Local visual homing by warping of two-dimensional images

Local visual homing methods can be used in the context of topological maps to travel between neighboring locations. These methods take two images as input and produce a home vector that points from the vantage point of one image to that of the other. “Warping” (Franz et al., Biol. Cyb. 79:191-202, 1998) is an attractive homing method since it does not require an external compass. Here we describe how the performance of warping can be substantially improved by extending the method from oneto two-dimensional images, with only a moderate increase in the computational effort. Experiments on several image databases confirm the improved performance.