The SGM Algorithm based on Census Transform for Binocular Stereo Vision

  • Liye Zhang
  • , Fudong Cai
  • , Jinjun Wang
  • , Changfeng Lv
  • , Wei Liu
  • , Guoxin Guo
  • , Huanyun Liu

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

5 Scopus citations

Abstract

Aiming to reduce the error matching rate of binocular image matching and improve the accuracy of disparity map, the matching cost calculation method of Semi-Global Matching (SGM) algorithm is improved, the Census transform and adaptive window is used to calculate the cost simultaneously, and the size and shape of the cost calculation window are determined by judging the gradient size of matching points, which improves the matching accuracy and reduces the computational complexity of the algorithm. Experimental results show that the proposed algorithm can effectively improve the accuracy of binocular ranging.

Original languageEnglish
Title of host publicationProceedings - 2022 International Conference on Machine Learning and Knowledge Engineering, MLKE 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages50-54
Number of pages5
ISBN (Electronic)9781665495677
DOIs
StatePublished - 2022
Event2022 International Conference on Machine Learning and Knowledge Engineering, MLKE 2022 - Virtual, Guilin, China
Duration: 25 Feb 202227 Feb 2022

Publication series

NameProceedings - 2022 International Conference on Machine Learning and Knowledge Engineering, MLKE 2022

Conference

Conference2022 International Conference on Machine Learning and Knowledge Engineering, MLKE 2022
Country/TerritoryChina
CityVirtual, Guilin
Period25/02/2227/02/22

Keywords

  • binocular image matching
  • Census transform
  • disparity map
  • SGM algrithm

Fingerprint

Dive into the research topics of 'The SGM Algorithm based on Census Transform for Binocular Stereo Vision'. Together they form a unique fingerprint.

Cite this