PlayClass: Automated Play Behaviour Classification in Poultry

2026-05-26

AI Summary

This study addresses the prevailing focus on negative indicators in automated animal welfare monitoring by introducing a novel approach to recognizing positive behaviors—specifically, play in poultry. The work proposes a top-view video–based classification pipeline that, for the first time, integrates frozen image and video foundation models for this purpose. It employs a three-stage chunked long-term tracking strategy guided by YOLO-informed SAM to mitigate identity confusion and combines handcrafted motion features with V-JEPA 2.1 video embeddings. Evaluated across multiple model scales, the method achieves state-of-the-art performance with a macro-averaged F₁ score of 77.0, significantly advancing the automated assessment of positive animal behaviors.

Abstract

Automated monitoring of animal welfare has largely targeted negative indicators, leaving positive welfare behaviours such as play underexplored. To address this gap, we present PlayClass, a pipeline for play-behaviour classification in poultry from top-down pen video. The pipeline leverages long-duration tracking with SAM 3 via YOLO-guided chunk boundaries to minimise identity errors in point-based prompting, and frozen embeddings from image and video foundation models for play action classification. Although handcrafted motion features from tracked masks alone achieved competitive accuracy, V-JEPA 2.1 consistently outperformed all other backbones across model scales, reaching 77.0 macro-averaged F$_1$ when combined with handcrafted features. Despite this result, the dataset remains challenging due to play sub-types sharing similar kinematic profiles with non-play and inter-bird occlusion. Overall, our work provides encouraging evidence towards automated frameworks for play behaviour classification in poultry.

Problem

• animal welfare
• play behaviour
• poultry
• automated monitoring
• positive welfare

Innovation

• play behaviour classification
• foundation models
• long-duration tracking
• animal welfare monitoring
• V-JEPA