HIDDEN MARKOV RANDOM FIELD, AN APPLICATION TO RAILWAY INFRASTRUCTURE DIAGNOSIS

Abstract

Hidden Markov Random Fields (HMRF) are widely used in solving various problems. Image segmentation is an example of such HMRF success. This paper presents a post-processing tool based on such a model and designed to increase the relevancy of a diagnosis system for rail defects detection. In this application, the hidden Markov field is not only used to define a spatial smoothness prior as it is often done in image segmentation, but it is used to learn the spatial interaction between track singular points, and so the track label patterns. For this, an approach based on a semi-parametric model is presented.