Title :
Map-assisted visual localization using line features in urban area
Author :
Li, Haifeng ; Wang, Hongpeng ; Lu, Xiang ; Liu, Jingtai
Author_Institution :
Inst. of Robot. & Autom. Inf. Syst., Nankai Univ., Tianjin, China
Abstract :
A novel method is presented for robustly estimating the location of a mobile robot in urban areas based on images extracted from a monocular onboard camera, given a 2D building boundary map. The proposed approach firstly reconstructs a set of vertical planes by sampling and clustering vertical lines from the image with Random Sample Consensus (RANSAC), using the derived 1D homographies to inform the planar model. Then, an optimal autonomous localization algorithm based on the 2D building outline map is proposed. The physical experiments are carried out to validate the robustness and accuracy of our localization approach.
Keywords :
SLAM (robots); building; cameras; feature extraction; geometry; image reconstruction; image sampling; iterative methods; mobile robots; pattern clustering; robot vision; 1D homographies; 2D building boundary map; 2D building outline map; RANSAC; image extraction; map-assisted visual localization; mobile robot; monocular onboard camera; optimal autonomous localization algorithm; random sample consensus; robust location estimation; urban area; vertical line clustering; vertical line sampling; vertical plane reconstruction; Buildings; Cameras; Equations; Global Positioning System; Image segmentation; Robot vision systems;
Conference_Titel :
Control and Decision Conference (CCDC), 2012 24th Chinese
Conference_Location :
Taiyuan
Print_ISBN :
978-1-4577-2073-4
DOI :
10.1109/CCDC.2012.6243064
