Title :
CD SLAM - continuous localization and mapping in a dynamic world
Author :
Pirker, Katrin ; Rüther, Matthias ; Bischof, Horst
Author_Institution :
Inst. for Comput. Graphics & Vision, Univ. of Technol., Graz, Austria
Abstract :
When performing large-scale perpetual localization and mapping one faces problems like memory consumption or repetitive and dynamic scene elements requiring robust data association. We propose a visual SLAM method which handles short- and long-term scene dynamics in large environments using a single camera only. Through visibility-dependent map filtering and efficient keyframe organization we reach a considerable performance gain only through incorporation of a slightly more complex map representation. Experiments on a large, mixed indoor/outdoor dataset over a time period of two weeks demonstrate the scalability and robustness of our approach.
Keywords :
SLAM (robots); filtering theory; mobile robots; robot dynamics; robot vision; sensor fusion; CD SLAM; complex map representation; continuous localization and mapping; dynamic scene elements; keyframe organization; memory consumption; mobile robot; perpetual localization and mapping; repetitive scene elements; robust data association; visibility-dependent map filtering; visual SLAM method; Buildings; Cameras; Histograms; Optimization; Robustness; Simultaneous localization and mapping; Space exploration;
Conference_Titel :
Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-61284-454-1
DOI :
10.1109/IROS.2011.6094588