Radially distorted planar motion compatible homographies

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding

Abstract

Fast and accurate homography estimation is essential to many computer vision applications, including scene degenerate cases and planarity detection. Such cases arise naturally in man-made environments, and failure to handle them will result in poor positioning estimates. Most modern day consumer cameras are affected by some level of radial distortion, which must be compensated for in order to get accurate estimates. This often demands calibration procedures, with specific scene requirements, and off-line processing. In this paper a novel polynomial solver for radially distorted planar motion compatible homographies is presented. The proposed algorithm is fast and numerically stable, and is proven on both synthetic and real data to work well inside a RANSAC loop.

Detaljer

Författare
Enheter & grupper
Forskningsområden

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Datorseende och robotik (autonoma system)
  • Signalbehandling

Nyckelord

Originalspråkengelska
Titel på värdpublikationProceedings of the 9th International Conference on Pattern Recognition Applications and Methods
Undertitel på gästpublikationICPRAM 2020
RedaktörerMaria De Marsico, Gabriella Sanniti di Baja, Ana Fred
FörlagSciTePress
Sidor280-288
Antal sidor9
Volym1
ISBN (elektroniskt)9789897583971
StatusPublished - 2020
PublikationskategoriForskning
Peer review utfördJa
Evenemang9th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2020 - Valletta, Malta
Varaktighet: 2020 feb 222020 feb 24

Konferens

Konferens9th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2020
LandMalta
OrtValletta
Period2020/02/222020/02/24