197: 106957.
Bozek, K., Hebert, L., Portugal, Y., Mikheyev, A.S. & Stephens, G.J. (2021). Markerless tracking of an entire honey bee colony. Nature Communications, 12: 1733.
Chen, W.S., Wang, C.H., Jiang, J.A. & Yang, E.C. (2015). Development of a monitoring system for honeybee activities. In: Proceedings of the 9th International Conference on Sensing Technology, Auckland, New Zealand, pp. 745-750.
Hadjur, H., Ammar, D. & Lefèvre, L. (2022). Toward an intelligent and efficient beehive: A survey of precision beekeeping systems and services. Computers and Electronics in Agriculture, 192: 106604.
Kimura, T., Ohashi, M., Crailsheim, K., Schmickl, T., Okada, R., Radspieler, G. & Ikeno, H. (2014). Development of a new method to track multiple honey bees with complex behaviors on a flat laboratory arena. PLoS ONE, 9: e84656.
Kulyukin, V.A. & Kulyukin, A.V. (2023). Accuracy vs. energy: An assessment of bee object inference in videos from on-hive video loggers with YOLOv3, YOLOv4-Tiny, and YOLOv7-Tiny. Sensors, 23: 6791.
Ratnayake, M.N., Dyer, A.G. & Dorin, A. (2021). Tracking individual honeybees among wildflower clusters with computer vision-facilitated pollinator monitoring. PLoS ONE, 16: e0239504.
Rodriguez, I.F., Chan, J., Alvarez Rios, M., Branson, K., Agosto-Rivera, J.L., Giray, T. & Mégret, R. (2022). Automated video monitoring of unmarked and marked honey bees at the hive entrance. Frontiers in Computer Science, 3: 769338.
Zheng, Y., Cao, X., Xu, S., Guo, S., Huang, R., Li, Y., Chen, Y., Yang, L., Cao, X., Idrus, Z. & Sun, H. (2024). Intelligent beehive monitoring system based on internet of things and colony state analysis. Smart Agricultural Technology, 9: 100584.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Jia-Xu Wu, Hao-Yu Han, Han-Jun Liu, Yi-Xian Guo, Jing-Lin Gao, Shan Zhao, Shi-Jie Wang
This work is licensed under a Creative Commons Attribution 4.0 International License.
Sociobiology is a diamond open access journal which means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles in this journal without asking prior permission from the publisher or the author. This is in accordance with the BOAI definition of open access.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
eISSN 2447-8067
