Image-based localization for AIBO using wavelet transform
Alberto Pretto, Emanuele Menegatti, Enrico Pagello, Yoshiaki Jitsukawa, Ryuichi Ueda and Tamio Arai
The 10th Congress of the Italian Association for Artificial Intelligence - Special Track on AI and Robotics
Roma, Italy, September 10-13, 2007
Abstract
This paper describes a new way to calculate the similarity between images to be used in the image-based localization approach on autonomous robots with low computational resources. We propose a novel signature to be extracted from the image and to be stored in memory instead of the image itself. The proposed signature allows, at the same time, memory saving and fast similarity calculation. The signature is based on the calculation of the 2D Haar Wavelet Transform of the gray-level image. This work has been carried out using the AIBOs ERS-7 of the RoboCup Team Araibo of the University of Tokyo. AIBO is fitted with a perspective camera, so we developed a technique that minimizes the number of images to be collected as reference images and that can be performed by the AIBO in a semi-autonomous way. We present experiments showing the effectiveness of the proposed image similarity measure. The used images were collected on a RoboCup field, however, the proposed image similarity measure does not use any information on the structure of the environment and do not exploit the peculiar features of the RoboCup environment. This will lead to the development of an image similarity measure for image-based localization in a general environment for AIBO robots.