Beyond Proximity: A Keypoint-Trajectory Framework for Classifying Affiliative and Agonistic Social Networks in Dairy Cattle

TL;DR

This paper introduces a pose-based computational framework that classifies social interactions in dairy cattle by analyzing keypoint trajectories, surpassing proximity-based methods and enabling better welfare monitoring.

Contribution

It presents an innovative, end-to-end vision pipeline that models spatiotemporal keypoint geometry to distinguish social interaction valence in cattle.

Findings

Achieved 77.51% accuracy in classifying social behaviors.

Outperformed proximity-only baselines in behavioral discrimination.

Demonstrated near-real-time performance on standard hardware.

Abstract

Precision livestock farming requires objective assessment of social behavior to support herd welfare monitoring, yet most existing approaches infer interactions using static proximity thresholds that cannot distinguish affiliative from agonistic behaviors in complex barn environments. This limitation constrains the interpretability of automated social network analysis in commercial settings. We present a pose-based computational framework for interaction classification that moves beyond proximity heuristics by modeling the spatiotemporal geometry of anatomical keypoints. Rather than relying on pixel-level appearance or simple distance measures, the proposed method encodes interaction-specific motion signatures from keypoint trajectories, enabling differentiation of social interaction valence. The framework is implemented as an end-to-end computer vision pipeline integrating YOLOv11 for object detection (mAP@0.50: 96.24%), supervised individual identification (98.24% accuracy), ByteTrack for multi-object tracking (81.96% accuracy), ZebraPose for 27-point anatomical keypoint estimation, and a support vector machine classifier trained on pose-derived distance dynamics. On annotated interaction clips collected from a commercial dairy barn, the classifier achieved 77.51% accuracy in distinguishing affiliative and agonistic behaviors using pose information alone. Comparative evaluation against a proximity-only baseline shows substantial gains in behavioral discrimination, particularly for affiliative interactions. The results establish a proof-of-concept for automated, vision-based inference of social interactions suitable for constructing interaction-aware social networks, with near-real-time performance on commodity hardware.