TailSafe: A Pig Head-to-Rear Contact Detection System using Convolutional Neural Networks

Abstract

Pig tail biting poses significant challenges in pig farm monitoring, serving as an indicator of underlying pen issues. Existing monitoring methods are limited in their scalability and invasiveness. This study introduces TailSafe, a web-based decision support tool utilizing YOLOv5 and convolutional neural networks. TailSafe enables farmers to diagnose pig pen issues through potential tail biting outbreaks. Users upload pig pen images for processing, and the system provides results for contact presence classification and counts. TailSafe comprises two components: a detection method to identify pig heads and rears, and an interaction method to compute head-to-rear IoUs for contact identification.