A comparison of EKF and SGD applied to a view-based SLAM approach with omnidirectional images

Valiente, David; Gil, Arturo; Fernández, Lorenzo; Reinoso, Óscar

doi:10.1016/j.robot.2013.11.009

Cited by 21 publications

(14 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, in Section 5.2 we show different map solutions obtained with this SLAM approach. All the set of results presented here are also compared with a former SLAM version [22] which does not use GP nor data information distribution in order to initialize views.…”

Section: Resultsmentioning

confidence: 99%

“…Figure 13 presents a different solution for the same scenario where a different initialization ratio has been considered. In order to compare and prove the benefits of this proposal, Figure 14 presents results obtained with the former EKF-based SLAM approach [22]. By inspecting Figure 12(a) and Figure 13(a), it can be confirmed that lower initialization ratios ensure a more robust solution with a larger number of views, but obviously at a higher computational cost.…”

Section: Map Building Based On Data Information Distributionmentioning

confidence: 94%

“…Our former approach [22] relied on a relative measurement between images so as to define an initialization ratio, which was experimentally defined as:…”

Section: Map Buildingmentioning

confidence: 99%

See 2 more Smart Citations

Information-based view initialization in visual SLAM with a single omnidirectional camera

Valiente

Ghaffari

Miró

et al. 2015

Robotics and Autonomous Systems

Self Cite

View full text Add to dashboard Cite

This paper presents a novel mechanism to initiate new views within the map building process for an EKF-based visual SLAM (Simultaneous Localization and Mapping) approach using omnidirectional images. In presence of non-linearities, the EKF is very likely to compromise the final estimation. Particularly, the omnidirectional observation model is induces non-linear errors, thus it becomes a potential source of uncertainty. To deal with this issue we propose a novel mechanism for view initialization which accounts for information gain and losses more efficiently. The main outcome of this contribution is the reduction of the map uncertainty and thus the higher consistency of the final estimation. Its basis relies on a Gaussian Process to infer an information distribution model from sensor data. This model represents feature points existence probabilities and their information content analysis leads to the proposed view initialization scheme. To demonstrate the suitability and effectiveness of the approach we present a series of real data experiments conducted with a robot equipped with a camera sensor and map model solely based on omnidirectional views. The results reveal a beneficial reduction on the uncertainty but also on the error in the pose and the map estimate.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Map Building Based On Data Information Distributionmentioning

confidence: 94%

See 1 more Smart Citation

Information-based view initialization in visual SLAM with a single omnidirectional camera

Valiente

Ghaffari

Miró

et al. 2015

Robotics and Autonomous Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Besides this, neither parametrization nor tracking are required. Its performance was evaluated [32,35] within a comparison framework under the cover of the original fundamentals for such a SLAM basis [36][37][38], which established the initial foundations for the improved implementations and contributions of the present paper.…”

Section: Introductionmentioning

confidence: 99%

Robust Visual Localization with Dynamic Uncertainty Management in Omnidirectional SLAM

et al. 2017

Self Cite

View full text Add to dashboard Cite

This work presents a robust visual localization technique based on an omnidirectional monocular sensor for mobile robotics applications. We intend to overcome the non-linearities and instabilities that the camera projection systems typically introduce, which are especially relevant in catadioptric sensors. In this paper, we come up with several contributions. First, a novel strategy for the uncertainty management is developed, which accounts for a realistic visual localization technique, since it dynamically encodes the instantaneous variations and drifts on the uncertainty, by defining an information metric of the system. Secondly, an epipolar constraint adaption to the omnidirectional geometry reference is devised. Thirdly, Bayesian considerations are also implemented, in order to produce a final global metric for a consistent feature matching between images. The resulting outcomes are supported by real data experiments performed with publicly-available datasets, in order to assess the suitability of the approach and to confirm the reliability of the main contributions. Besides localization results, real visual SLAM (Simultaneous Localization and Mapping) comparison experiments with acknowledged methods are also presented, by using a public dataset and benchmark framework.

show abstract

“…Grisetti et al, 2007a;Hähnel et al, 2003;Biber et al, 2004;Eustice et al, 2005;Triebel and Burgard, 2005). Other researchers have used cameras (Gil et al, 2010b,c), omnidirectional vision sensors (Valiente et al, 2014) and others to obtain usable information to build the map. SLAM algorithms typically differ also in the underlying algorithm used to estimate the map.…”

Section: Introductionmentioning

confidence: 99%

Occupancy grid based graph-SLAM using the distance transform, SURF features and SGD

Gil

Juliá

Reinoso

2015

Engineering Applications of Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

A comparison of EKF and SGD applied to a view-based SLAM approach with omnidirectional images

Cited by 21 publications

References 17 publications

Information-based view initialization in visual SLAM with a single omnidirectional camera

Information-based view initialization in visual SLAM with a single omnidirectional camera

Robust Visual Localization with Dynamic Uncertainty Management in Omnidirectional SLAM

Occupancy grid based graph-SLAM using the distance transform, SURF features and SGD

Contact Info

Product

Resources

About