Experimental Analysis of Animal Behavior for Biomedical Applications
Authors:
- Florin RotaruFRFlorin Rotaru
- Silviu-Ioan BejinariuSilviu-Ioan Bejinariu
- Hariton-Nicolae CostinHariton-Nicolae Costin
- Ramona LucaRLRamona Luca
- Mihaela LucaMLMihaela Luca
- Cristina Diana NitaCNCristina Diana Nita
- Diana CostinDCDiana Costin
- Bogdan-Ionel TambaBTBogdan-Ionel Tamba
- Ivona CostachescuICIvona Costachescu
- Gabriela-Dumitrita StanciuGabriela-Dumitrita Stanciu
- Gabriela-Gladiola PetroiuGPGabriela-Gladiola Petroiu
Open Access
- 2 May 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (9) , 4488
Abstract
This study addresses the problem of robust video-based tracking of laboratory rats in open-field and Y-maze experiments under challenging acquisition conditions, including non-uniform illumination, low contrast, and heterogeneous recording setups. Existing approaches based on classical image processing or deep learning often fail to maintain stable localization under such conditions or require large, annotated datasets. We propose a hybrid tracking framework that combines an improved motion–appearance voting mechanism with consistency-constrained optimization for open-field experiments, together with a comparative deep learning-based detection strategy for Y-maze analysis. The proposed method introduces (i) adaptive dual-threshold motion extraction, (ii) directionally constrained temporal validation, and (iii) a robustness-driven fusion of motion and appearance cues. Experimental results demonstrate that the proposed approach achieves reliable tracking with a maximum localization error below 10 pixels under severe illumination variations. In the Y-maze scenario, a comparative evaluation of multiple detectors (YOLOv5, YOLOv9, YOLO12, Faster R-CNN) highlights the trade-off between accuracy and inference time, with YOLOv9 providing the best balance. The main contribution consists of enabling robust behavioral quantification in low-quality experimental conditions using limited training data, bridging the gap between classical tracking robustness and deep learning flexibility.Keywords
This publication has 27 references indexed in Scilit:
- Animal behavior analysis methods using deep learning: A surveyExpert Systems with Applications, 2025
- Computer Vision – ECCV 20242025
- Enhancing keypoint detection in Y-Maze behavior test automation: introducing stadium heatmap and squared adaptive wing lossMultimedia Tools and Applications, 2024
- Computational modeling of animal behavior in T-mazes: Insights from machine learningEcological Informatics, 2024
- A deep learning-based approach for real-time rodent detection and behaviour classificationMultimedia Tools and Applications, 2022
- A review of behavioral methods for the evaluation of cognitive performance in animal models: Current techniques and links to human cognitionPhysiology & Behavior, 2022
- Behavioral tests in rodent models of strokeBrain Hemorrhages, 2020
- Brain development in rodents and humans: Identifying benchmarks of maturation and vulnerability to injury across speciesProgress in Neurobiology, 2013
- A systematic analysis of performance measures for classification tasksInformation Processing & Management, 2009
- Stress, behavioral arousal, and open field activity—A reexamination of emotionality in the ratNeuroscience & Biobehavioral Reviews, 1979