Resumen de Handle identification by keypoint extraction

Ekaitz Jauregi , José María Martínez Otzeta , Basilio Sierra Araujo , Elena Lazkano Ortega

• Door identification is a key problem to be solved during mobile robot navigation. Doors give access to many locations that are defined as goals for the robot. This paper presents an approach to door identification by means of recognition of the door handle. Rather than using the lines defined by the door blades, the region of interest of an image is extracted by means of the Hough transform and afterwards keypoints are obtained and matched against a database in order to positively recognize the door. The keypoint extraction is performed using three different methods, SIFT, SURF and its upright variant USURF, that are compared in terms of different performance measures. The approach is evaluated and tested on a real PeopleBot robot.