RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación
Artículo científico (JournalArticle)
Evaluation of Multi-Object Detection models for automated goat behavior identification in intensive farming facilities
[EN] Computer vision offers significant potential for the continuous, stress-free, and cost-effective monitoring of animal behavior, yet its application in goat farming remains limited. In this study, a Multi-Object Detection (MOD) model was developed to classify goat behavior into four categories: eating, standing, drinking, and lying. Zenithal videos were recorded under both light and dark conditions on an experimental goat farm, resulting in 10740 labelled annotations used to train, validate, and test 13 models leveraging Transformer- and CNN-based pretrained architectures. YOLO-based models (YOLOv8 and YOLOX) achieved the highest overall performances across both large and lightweight versions, demonstrating high detection capability and potential suitability for hardwareconstrained scenarios. YOLOX-based MOD model is identified as the most suitable for goat behavior detection due to its superior classification accuracy, fast inference speed, and fully open-source license, enabling flexible customization, deployment, and reproducibility. Other models, particularly DAB-DETR and H-DINO, underperformed, especially in detecting drinking behavior, which represents the most challenging class due to its visual similarity with standing, class imbalance, and fisheye distortion effects that affect the frame regions where drinkers are located. Mitigation strategies, including focal loss and distortion correction, improved detection accuracy for this class and reduced performance variability. The developed MOD model can be deployed for continuous group-level monitoring of goats, paving the way for scalable and efficient solutions for advanced behavioral analyses. Future works will focus on integrating tracking algorithms for animal-level insights, as well as on evaluating model generalizability across different farming conditions and goat breeds., This work was supported by the "Ayuda a Primeros Proyectos de Investigacion" program [grant number PAID-06-23] , Vice-rectorate for Research of Universitat Politecnica de Valencia (UPV) . Andrea Costantino was supported by the grant JDC2022-049782-I funded by MICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR. Daniel Alexander Mendez was supported by R+D+i project TED2021-130759B-C31, funded by MCIN/AEI/10.13039/501100011033/and by the "European Union NextGenerationEU/PRTR" and by the grant JDC2023-050534-I funded by MICIU/AEI/10.13039/501100011033 and for FSE+. Eliseo Gil Vidal was supported by PLF4ALL project (CIAICO/2021/212, Generalitat Valenciana).