Decoding animal health: Computer vision approaches to motion and emotional states in animals

Animal body conformation plays an important role in health and athletic performance across species. The selective breeding process, introduced by humans in modern domestication, has shaped animal bodies to achieve visually appealing traits or functional specialisation. But these modifications can create predispositions to health issues that are challenging to detect. Assessment of body conformation, pose, and motion provides valuable insights into health parameters and forms a cornerstone of the veterinary clinical examination. However, traditional assessment methods face significant limitations: they are subjective, prone to human bias, constrained by the visual limitations of observers, and often lack robust evidence-based associations between observed deviations and underlying pathology. Recent computer vision methodologies offer potentially transformative solutions to these challenges. We will explore some examples of how keypoint tracking methods and parametric models can assist veterinarians and animal owners in detecting subtle signs of disease. The veterinary world can expect a technological shift, where the use of computer vision can offer objective, quantifiable measurements that enable earlier intervention and more precise health monitoring.