Previous work on visual SLAM has shown that indexing on space and scale facilitates the use of feature descriptors for matching in real-time systems and that this can significantly increase robustness. However, the performance gains necessarily diminish as uncertainty about camera position increases. In this paper we address this issue by introducing a further level of indexing based on appearance, using low order Haar wavelet coefficients. This enables fast look up of descriptors even when the camera is lost, hence allowing efficient relocalisation. Results of experiments on a range of real world test cases demonstrate that the method is effective, including single frame relocalisation rates up to 90\% using relatively low numbers of descriptor comparisons.
|Translated title of the contribution||Appearance Based Indexing for Relocalisation in Real-Time Visual SLAM|
|Title of host publication||19th British Machine Vision Conference|
|Number of pages||10|
|Publication status||Published - Sep 2008|
Bibliographical noteISBN: 9781901725360
Name and Venue of Conference: 19th Bristish Machine Vision Conference
Other identifier: 2000939