Analysis of Motion Patterns for Pain Estimation of Horses

Abstract

This paper focuses on the automated analysis of motion patterns for relating an individual's behaviour with its pain experience. Reliable, automated behaviour analysis can improve video observation considerably, i.e. by lessening the work load of human operators, decreasing human error and by increasing anonymity and privacy. Possible applications are observation of traffic, public places and public transport. A new potential application is the early detection of pathologically relevant events, e.g. animal diseases (e.g. colics in horses), the automated post-surgical pain assessment of animals and similar applications. The challenge in the horses scenario is that they are flight animals that can not afford much of visible pain behaviour.

Our approach is built on top of state of the art methods for object detection and tracking. From the object motion we derive motion patterns and respective features which we analyse by machine-learning methods. In the this paper we will present atypical behaviour detection (i.e. pain estimation) in animal videos, for which we have acquired a large video database. It could be shown that the condition of the horse can be analysed and classified by means of local histograms.