Efficient 3D voxel reconstruction of human shape within robotic work cells

Dominik Stengel, Thomas Wiedemann, Birgit Vogel-Heuser

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

In this paper an efficient voxel reconstruction method within a robotic work cell by means of shape from silhouette is presented. A procedure is proposed which includes occlusions from the robot's kinematics into the reconstruction step, i.e. the time-dependent occupied space. Axis values together with surface models from the robot are used for modeling occlusions coming from the moving device. An image-based method for simplified in-place frame calibration is shown and compared to a regular marker-based method. A learning method for background models is introduced, which includes overlapping image areas from the robot and offers improved learning rates. For efficiency reasons the implementation was done on the GPU. The achieved performance using five cameras in an industrial setting is shown and discussed with respect to quality and framerates.

Original languageEnglish
Title of host publication2012 IEEE International Conference on Mechatronics and Automation, ICMA 2012
Pages1386-1392
Number of pages7
DOIs
StatePublished - 2012
Event2012 9th IEEE International Conference on Mechatronics and Automation, ICMA 2012 - Chengdu, China
Duration: 5 Aug 20128 Aug 2012

Publication series

Name2012 IEEE International Conference on Mechatronics and Automation, ICMA 2012

Conference

Conference2012 9th IEEE International Conference on Mechatronics and Automation, ICMA 2012
Country/TerritoryChina
CityChengdu
Period5/08/128/08/12

Keywords

  • 3D Voxel Reconstruction
  • Industrial Human-Robot Cooperation
  • Multi-View Moving Object Detection

Fingerprint

Dive into the research topics of 'Efficient 3D voxel reconstruction of human shape within robotic work cells'. Together they form a unique fingerprint.

Cite this