Vol. 10, No 2: 40–49.

Computer and Information Sciences

2025

Scientific article

UDK 004.032.26:591.5(470.22)

pdf-version

Grigory A. Bondar
bachelor's degree, Petrozavodsk State University
(Petrozavodsk, Russia),
g4bondar@gmail.com
Nikita S. Kuleznev
bachelor's degree, Petrozavodsk State University
(Petrozavodsk, Russia),
kuleznevnik.34@gmail.com

Developing a Service for Detecting Animals in Photographs

Scientific adviser:
Vyacheslav M. Dimitrov
Reviewer:
Aleksandr A. Kuzmenkov
Paper submitted on: 06/02/2025;
Accepted on: 06/29/2025;
Published online on: 06/29/2025.
Abstract. Automating the detection of animals in camera trap photographs is a significant challenge in ecological research. This study aims to develop a web service for the automatic identification of fauna representatives native to Karelia. The research methodology involved compiling a dataset of 6,706 images of animals, training the YOLOv11 neural network model for object recognition, and designing a web interface integrated with the "Smart Ecosystems. Monitoring 4.0" platform. The results demonstrate the successful implementation of an automated system for processing camera trap data — from image acquisition to web-based visualization — for efficient biodiversity monitoring.
Keywords: computer vision, YOLOv11, object detection, ecosystem monitoring, camera traps, animal recognition

For citation: Bondar, G. A., Kuleznev, N. S. Developing a Service for Detecting Animals in Photographs. StudArctic forum. 2025, 10 (2): 40–49.

References

Bondar G.A., Kuleznev N.S., et al. Developing a service for detecting animals in photographs. Digital technologies in education, science, and society: Proceedings of the XVIII all-Russian scientific and practical conference (Petrozavodsk, December 3–5, 2024). Petrozavodsk, Petrozavodsk State University, 2024, pp. 18-21. (In Russ.)

Danilov P.I., Belkin V.V. Mammals of Karelia. Petrozavodsk, Karelian Research Centre of the Russian Academy of Sciences, 2011, 264 p. (In Russ.)

Shapiro L., Stockman G. Computer vision. Moscow, BINOM. Laboratoriya znaniy, 2013, 752 p. (In Russ.)

LeCun Y., Bengio Y., et al. Deep learning. Nature, 2015, Vol. 521, No. 7553, pp. 436-444. DOI: 10.1038/nature14539

Norouzzadeh M.S., Nguyen A., et al. Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning. Proceedings of the National Academy of Sciences, 2018, Vol. 115, No. 25, pp. E5716-E5725. DOI: 10.1073/pnas.1719367115

Redmon J.,  Divvala S., et al. You only look once: unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Institute of Electrical and Electronics Engineers, 2016, pp. 779-788. DOI: 10.1109/CVPR.2016.91

Displays: 93; Downloads: 26;