Edge-based features from omnidirectional images for robot localization

Abstract

We propose a method for extracting low-dimensional features from omnidirectional images to be used for robot localization and navigation. Edge detection is combined with thresholding to locate sharp edge pixels, the coordinates of which are fed into a Parzen density estimator (1962) to compute the edge spatial density. The use of the fast Fourier transform makes this density estimate feasible in real-time, while principal component analysis further drops the dimensionality of the resulting feature vector to a manageable number. We show experimental results from a Nomad XR4000 robot in an office environment.