In this paper we present several interest points detectors
and we analyze their suitability when used as landmark extractors for
vision-based simultaneous localization and mapping (vSLAM). For this
purpose, we evaluate the detectors according to their repeatability under
changes in viewpoint and scale. These are the desired requirements for
visual landmarks. Several experiments were carried out using sequence
of images captured with high precision. The sequences represent planar
objects as well as 3D scenes.
Draft: [pdf: 600k]
Online: Lecture Notes in Computer Science. Current Topics in Artificial Intelligence
Bibtex
@InBook{mozos2007lnai,
TITLE = {Lecture Notes in Computer Science},
AUTHOR = {Oscar Martinez Mozos and Arturo Gil and Monica Ballesta and Oscar Reinoso},
CHAPTER = {Interest Point Detectors for Visual SLAM},
EDITOR = {Daniel Borrajo and Luis Castillo and Juan Manuel Corchado},
PUBLISHER = {Springer-Verlag, Germany},
SERIES = {Current Topics in Artificial Intelligence},
YEAR = {2008},
VOLUME = {4788},
PAGES = {170--179},
}