Fast relocalisation and loop closing in keyframe-based SLAM

  title={Fast relocalisation and loop closing in keyframe-based SLAM},
  author={Raul Mur-Artal and Juan D. Tard{\'o}s},
  journal={2014 IEEE International Conference on Robotics and Automation (ICRA)},
  • Raul Mur-Artal, J. D. Tardós
  • Published 29 September 2014
  • Computer Science
  • 2014 IEEE International Conference on Robotics and Automation (ICRA)
In this paper we present for the first time a relocalisation method for keyframe-based SLAM that can deal with severe viewpoint change, at frame-rate, in maps containing thousands of keyframes. As this method relies on local features, it permits the interoperability between cameras, allowing a camera to relocalise in a map built by a different camera. We also perform loop closing (detection + correction), at keyframerate, in loops containing hundreds of keyframes. For both relocalisation and… 
Robust Relocalization Based on Active Loop Closure for Real-Time Monocular SLAM
An active loop closure based relocalization system, which enables the monocular SLAM to detect and recover from tracking failures automatically even in previously unvisited areas where no keyframe exists, and is more robust than others.
Keyframe-Based Camera Relocalization Method Using Landmark and Keypoint Matching
This paper presents an accurate method for RGB camera relocalization in the case of a very sparse 3D map built by limited keyframes by using the landmark-based place recognition method to generate from keyframes the images similar to the current view along with the set of pairwise matched landmarks.
RGBiD-SLAM for Accurate Real-time Localisation and 3D Mapping
A complete SLAM system for RGB-D cameras, namely RGB-iD SLAM, which is a dense direct SLAM method with the main characteristic of working with the depth maps in inverse depth parametrisation for the routines of dense alignment or keyframe fusion.
ORB-SLAM: A Versatile and Accurate Monocular SLAM System
A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation.
Using collaborative sharing on cloud for fast relocalization in keyframe-based SLAM
This paper presents an approach based on cloud-based sharing, which aims at providing a way for fast relocalization on the existing keyframe-based SLAM framework, and proposes various mechanisms to eliminate the degeneration of this distributed model and the unstable network.
The accuracy of relocalization and loop closing process using ORB SLAM algorithm in a variety of environmental settings is shown and the applicability of the approach in real time application like autonomous navigation is shown.
LiPo-LCD: Combining Lines and Points for Appearance-based Loop Closure Detection
This paper introduces LiPo-LCD, a novel appearance-based loop closure detection method that integrates lines and points that compares well with several state-of-the-art solutions for a number of datasets involving different environmental conditions.
On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation
This paper shows how to circumvent this limitation by adapting a pre-trained forest to a new scene on the fly, and achieves relocalisation performance that is on par with that of offline forests, and the approach runs in under 150ms, making it desirable for real-time systems that require online Relocalisation.
Sequence-based sparse optimization methods for long-term loop closure detection in visual SLAM
This work proposes a new Robust Multimodal Sequence-based (ROMS) method for robust loop closure detection in long-term visual SLAM, and develops a new algorithm to solve the formulated optimization problem efficiently, which guarantees to converge to the global optima theoretically.
FD-SLAM: 3-D Reconstruction Using Features and Dense Matching
An RGB-D SLAM system that leverages the advantages of both approaches: using dense frame-to-model odometry to build accurate sub- maps and on-the-fly feature-based matching across sub-maps for global map optimisation.


Automatic Relocalization and Loop Closing for Real-Time Monocular SLAM
The relocalization module can be used to recognize overlap in maps, i.e., when the camera has returned to a previously mapped area, and the system combining all of these abilities is able to map larger environments and for significantly longer periods than previous systems.
Improving the Agility of Keyframe-Based SLAM
This paper presents two approaches to improving the agility of a keyframe-based SLAM system, and implements a very simple inter-frame rotation estimator to aid tracking when the camera is rapidly panning and enables a trivially simple yet effective relocalisation method.
Unified Loop Closing and Recovery for Real Time Monocular SLAM
A unified method for recovering from tracking failure and closing loops in real time monocular simultaneous localisation and mapping, and a bag-of-words appearance model for ranking potential loop closures and a robust method for using both structure and image appearance to confirm likely matches.
Double window optimisation for constant time visual SLAM
We present a novel and general optimisation framework for visual SLAM, which scales for both local, highly accurate reconstruction and large-scale motion with long loop closures. We take a two-level
Robust monocular SLAM in dynamic environments
A novel prior-based adaptive RANSAC algorithm (PARSAC) is proposed to efficiently remove outliers even when the inlier ratio is rather low, so that the camera pose can be reliably estimated even in very challenging situations.
Scale Drift-Aware Large Scale Monocular SLAM
This paper describes a new near real-time visual SLAM system which adopts the continuous keyframe optimisation approach of the best current stereo systems, but accounts for the additional challenges presented by monocular input and presents a new pose-graph optimisation technique which allows for the efficient correction of rotation, translation and scale drift at loop closures.
Appearance-only SLAM at large scale with FAB-MAP 2.0
A new formulation of appearance-only SLAM suitable for very large scale place recognition that incorporates robustness against perceptual aliasing and substantially outperforms the standard term-frequency inverse-document-frequency (tf-idf) ranking measure.
Temporally scalable visual SLAM using a reduced pose graph
This paper demonstrates a system for temporally scalable visual SLAM using a reduced pose graph representation that uses new measurements to continually improve the map, yet achieves efficiency by avoiding adding redundant frames and not using marginalization to reduce the graph.
Parallel Tracking and Mapping for Small AR Workspaces
A system specifically designed to track a hand-held camera in a small AR workspace, processed in parallel threads on a dual-core computer, that produces detailed maps with thousands of landmarks which can be tracked at frame-rate with accuracy and robustness rivalling that of state-of-the-art model-based systems.