Using Scale Space Image Histograms for Global Localization of Mobile Robots

The scale invariant feature transform and the integral invariants are two well known approaches for visual feature extraction. Each of these approaches has been successfully applied to global localization of mobile robots. In this paper, we propose applying a combination of the two concepts. We demonstrate that extracting the integral invariants from the scale space does indeed improve the localization accuracy. We also show that the computation time of the proposed approach is much less than the scale invariant feature transform.