The Scale Invariant Feature Transform, SIFT, has been successfully applied to robot localization. Still, the number of features extracted with this approach is immense, especially when dealing with omnidirectional vision. In this work, we propose a new approach that reduces the number of features generated by SIFT as well as their extraction and matching time. With the help of a particle filter, we demonstrate that we can still localize the mobile robot accurately with a lower number of features. 1.

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. 1

The Scale Invariant Feature Transform, SIFT, has been successfully applied to robot localization. Still, the number of features extracted with this approach is immense, especially when dealing with omnidirectional vision. In this work, we propose a new approach that reduces the number of features generated by SIFT as well as their extraction and matching time. With the help of a Particle Filter, we demonstrate that we can still localize the mobile robot accurately with a lower number of features