Skip to main navigation Skip to search Skip to main content

Fundamental matrix estimation based on improved genetic algorithm

  • University of Science and Technology Beijing
  • China Southern Power Grid

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

2 Scopus citations

Abstract

Fundamental matrix estimation is the key technology in 3D reconstruction and widely used in many aspects in computer vision. In this paper, a global search genetic algorithm combining with a local search hill climbing algorithm is proposed to optimize MAPSAC algorithm for estimating fundamental matrix. The average distances between points and epipolar lines under noise and outliers are investigated with synthetic and real image feature point data respectively. The simulation results show proposed method is more robust to noise and outliers and can estimate fundamental matrix more precisely.

Original languageEnglish
Title of host publicationProceedings - 2016 8th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages326-329
Number of pages4
ISBN (Electronic)9781509007684
DOIs
StatePublished - 13 Dec 2016
Externally publishedYes
Event8th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2016 - Hangzhou, Zhejiang, China
Duration: 11 Sep 201612 Sep 2016

Publication series

NameProceedings - 2016 8th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2016
Volume1

Conference

Conference8th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2016
Country/TerritoryChina
CityHangzhou, Zhejiang
Period11/09/1612/09/16

Keywords

  • Computer vision
  • Epipolar geometry
  • Fundamental matrix
  • Genetic algorithm
  • Hill climbing algorithm

Fingerprint

Dive into the research topics of 'Fundamental matrix estimation based on improved genetic algorithm'. Together they form a unique fingerprint.

Cite this