Estimation with Applications to Tracking and Navigation
Estimation with Applications to Tracking and Navigation
Real-Time Simultaneous Localisation and Mapping with a Single Camera
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Hi-index | 0.00 |
For colored measurement noise model, paper presents a Simultaneous Localization and Mapping (SLAM) algorithm for wheeled robot with colored measurement noise. Colored measurement noise model is converted into white measurement noise model by recombining the process model and the measurement model for wheeled robot. In order to make the process noise and the measurement noise irrelevant each other, the process model is re-defined. Estimating state and building a map are conducted in accordance with the virtual process model and the virtual measurement model. In data association step, part observed landmarks are processed as redundant landmarks. Some indicators of the filter are used to evaluate the performance the algorithm. The simulation results show that the proposed algorithm is consistent and robust.