SURF features for efficient robot localization with omnidirectional images

Murillo, Ana C.; Guerrero, J. J.; Sagüés, Carlos

doi:10.1109/robot.2007.364077

Cited by 189 publications

(116 citation statements)

References 18 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…While there exists a large body of literature on omnidirectional camera calibration [15], [16], [17], [18], localization [19], [20] and sparse structure-from-motion / SLAM [21], [22], [23], surprisingly little research has been carried out towards dense 3D reconstruction with catadioptric cameras.…”

Section: Related Workmentioning

confidence: 99%

Omnidirectional 3D reconstruction in augmented Manhattan worlds

Schoenbein

Geiger

2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper proposes a method for high-quality omnidirectional 3D reconstruction of augmented Manhattan worlds from catadioptric stereo video sequences. In contrast to existing works we do not rely on constructing virtual perspective views, but instead propose to optimize depth jointly in a unified omnidirectional space. Furthermore, we show that plane-based prior models can be applied even though planes in 3D do not project to planes in the omnidirectional domain. Towards this goal, we propose an omnidirectional slanted-plane Markov random field model which relies on plane hypotheses extracted using a novel voting scheme for 3D planes in omnidirectional space. To quantitatively evaluate our method we introduce a dataset which we have captured using our autonomous driving platform AnnieWAY which we equipped with two horizontally aligned catadioptric cameras and a Velodyne HDL-64E laser scanner for precise ground truth depth measurements. As evidenced by our experiments, the proposed method clearly benefits from the unified view and significantly outperforms existing stereo matching techniques both quantitatively and qualitatively. Furthermore, our method is able to reduce noise and the obtained depth maps can be represented very compactly by a small number of image segments and plane parameters.

show abstract

Section: Related Workmentioning

confidence: 99%

Omnidirectional 3D reconstruction in augmented Manhattan worlds

Schoenbein

Geiger

2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…SIFT features were also used indoors using a topological approach by Andreasson et al [2] and a metric approach by Se et al [13]. Murillo et al [12] proposed a two step approach. First, SIFT features were used to obtain the topological location of the observer.…”

Section: Related Workmentioning

confidence: 99%

Real-time topometric localization

Badino

Huber

Kanade

2012

2012 IEEE International Conference on Robotics and Automation

158

111

View full text Add to dashboard Cite

Abstract-Autonomous vehicles must be capable of localizing even in GPS denied situations. In this paper, we propose a realtime method to localize a vehicle along a route using visual imagery or range information. Our approach is an implementation of topometric localization, which combines the robustness of topological localization with the geometric accuracy of metric methods. We construct a map by navigating the route using a GPS-equipped vehicle and building a compact database of simple visual and 3D features. We then localize using a Bayesian filter to match sequences of visual or range measurements to the database. The algorithm is reliable across wide environmental changes, including lighting differences, seasonal variations, and occlusions, achieving an average localization accuracy of 1 m over an 8 km route. The method converges correctly even with wrong initial position estimates solving the kidnapped robot problem.

show abstract

“…The matches have been obtained using SURF descriptors (Murillo et al, 2007). In the simulated experiments, an observation noise with an standard deviation of 0.125 degrees is used.…”

Section: Methodsmentioning

confidence: 99%

PARAMETERIZATION AND INITIALIZATION OF BEARING-ONLY INFORMATION - A Discussion

Aragüés

Sagüés

2008

Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics Service

View full text Add to dashboard Cite

Abstract:In this paper we discuss feature parameterization and initialization for bearing-only data obtained from vision sensors. The interest of this work refers to the comparison of the bearing-only data representation and initialization techniques. The behavior of the algorithm is analyzed for different robot motions and depth of the features. The results are evaluated in terms of the sensitivity to step size and performance to ill conditioned situations. The problem studied refers to robots moving on the plane, sensing the environment and extracting bearing-only information from uncalibrated cameras to recover the position of the landmarks and its own localization.

show abstract

SURF features for efficient robot localization with omnidirectional images

Cited by 189 publications

References 18 publications

Omnidirectional 3D reconstruction in augmented Manhattan worlds

Omnidirectional 3D reconstruction in augmented Manhattan worlds

Real-time topometric localization

PARAMETERIZATION AND INITIALIZATION OF BEARING-ONLY INFORMATION - A Discussion

Contact Info

Product

Resources

About