Real-Time Feature Acquisition and Integration for Vision-Based Mobile Robots

Authors:
Thomas Hübner;Renato Pajarola
Affiliations:
Visualization and MultiMedia Lab, University of Zurich, Zurich, Switzerland 8050;Visualization and MultiMedia Lab, University of Zurich, Zurich, Switzerland 8050
Venue:
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Year:
2009

Citing 8
Cited 0

Least-Squares Estimation of Transformation Parameters Between Two Point Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Method for Registration of 3-D Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Determining the Epipolar Geometry and its Uncertainty: A Review

International Journal of Computer Vision
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Speeded-Up Robust Features (SURF)

Computer Vision and Image Understanding
SURF: speeded up robust features

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Machine learning for high-speed corner detection

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we propose a new system for real-time feature acquisition and integration based on high-resolution stereo images that is suitable for mobile robot platforms with limited resources. We combine a fast feature detection stage with a stable scale-invariant feature description method utilizing optimized spatial matching. Putative image feature matches are used to determine 3D coordinates of feature points and to estimate corresponding view transformations. Experimental results show the advantages of our system in terms of performance and accuracy compared to the standard methods used in the area.