Distorted pinhole model for image warping in lane detection applications

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

Abstract

Perspective distortion is a typical transformation reproduced by the pinhole model. However, camera lenses introduce radial distortion that reduces the accuracy of image processing tasks, such as lane detection for visual navigation. This paper proposes an image warping method based on the distorted pinhole camera model for lane detection applications. The theoretical principles of the imaging process are analyzed. The usefulness of this method is illustrated by estimating the pose of a ground vehicle using lane lines. The results show that the proposed approach is feasible for visual feedback in robot navigation applications.

Original languageEnglish
Title of host publicationOptics and Photonics for Information Processing XV
EditorsKhan M. Iftekharuddin, Abdul A. S. Awwal, Victor Hugo Diaz-Ramirez, Andres Marquez
PublisherSPIE
ISBN (Electronic)9781510644762
DOIs
StatePublished - 2021
EventOptics and Photonics for Information Processing XV 2021 - San Diego, United States
Duration: 1 Aug 20215 Aug 2021

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11841
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceOptics and Photonics for Information Processing XV 2021
Country/TerritoryUnited States
CitySan Diego
Period1/08/215/08/21

Keywords

  • Distorted pinhole camera
  • Homography
  • Lens distortion
  • Pose estimation
  • Robot navigation

Fingerprint

Dive into the research topics of 'Distorted pinhole model for image warping in lane detection applications'. Together they form a unique fingerprint.

Cite this