Object pose planning for generating 3-D models from range image sequences

H. Zha, Kenichi Morooka, N. Okada, T. Nagata

Research output: Chapter in Book/Report/Conference proceedingOther chapter contribution

Abstract

We propose a method to create a complete model of a complex curved object using multiple range images acquired from different directions. The pose of the object is changed by a manipulator in order to view the object from specified views. The pose is planned after each new image is merged into a unified representation. To estimate the precise transformations between different views of the object, a registration algorithm is used to match corresponding points while avoiding object occlusions.

Original languageEnglish
Title of host publicationProceedings of the Japan/USA Symposium on Flexible Automation
EditorsK. Stelson, F. Oba
Pages901-904
Number of pages4
Volume2
Publication statusPublished - 1996
EventProceedings of the 1996 Japan-USA Symposium on Flexible Automation. Part 2 (of 2) - Boston, MA, USA
Duration: Jul 7 1996Jul 10 1996

Other

OtherProceedings of the 1996 Japan-USA Symposium on Flexible Automation. Part 2 (of 2)
CityBoston, MA, USA
Period7/7/967/10/96

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint

Dive into the research topics of 'Object pose planning for generating 3-D models from range image sequences'. Together they form a unique fingerprint.

Cite this