Temporally scalable visual SLAM using a reduced pose graph
Authors:
Open Access
- 1 May 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10504729,p. 54-61
Abstract
In this paper, we demonstrate a system for temporally scalable visual SLAM using a reduced pose graph representation. Unlike previous visual SLAM approaches that maintain static keyframes, our approach uses new measurements to continually improve the map, yet achieves efficiency by avoiding adding redundant frames and not using marginalization to reduce the graph. To evaluate our approach, we present results using an online binocular visual SLAM system that uses place recognition for both robustness and multi-session operation. Additionally, to enable large-scale indoor mapping, our system automatically detects elevator rides based on accelerometer data. We demonstrate long-term mapping in a large multi-floor building, using approximately nine hours of data collected over the course of six months. Our results illustrate the capability of our visual SLAM system to map a large are over extended period of time.Keywords
This publication has 23 references indexed in Scilit:
- Wide-area augmented reality using camera tracking and mapping in multiple regionsComputer Vision and Image Understanding, 2011
- CI‐Graph simultaneous localization and mapping for three‐dimensional reconstruction of large and complex environments using a multicamera systemJournal of Field Robotics, 2010
- Experimental Analysis of Sample-Based Maps for Long-Term SLAMThe International Journal of Robotics Research, 2009
- Parallel Tracking and Mapping for Small AR Workspaces2007
- Exactly Sparse Extended Information Filters for Feature-based SLAMThe International Journal of Robotics Research, 2007
- D-SLAM: A Decoupled Solution to Simultaneous Localization and MappingThe International Journal of Robotics Research, 2007
- Fast iterative alignment of pose graphs with poor initial estimates2006
- Square Root SAM2005
- Incremental mapping of large cyclic environments2003
- Estimating Uncertain Spatial Relationships in Robotics1990