Dynamics are Important for the Recognition of Equine Pain in Video
This work addresses the challenge of pain recognition in horses, which is crucial for animal welfare but difficult due to their tendency to hide pain, representing a novel application in machine learning with incremental improvements over existing methods.
The study tackled the problem of recognizing pain in non-verbal prey animals like horses by proposing a deep recurrent two-stream architecture for video-based pain detection, achieving results that surpass veterinary expert performance and outperform pain detection in other larger non-human species.
A prerequisite to successfully alleviate pain in animals is to recognize it, which is a great challenge in non-verbal species. Furthermore, prey animals such as horses tend to hide their pain. In this study, we propose a deep recurrent two-stream architecture for the task of distinguishing pain from non-pain in videos of horses. Different models are evaluated on a unique dataset showing horses under controlled trials with moderate pain induction, which has been presented in earlier work. Sequential models are experimentally compared to single-frame models, showing the importance of the temporal dimension of the data, and are benchmarked against a veterinary expert classification of the data. We additionally perform baseline comparisons with generalized versions of state-of-the-art human pain recognition methods. While equine pain detection in machine learning is a novel field, our results surpass veterinary expert performance and outperform pain detection results reported for other larger non-human species.