Robust Real-Time Visual SLAM Using Scale Prediction and Exemplar Based Feature Description

Chekhlov, Denis; Pupilli, Mark; Mayol, W.W.; Calway, Andrew

doi:10.1109/cvpr.2007.383026

Cited by 65 publications

(48 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most expensive part of the algorithm is generally the computation of the image scale space. Previous work [4] has also investigated solutions to avoid this cost in the case of monocular SLAM using the estimated camera pose. An alternative is proposed here for stereo pairs that avoids the knowledge of camera position.…”

Section: True Scalementioning

confidence: 99%

A Constant-Time Efficient Stereo SLAM System

Mei¹,

Sibley²,

Cummins³

et al. 2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

Continuous, real-time mapping of an environment using a camera requires a constanttime estimation engine. This rules out optimal global solving such as bundle adjustment. In this article, we investigate the precision that can be achieved with only local estimation of motion and structure provided by a stereo pair. We introduce a simple but novel representation of the environment in terms of a sequence of relative locations. We demonstrate precise local mapping and easy navigation using the relative map, and importantly show that this can be done without requiring a global minimisation after loop closure. We discuss some of the issues that arise from using a relative representation, and evaluate our system on long sequences processed at a constant 30-45 Hz, obtaining precisions down to a few metres over distances of a few kilometres.

show abstract

Section: True Scalementioning

confidence: 99%

A Constant-Time Efficient Stereo SLAM System

Mei¹,

Sibley²,

Cummins³

et al. 2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

show abstract

“…In the past a few years, SLAM was extensively studied [11,4,10,16,17] and used for real-time camera tracking. SLAM methods estimate the environment structure and the camera trajectory online, under a highly nonlinear partial observation model.…”

Section: Real-time Camera Trackingmentioning

confidence: 99%

Keyframe-based real-time camera tracking

Dong

Jia

Bao

2009

2009 IEEE 12th International Conference on Computer Vision

View full text Add to dashboard Cite

show abstract

“…The intention is to show that with a higher frame rate a performance similar to the recent improvements discussed above [5,6,7,8,9] can be achieved, while additionally all these measures could again be used to even further improve performance. From the variety of state-of-the-art monocular SLAM frameworks mentioned before [4,7,8,9] we are using in this work MonoSLAM algorithm, because we think that it is the most advanced.…”

Section: Introductionmentioning

confidence: 99%

“…This work tackles mainly the problem of camera robust localization, and Chekhlov et al [8] extended this SLAM framework to operate over a large range of views using a SIFT-like spatial gradient descriptor.…”

Section: Introductionmentioning

confidence: 99%

Improving Localization Robustness in Monocular SLAM Using a High-Speed Camera

Gemeiner¹,

Davison²,

Vincze³

2008

Robotics: Science and Systems IV

View full text Add to dashboard Cite

Abstract-In the robotics community localization and mapping of an unknown environment is a well-studied problem. To solve this problem in real-time using visual input, a standard monocular Simultaneous Localization and Mapping (SLAM) algorithm can be used. This algorithm is very stable when smooth motion is expected, but in case of erratic or sudden movements, the camera pose typically gets lost. To improve robustness in Monocular SLAM (MonoSLAM) we propose to use a camera with faster readout speed to obtain a frame rate of 200Hz. We further present an extended MonoSLAM motion model, which can handle movements with significant jitter. In this work the improved localization and mapping have been evaluated against ground truth, which is reconstructed from off-line vision. To explain the benefits of using a high frame rate vision input in MonoSLAM framework, we performed repeatable experiments with a high-speed camera mounted onto a robotic arm. Due to the dense visual information MonoSLAM can faster shrink localization and mapping uncertainties and can operate under fast, erratic, or sudden movements. The extended motion model can provide additional robustness against significant handheld jitter when throwing or shaking the camera.

show abstract

Robust Real-Time Visual SLAM Using Scale Prediction and Exemplar Based Feature Description

Cited by 65 publications

References 11 publications

A Constant-Time Efficient Stereo SLAM System

A Constant-Time Efficient Stereo SLAM System

Keyframe-based real-time camera tracking

Improving Localization Robustness in Monocular SLAM Using a High-Speed Camera

Contact Info

Product

Resources

About