Structured light 3-D vision inspection based on RBF neural network

  • Guangjun Zhang*
  • , Zhenzhong Wei
  • , Xin Li
  • *Corresponding author for this work

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

Abstract

The principle of structured light based 3-D vision inspection is. And a method of establishing calibration points for 3-D vision inspection system are discussed in detail. This method is based on a Flexible Calibration Target, and composed of a photo-electrical aiming device and a 3-D translation platform. The application of RBF (radial basis function) neural network to the establishment of the inspection model for the structured light based 3-D vision is described in detail. The inspection model of 3-D vision based on RBF neural network is successfully established using the calibration points. The model's training accuracy is 0.078mm, and the testing accuracy is 0.083mm.

Original languageEnglish
Title of host publicationProceedings of the Second International Symposium on Instrumentation Science and Technology
EditorsT. Jiubin, W. Xianfang, T. Jiubin, W. Xianfang
Pages2/314-2/320
StatePublished - 2002
EventProceedings of the second International Symposium on Instrumentation Science and Technology - Jinan, China
Duration: 18 Aug 200222 Aug 2002

Publication series

NameProceedings of the Second International Symposium on Instrumentation Science and Technology
Volume2

Conference

ConferenceProceedings of the second International Symposium on Instrumentation Science and Technology
Country/TerritoryChina
CityJinan
Period18/08/0222/08/02

Keywords

  • 3-D vision inspection
  • Calibration point
  • Flexible calibration target
  • RBF neural network
  • Structured light
  • Training and testing of network

Fingerprint

Dive into the research topics of 'Structured light 3-D vision inspection based on RBF neural network'. Together they form a unique fingerprint.

Cite this