Rover localization in natural environments by indexing panoramic images
- 25 June 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1365-1370
- https://doi.org/10.1109/robot.2002.1014733
Abstract
In this paper, we present an approach to qualitative rover lo- calization with panoramic images. The approach relies on the possibility to efficiently and robustly compute the resemblance between panoramic images, indexing them by histograms of local appearances. A database of image indexes is dynami- cally built during rover motions: when the rover re-perceives an already crossed area, it matches the current image with the stored ones (place recognition), and thus gets a qualitative es- timate of its position. Experimental results on a 400 images database illustrates the algorithms throughout the paper.Keywords
This publication has 12 references indexed in Scilit:
- Image-based memory of environmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Object indexing using an iconic sparse distributed memoryPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Robust localization using context in omnidirectional imagingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Recursive implementation of the Gaussian filterPublished by Elsevier ,2000
- Recognition without Correspondence using Multidimensional Receptive Field HistogramsInternational Journal of Computer Vision, 2000
- A structured probabilistic model for recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Spatial Color Indexing and ApplicationsInternational Journal of Computer Vision, 1999
- Scale-Space Theory in Computer VisionPublished by Springer Nature ,1994
- Color indexingInternational Journal of Computer Vision, 1991
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991