Topological SLAM using a graph-matching based method on omnidirectional images

Abstract

Image feature extraction and matching is useful in many areas of robotics such as object and scene recognition, autonomous navigation, SLAM and so on. This paper describes a new approach to the problem of matching features and its application in scene recognition and topological SLAM. For that purpose we propose a previous image segmentation into regions in order to group the extracted features in a graph so that each graph defines a single region of the image. The matching process will take into account the features and the structure (graph) using the GTM algorithm. Then, using this method of comparing images, we propose an algorithm to construct topological maps. During the experimentation phase we will test the robustness of the method and its ability constructing topological maps.