Memory-efficient real-time map building using octree of planes and points

This paper presents an octree-based map building algorithm for mobile home-service robots. The robot is equipped with a time-of-flight camera, which produces point clouds of the environment surfaces. Given the successive input of point clouds, a 3D map is incrementally computed in real time. The map...

Full description

Saved in:
Bibliographic Details
Published inAdvanced robotics Vol. 27; no. 4; pp. 301 - 308
Main Authors Jo, Yonghyun, Jang, Hanyoung, Kim, Yeon-Ho, Cho, Joon-Kee, Moradi, Hadi, Han, JungHyun
Format Journal Article
LanguageEnglish
Published Routledge 01.03.2013
Subjects
GPU
home-service robot
map building
octree
Online AccessGet full text

Cover

More Information
Summary:This paper presents an octree-based map building algorithm for mobile home-service robots. The robot is equipped with a time-of-flight camera, which produces point clouds of the environment surfaces. Given the successive input of point clouds, a 3D map is incrementally computed in real time. The map is accurate and memory-efficient because the octree nodes containing points on a plane are merged and represented simply by an index to the plane. The real-time performance is achieved largely due to the parallel processing capability of the many-core Graphics Processing Unit used for plane extraction.
ISSN:0169-1864
1568-5535
DOI:10.1080/01691864.2013.755248