DocumentCode :
2696596
Title :
Experiences in building a visual SLAM system from open source components
Author :
Hertzberg, Christoph ; Wagner, René ; Birbach, Oliver ; Hammer, Tobias ; Frese, Udo
Author_Institution :
FB3-Math. und Inf., Univ. Bremen, Bremen, Germany
fYear :
2011
fDate :
9-13 May 2011
Firstpage :
2644
Lastpage :
2651
Abstract :
This paper shows that the field of visual SLAM has matured enough to build a visual SLAM system from open source components. The system consists of feature detection, data association, and sparse bundle adjustment. For all three modules we evaluate different libraries w.r.t. ground truth.
Keywords :
SLAM (robots); feature extraction; image matching; mobile robots; public domain software; robot vision; software libraries; stereo image processing; visual servoing; data association; feature detection; open source library; sparse bundle adjustment; stereomatching; visual SLAM system; volumetric mapping; Cameras; Detectors; Feature extraction; Libraries; Simultaneous localization and mapping; Visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation (ICRA), 2011 IEEE International Conference on
Conference_Location :
Shanghai
ISSN :
1050-4729
Print_ISBN :
978-1-61284-386-5
Type :
conf
DOI :
10.1109/ICRA.2011.5980140
Filename :
5980140
Link To Document :
بازگشت