Abstract

Timely detection of horse pain is important for equine welfare. Horses express pain through their facial and body behavior, but may hide signs of pain from unfamiliar human observers. In addition, collecting visual data with detailed annotation of horse behavior and pain state is both cumbersome and not scalable. Consequently, a pragmatic equine pain classification system would use video of the unobserved horse and weak labels. This paper proposes such a method for equine pain classification by using multi-view surveillance video footage of unobserved horses with induced orthopaedic pain, with temporally sparse video level pain labels. To ensure that pain is learned from horse body language alone, we first train a self-supervised generative model to disentangle horse pose from its appearance and background before using the disentangled horse pose latent representation for pain classification. To make best use of the pain labels, we develop a novel loss that formulates pain classification as a multi-instance learning problem. Our method achieves pain classification accuracy better than human expert performance with 60% accuracy. The learned latent horse pose representation is shown to be viewpoint covariant, and disentangled from horse appearance. Qualitative analysis of pain classified segments shows correspondence between the pain symptoms identified by our model, and equine pain scales used in veterinary practice.

Keywords

Visualization; Computer vision; Analytical models; Pain; Annotations; Surveillance; Computational modeling; Action and Behavior Recognition Vision for Animals

Published in

Title: 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
ISBN: 978-1-6654-0915-5, eISBN: 978-1-6654-0915-5
Publisher: The Institute of Electrical and Electronics Engineers

Conference

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 03-08 January 2022, Hawaii, USA

SLU Authors

• Ask, Katrina

  • Department of Animal Biosciences, Swedish University of Agricultural Sciences
    

• Hernlund, Elin

  • Department of Animal Biosciences, Swedish University of Agricultural Sciences
    

• Haubro Andersen, Pia

  • Department of Animal Biosciences, Swedish University of Agricultural Sciences
    

UKÄ Subject classification

Computer Vision and Robotics (Autonomous Systems)
Medical Bioscience


Publication identifier

DOI: https://doi.org/10.1109/WACV51458.2022.00023

Permanent link to this page (URI)

https://res.slu.se/id/publ/118991