Door-detection using computer vision and fuzzy logic ∗

Abstract: One of the existing methods to perform the navigation in indoor environments consists in using a topological map in combination with appropriate behaviours. Door is a very common element in this kind of environments and its detection can be very useful either to know the environment structure, to aid an exploration task and to perform an efficient navigation. In this work we use the information provided by the camera of a robot to assign a belief degree on the existence of a door in it. The segments of the images captured are analyzed in order to detect those segments that could belong to the frame of a door. Several fuzzy concepts are defined to lead the search process and find different cases in which doors can be seen. Features of the segments like size, direction or the distance between them are measured and analyzed using fuzzy logic in order to establish a membership degree of the segments on the defined fuzzy concepts. The proposed method has proved to successfully detect typical doors of indoor environments under strong perspective deformations using grey-level images. Furthermore, according to our experimentation it is suitable for real-time applications in mobile robots. Key-Words: Mobile robot, Robot vision, Robot navigation, Perceptual fuzzy models, Computer vision.