Title :
Visual loop closing using multi-resolution SIFT grids in metric-topological SLAM
Author :
Pradeep, V. ; Medioni, Gerard ; Weiland, J.
Author_Institution :
Univ. of Southern California, Los Angeles, CA, USA
Abstract :
We present an image based simultaneous localization and mapping (SLAM) framework with online, appearance only loop closing. We adopt a layered approach with metric maps over small areas at the local level and a global, graph based abstract topological framework to build consistent maps over large distances. Rao-Blackwellised particle filtering and sparse bundle adjustment are efficiently coupled with a stereo vision based odometry module to construct conditionally independent `submaps´ using SIFT features. By extracting keyframes from these submaps, a multiresolution dictionary of distinct features is built online to learn a generative model of appearance and perform loop closure. Creating such a dictionary also enables the system to distinguish between similar regions during loop closure without requiring any offline training, as has been described in other approaches. Furthermore, instead of occupancy or grid maps, we build 3D reconstructions of the world; a model we plan to use as input to a scene interpretation module for providing navigational cues to the visually impaired. We demonstrate the robustness of our SLAM system with indoor and outdoor experiments for full 6 degrees of freedom motion using only a stereo camera in hand, running at 1 Hz on a standard PC.
Keywords :
SLAM (robots); particle filtering (numerical methods); solid modelling; stereo image processing; Rao Blackwellised particle filtering; graph based abstract topological framework; multiresolution SIFT grid; odometry module stereo vision; scale invariant feature; scene interpretation module; simultaneous localization and mapping; visual loop closing; world 3D reconstructions; Cameras; Dictionaries; Filtering; Image reconstruction; Layout; Multiresolution analysis; Navigation; Robustness; Simultaneous localization and mapping; Stereo vision;
Conference_Titel :
Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on
Conference_Location :
Miami, FL
Print_ISBN :
978-1-4244-3992-8
DOI :
10.1109/CVPR.2009.5206769