Closing loops without places
Authors:
- 1 October 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21530858,p. 3738-3744
Abstract
This paper proposes a new topo-metric representation of the world based on co-visibility that simplifies data association and improves the performance of appearance-based recognition. We introduce the concept of dynamic bagof-words, which is a novel form of query expansion based on finding cliques in the landmark co-visibility graph. The proposed approach avoids the - often arbitrary - discretisation of space from the robot's trajectory that is common to most image-based loop closure algorithms. Instead we show that reasoning on sets of co-visible landmarks leads to a simple model that out-performs pose-based or view-based approaches. Using real and simulated imagery, we demonstrate that dynamic bag-of-words query expansion can improve precision and recall for appearance-based localisation.Keywords
This publication has 19 references indexed in Scilit:
- A comparison of loop closing techniques in monocular SLAMRobotics and Autonomous Systems, 2009
- A Constant-Time Efficient Stereo SLAM System2009
- FAB-MAP: Probabilistic Localization and Mapping in the Space of AppearanceThe International Journal of Robotics Research, 2008
- Unified Loop Closing and Recovery for Real Time Monocular SLAM2008
- Parallel Tracking and Mapping for Small AR Workspaces2007
- Scalable Recognition with a Vocabulary Tree2006
- SLAM-Loop Closing with Visually Salient Features2005
- Simultaneous Localization and Map Building in Large-Scale Cyclic Environments Using the Atlas FrameworkThe International Journal of Robotics Research, 2004
- Real-time simultaneous localisation and mapping with a single camera2003
- Video Google: a text retrieval approach to object matching in videos2003