SIFT, SURF & seasons: Appearance-based long-term localization in outdoor environments

In this paper, we address the problem of outdoor, appearance-based topological localization, particularly over long periods of time where seasonal changes alter the appearance of the environment. We investigate a straightforward method that relies on local image features to compare single-image pairs. We first look into which of the dominating image feature algorithms, SIFT or the more recent SURF, that is most suitable for this task. We then fine-tune our localization algorithm in terms of accuracy, and also introduce the epipolar constraint to further improve the result. The final localization algorithm is applied on multiple data sets, each consisting of a large number of panoramic images, which have been acquired over a period of nine months with large seasonal changes. The final localization rate in the single-image matching, cross-seasonal case is between 80% to 95%.