Improved Data Association Method in Binocular Vision-SLAM

Abstract

This paper presents an approach to binocular vision simultaneous localization and mapping (SLAM). SIFT (Scale Invariant Feature Transform) algorithm is used to extract the Natural landmarks, The minimal connected dominating set(CDS) approach is used in data association which solve the problem that the scale of data association increase with the map grows in process of SLAM. Two improvements are introduced to improve the CDS'S performance. Firstly, CDS is constructed lingeringly. Secondly, CDS is searched adaptively. SLAM is completed by fusing the information of binocular vision and robot pose with Extended Kalman Filter (EKF). The system has been implemented and tested on data gathered with a mobile robot in a typical office environment. Simulation results indicate that improved connected dominating set data association results are reliable, the capability of reducing computational complexity is outstanding.