Monocular vision based Monte Carlo localization for mobile robot

Abstract

To deal with the localization problem of robot equipped with monocular camera,a Monte Carlo method based on scale invariant feature transform (SIFT) is proposed. The features are extracted by modified SIFT to make the features invariant to changes in illumination,scale,3D viewpoint and noise,and to reduce the number of features generated by SIFT as well as their extraction and matching time. During robot motion,the information from feature observations is fused with that from the odometry by particle filter,so more exact coordinates of the features are gotten. Experimental results show the effectiveness of the approach.