A New Real-Time Visual SLAM Algorithm Based on the Improved FAST Features
The visual SLAM is less dependent on hardware, so it attracts growing interests. However, the visual SLAM, especially the Extend Kalman Filter-based monocular SLAM is computational expensive, and is hard to fulfill real-time process. In this paper, we propose an algorithm, which uses the binary robust independent elementary Features descriptor to describe the features from accelerated segment test feature aiming at improving feature points extraction and matching, and combines with the 1-point random sample consensus strategy to speedup the EKF-based visual SLAM. The proposed algorithm can improve the robustness of the EKF-based visual SLAM and make it operate in real-time. Experimental results validate the proposed algorithm.
KeywordsFeature Point Extend Kalman Filter Feature Point Extraction From Accelerate Segment Test Binary Robust Independent Elementary Feature
Unable to display preview. Download preview PDF.
- 1.Davison, A.J.: Real-time simultaneous localisation and mapping with a single camera. In: Proceedings of the International Conference on Computer Vision, Nice (2003)Google Scholar
- 4.Klein, G., Murray, D.W.: Parallel tracking and mapping for small AR workspaces. In: Proceedings of the International Symposium on Mixed and Augmented Reality, pp. 1–10 (2007)Google Scholar
- 8.Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the 7th International Conference on Computer Vision, Kerkyra, Herbert Bay (1999)Google Scholar