Real-Time SLAM Relocalisation
- 1 January 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1-8
Abstract
Monocular SLAM has the potential to turn inexpensive cameras into powerful pose sensors for applications such as robotics and augmented reality. However, current implementations lack the robustness required to be useful outside laboratory conditions: blur, sudden motion and occlusion all cause tracking to fail and corrupt the map. Here we present a system which automatically detects and recovers from tracking failure while preserving map integrity. By extending recent advances in keypoint recognition the system can quickly resume tracking - i.e. within a single frame time of 33 ms - using any of the features previously stored in the map. Extensive tests show that the system can reliably generate maps for long sequences even in the presence of frequent tracking failure.Keywords
This publication has 15 references indexed in Scilit:
- MonoSLAM: Real-Time Single Camera SLAMIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Automatic Relocalisation for a Single-Camera Simultaneous Localisation and Mapping System2007
- Unified Inverse Depth Parametrization for Monocular SLAM2006
- Keypoint recognition using randomized treesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Scalable Monocular SLAM2006
- Vision-based global localization and mapping for mobile robotsIEEE Transactions on Robotics, 2005
- Reducing drift in parametric motion tracking2002
- Data association in stochastic mapping using the joint compatibility testIEEE Transactions on Robotics and Automation, 2001
- Shape Quantization and Recognition with Randomized TreesNeural Computation, 1997
- Random sample consensusCommunications of the ACM, 1981