RT info:eu-repo/semantics/article
T1 Vision-Based Module for Herding with a Sheepdog Robot
A1 Riego Del Castillo, Virginia
A1 Sánchez González, Lidia
A1 Campazas Vega, Adrián
A1 Strisciuglio, Nicola
A2 Arquitectura y Tecnologia de Computadores
K1 Cibernética
K1 Computer vision
K1 Threat identification
K1 Wolf recognition
K1 Herding
K1 Sheepdog robots
K1 Precision livestock farming
K1 1207.03 Cibernética
K1 1203.04 Inteligencia Artificial
AB [EN] : Livestock farming is assisted more and more by technological solutions, such as robots.One of the main problems for shepherds is the control and care of livestock in areas difficult toaccess where grazing animals are attacked by predators such as the Iberian wolf in the northwestof the Iberian Peninsula. In this paper, we propose a system to automatically generate benchmarksof animal images of different species from iNaturalist API, which is coupled with a vision-basedmodule that allows us to automatically detect predators and distinguish them from other animals.We tested multiple existing object detection models to determine the best one in terms of efficiencyand speed, as it is conceived for real-time environments. YOLOv5m achieves the best performanceas it can process 64 FPS, achieving an mAP (with IoU of 50%) of 99.49% for a dataset where wolves(predator) or dogs (prey) have to be detected and distinguished. This result meets the requirementsof pasture-based livestock farms.
PB MDPI
LK https://hdl.handle.net/10612/20410
UL https://hdl.handle.net/10612/20410
NO Riego Del Castillo, V., Sánchez-González, L., Campazas-Vega, A., & Strisciuglio, N. (2022). Vision-Based Module for Herding with a Sheepdog Robot. Sensors (Basel, Switzerland), 22(14). https://doi.org/10.3390/S22145321
DS BULERIA. Repositorio Institucional de la Universidad de León
RD Jul 8, 2024