Vision-Based Module for Herding with a Sheepdog Robot

Virginia Riego Del Castillo, Lidia Sánchez-González*, Adrián Campazas-Vega, Nicola Strisciuglio

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

7 Citations (Scopus)
36 Downloads (Pure)

Abstract

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.

Original languageEnglish
Article number5321
JournalSensors (Basel, Switzerland)
Volume22
Issue number14
DOIs
Publication statusPublished - 16 Jul 2022

Keywords

  • computer vision
  • herding
  • precision livestock farming
  • sheepdog robots
  • threat identification
  • wolf recognition

Fingerprint

Dive into the research topics of 'Vision-Based Module for Herding with a Sheepdog Robot'. Together they form a unique fingerprint.

Cite this