Paper Info
Title
Appearance Based Indexing for Relocalisation in Real-Time Visual SLAM
Abstract
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 effi- cient relocalisation. Results of experiments on a range of real world test cases demonstrate that the method is effective, including single frame relocalisa- tion rates up to 90% using relatively low numbers of descriptor comparisons.
Year
DOI
Venue
2008
10.5244/C.22.37
BMVC
Keywords
Field
DocType
real time systems,indexation
Computer vision,Pattern recognition,Computer science,Search engine indexing,Appearance based,Robustness (computer science),Test case,Artificial intelligence,Haar wavelet
Conference
Citations 
PageRank 
References 
22
1.03
13
Authors
3
Name
Order
Citations
PageRank
Denis Chekhlov116410.61
Walterio W. Mayol-cuevas249748.81
Andrew Calway364554.66