Online dense local 3D world reconstruction from stereo image sequences

Author

Kagami, S. ; Takaoka, Y. ; Kida, Y. ; Nishiwaki, K. ; Kanade, T.

Author_Institution

Center of Digital Human Res., National Inst. of Adv. Ind. Sci. & Technol., Japan

fYear

2005

fDate

2-6 Aug. 2005

Firstpage

3858

Lastpage

3863

Abstract

This paper describes an online 3D reconstruction system from stereo image sequences to obtain a dense local world model for robot navigation. The proposed method consists of three components: 1) stereo depth map calculation, 2) correspondence calculation in time sequential images by tracking raw image features, 3) 6DOF camera motion estimation by RANSAC and integrate depth map into 3D reconstructed model. We examined and evaluated our method in a motion capture environment for comparison. Finally experimental results of a humanoid robot H7 are denoted.

Keywords

feature extraction; humanoid robots; image reconstruction; image sequences; motion estimation; navigation; path planning; robot vision; stereo image processing; 6DOF camera motion estimation; RANSAC; humanoid robot; motion capture; online dense local 3D world reconstruction; robot navigation; stereo depth map calculation; stereo image sequences; time sequential images; visual odometry; Cameras; Humanoid robots; Image reconstruction; Image sequences; Mobile robots; Robot vision systems; Stereo image processing; Stereo vision; Surface reconstruction; Tracking; 3D Reconstruction; Humanoid Robot; Stereo Image Sequence; Visual Odometory;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Robots and Systems, 2005. (IROS 2005). 2005 IEEE/RSJ International Conference on

Print_ISBN

0-7803-8912-3

Type

conf

DOI

10.1109/IROS.2005.1545432

Filename

1545432