Target recognition and positioning method for steel structure spraying robot based on binocular vision

Lingxiu Zhang, Guangming Zhang, Song Ding

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

Abstract

Aiming at the problem of spraying target identification and positioning of steel structure fireproof coating spraying robot, the stereo imaging model of binocular camera is established, and the collected binocular images are preprocessed by distortion correction and epipolar rectification. The application of multi-grid method in stereo matching and depth image calculation were studied, and the effect of multi-layer perceptron neural networks classifier (MLP) on segmentation of steel structure region in color image was researched. The experimental results in real scenes show that the error between the binocular vision measurement results and the actual distance is less than 2.5%. MLP classifier can effectively separate the target region from the color image, and further crop the depth image in this region to obtain the depth image containing only the target information.

Original languageEnglish
Title of host publicationInternational Conference on Image Processing and Intelligent Control, IPIC 2021
EditorsFeng Wu, Fengjie Cen
PublisherSPIE
ISBN (Electronic)9781510647244
DOIs
StatePublished - 2021
Event2021 International Conference on Image Processing and Intelligent Control, IPIC 2021 - Lanzhou, China
Duration: 30 Jul 20211 Aug 2021

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11928
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2021 International Conference on Image Processing and Intelligent Control, IPIC 2021
Country/TerritoryChina
CityLanzhou
Period30/07/211/08/21

Keywords

  • Binocular vision
  • MLP classifier
  • Multigrid method
  • Region segmentation
  • Steel structure

Fingerprint

Dive into the research topics of 'Target recognition and positioning method for steel structure spraying robot based on binocular vision'. Together they form a unique fingerprint.

Cite this