PUB - Publikationen an der Universität Bielefeld

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" [M.O. Franz, B. Scholkopf, H.A. Mallot, H.H. Bulthoff, Where did I take that snapshot? Scene-based homing by image matching, Biological Cybernetics 79 (3) (1998) 191-202] 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 one- to two-dimensional images, with only a moderate increase ill the computational effort. Experiments on several image databases confirm the improved performance. (c) 2008 Elsevier B.V. All rights reserved.