Development and Validation of an Automated Video Tracking Model for Stabled Horses

SIMPLE SUMMARY: Although there are some methods to detect pain in horses, because of bias and time-consumption, those methods are practically challenging. However, in recent years rapidly developed automated tracking methods have proven that computer-based behaviour monitoring is more reliable in many animal species. That is why in this study we aimed to investigate an automated video tracking model for horses in a clinical context. The findings will help to develop the automated detection of daily activity, to meet the ultimate objective of objectively assessing the pain and wellbeing of horses. An initial analysis of the obtained data offers the opportunity to construct an algorithm to track automatically behaviour patterns of horses. ABSTRACT: Changes in behaviour are often caused by painful conditions. Therefore, the assessment of behaviour is important for the recognition of pain, but also for the assessment of quality of life. Automated detection of movement and the behaviour of a horse in the box stall should represent a significant advancement. In this study, videos of horses in an animal hospital were recorded using an action camera and a time-lapse mode. These videos were processed using the convolutional neural network Loopy for automated prediction of body parts. Development of the model was carried out in several steps, including annotation of the key points, training of the network to generate the model and checking the model for its accuracy. The key points nose, withers and tail are detected with a sensitivity of more than 80% and an error rate between 2 and 7%, depending on the key point. By means of a case study, the possibility of further analysis with the acquired data was investigated. The results will significantly improve the pain recognition of horses and will help to develop algorithms for the automated recognition of behaviour using machine learning.