Mobile robot indoor localization using SURF algorithm based on LRF sensor

Abstract

In this paper we proposed a method to implement estimation of mobile robot's position by using SURF (Speeded Up Robust Features) algorithm based on depth image in indoor environment. SURF which is derived from SIFT algorithm has the advantage of fast calculation speed and a strong robustness. The depth image is generated from a 2D LRF (Laser Range Finder) sensor which is controlled to rotate around its y-axis. According to the interest points in each frame of depth image, we find the position relationship between each two frames and make a match between the corresponding interest points. In the experiment, we will show the implementation of position estimation using the method we proposed in this paper. The accuracy and efficiency of the proposed method has also been proved in the experiment.