Skip to main navigation Skip to search Skip to main content

The research on AGV visual guided under strong noise

  • Luoyang Institute of Electro-optical Devices
  • Beihang University

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

Abstract

In this paper, considering the complexity of AGV working environment, the image filtering, segmentation and graph morphology processing are carried out for the high noise of AGV working environment. To solve the problem of uneven light in the process of AGV travel, a dynamic threshold transfer and segmentation method is proposed, which greatly improves the accuracy and efficiency of the segmentation. At the same time, after extracting the morphological gradient of the marking line, the whole inspection method of image acquisition and the label processing of the boundary are established, and a one-sided fast center line searching algorithm is proposed. Compared with the traditional algorithm, the computation cost is reduced by more than 50%.

Original languageEnglish
Title of host publicationImage and Graphics Technologies and Applications - 13th Conference on Image and Graphics Technologies and Applications, IGTA 2018, Revised Selected Papers
EditorsYongtian Wang, Yuxin Peng, Zhiguo Jiang
PublisherSpringer Verlag
Pages35-44
Number of pages10
ISBN (Print)9789811317019
DOIs
StatePublished - 2018
Event13th Conference on Image and Graphics Technologies and Applications, IGTA 2018 - Beijing, China
Duration: 8 Apr 201810 Apr 2018

Publication series

NameCommunications in Computer and Information Science
Volume875
ISSN (Print)1865-0929

Conference

Conference13th Conference on Image and Graphics Technologies and Applications, IGTA 2018
Country/TerritoryChina
CityBeijing
Period8/04/1810/04/18

Keywords

  • Center line extraction
  • Fast dynamic threshold
  • Morphological filtering
  • Strong noise
  • Visual navigation AGV

Fingerprint

Dive into the research topics of 'The research on AGV visual guided under strong noise'. Together they form a unique fingerprint.

Cite this