Journal of South China University of Technology (Natural Science Edition) ›› 2015, Vol. 43 ›› Issue (6): 42-47.doi: 10.3969/j.issn.1000-565X.2015.06.007

• Mechanical Engineering • Previous Articles     Next Articles

Three-Dimension Modeling of Manufacturing Plant Scene Based on RGB-D Sensor

Quan Si-bo Li Wei-guang Zheng Shao-hua   

  1. School of Mechanical and Automotive Engineering，South China University of Technology，Guangzhou 510640，Guangdong，China
  • Received:2014-10-08 Revised:2015-02-13 Online:2015-06-25 Published:2015-05-04
  • Contact: 全思博(1983-)，男，博士生，主要从事机器人视觉研究． E-mail:quan.sibo@mail.scut.edu.cn
  • About author:全思博(1983-)，男，博士生，主要从事机器人视觉研究．
  • Supported by:
    Supported by the Guangdong“NC Generation”Mechanical Product Innovation Project(2013B011301026) and theProduction，Education and Ｒesearch Cooperative Project of Guangdong Province and the Ministry of Education(2012B091100311)

PDF

561

Abstract: Environment perception is a prerequisite for the autonomous intelligent operation of automatic guided ve-hicles，and 3D maps are more suitable than the 2D ones for representing an unstructured scene． However，the existing laser radar-and vision-based methods both have some deficiencies． In this paper，a ＲGB-D sensor mounted on a mobile robot with open-source ＲOS framework is used to build an integrated system for the three-dimension modeling of large-scale and complex scenes in manufacturing plants，and the architecture of hardware and ＲOS software modules of the system as well as the scanning strategy is introduced． Moreover，an experiment is carried out to investigate the automatic continuous scanning of a region in a manufacturing plant scene，the data registration and the three-dimension modeling of the system． The results show that the proposed system meets the requirements of three-dimension scene modeling well．

Key words: mobile robot, three-dimension scene modeling, ROS, manufacturing plant scene