Testing Image Segmentation for Topological SLAM with Omnidirectional Images

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 to scene recognition and topological SLAM. For that purpose we propose a prior 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. We compare two basic methods for image segmentation, in order to know the effect of segmentation in the result. We have also extend the initial segmentation algorithm in order to take into account the circular characteristics of the omnidirectional image. The matching process will take into account the features and the structure (graph) using the GTM algorithm, modified to take into account the cylindrical structure of omnidirectional images. Then, using this method of comparing images, we propose an algorithm for constructing topological maps. During the experimentation phase we will test the robustness of the method and its ability to construct topological maps. We have also introduced a new hysteresis behavior in order to solve some problems found in the graph construction.