Horse Eye Blink Detection and Classification for Equine Affective State Assessment
This work addresses the need for automated detection of subtle equine facial action units to assess pain and stress in horses, a domain-specific problem with limited prior work.
The authors developed and evaluated three methods for automated blink classification from horse videos, achieving a macro-F1 score of 0.898 for blink classification and 0.926 for binary blink detection, demonstrating potential for equine welfare monitoring.
Automated detection of equine facial action units (AUs) is a promising yet under-explored avenue for pain and affective state assessment in horses. Half and full-blink movements are recognised indicators of pain and stress, but as micro-expressions, their subtle, fine-grained nature makes them easily missed by the naked eye and only discernible through frame-by-frame video inspection, making reliable automated detection from video a particularly demanding task. We develop and evaluate three methods for automated blink classification from horse videos: a frame-based YOLOv12 detector, an optical flow magnitude thresholding approach, and a fine-tuned VideoMAE model, tested on a publicly available dataset. We achieve a macro-F1 score of 0.898 when doing blink classification and 0.926 on binary blink detection. Our results highlight both the potential and the inherent challenges of fine-grained AU detection for equine welfare monitoring.