TY - JOUR
T1 - Vision-Based Module for Herding with a Sheepdog Robot
AU - Riego Del Castillo, Virginia
AU - Sánchez-González, Lidia
AU - Campazas-Vega, Adrián
AU - Strisciuglio, Nicola
N1 - Funding Information:
The APC was funded by Universidad de León.
Publisher Copyright:
© 2022 by the authors.
PY - 2022/7/16
Y1 - 2022/7/16
N2 - 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 to access where grazing animals are attacked by predators such as the Iberian wolf in the northwest of the Iberian Peninsula. In this paper, we propose a system to automatically generate benchmarks of animal images of different species from iNaturalist API, which is coupled with a vision-based module 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 efficiency and speed, as it is conceived for real-time environments. YOLOv5m achieves the best performance as 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 requirements of pasture-based livestock farms.
AB - 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 to access where grazing animals are attacked by predators such as the Iberian wolf in the northwest of the Iberian Peninsula. In this paper, we propose a system to automatically generate benchmarks of animal images of different species from iNaturalist API, which is coupled with a vision-based module 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 efficiency and speed, as it is conceived for real-time environments. YOLOv5m achieves the best performance as 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 requirements of pasture-based livestock farms.
KW - computer vision
KW - herding
KW - precision livestock farming
KW - sheepdog robots
KW - threat identification
KW - wolf recognition
UR - http://www.scopus.com/inward/record.url?scp=85135115894&partnerID=8YFLogxK
U2 - 10.3390/s22145321
DO - 10.3390/s22145321
M3 - Article
C2 - 35891009
AN - SCOPUS:85135115894
SN - 1424-8220
VL - 22
JO - Sensors (Basel, Switzerland)
JF - Sensors (Basel, Switzerland)
IS - 14
M1 - 5321
ER -