Visual Learning for Landmark Recognition

Recognizing landmark is a critical task for mobile robots. Landmarks are used for robot positioning, and for building maps of unknown environments. In this context, the traditional recognition techniques based on strong geometric models cannot be used. Rather, models of landmarks must be built from observations using image-based visual learning techniques. Beyond its application to mobile robot navigation, this approach addresses the more general problem of identifying groups of images with common attributes in sequences of images. We show that, with the appropriate domain constraints and image descriptions, this can be done using efficient algorithms as follows: Starting with a "training" sequence of images, we identify groups of images corresponding to distinctive landmarks. Each group is described by a set of feature distributions. At run-time, the observed images are compared with the sets of models in order to recognize the landmarks in the input stream.