Relative Pose from SIFT Features

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00362923" target="_blank" >RIV/68407700:21230/22:00362923 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-19824-3_27" target="_blank" >https://doi.org/10.1007/978-3-031-19824-3_27</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-19824-3_27" target="_blank" >10.1007/978-3-031-19824-3_27</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Relative Pose from SIFT Features

Popis výsledku v původním jazyce

This paper derives the geometric relationship of epipolar geometry and orientation- and scale-covariant, e.g., SIFT, features. We derive a new linear constraint relating the unknown elements of the fundamental matrix and the orientation and scale. This equation can be used together with the well-known epipolar constraint to, e.g., estimate the fundamental matrix from four SIFT correspondences, essential matrix from three, and to solve the semi-calibrated case from three correspondences. Requiring fewer correspondences than the well-known point-based approaches (e.g., 5PT, 6PT and 7PT solvers) for epipolar geometry estimation makes RANSAC-like randomized robust estimation significantly faster. The proposed constraint is tested on a number of problems in a synthetic environment and on publicly available real-world datasets on more than 800 00 image pairs. It is superior to the state-of-the-art in terms of processing time while often leading more accurate results. The solvers are included in GC-RANSAC at https://github.com/danini/graph-cut-ransac.

Název v anglickém jazyce

Relative Pose from SIFT Features

Popis výsledku anglicky

This paper derives the geometric relationship of epipolar geometry and orientation- and scale-covariant, e.g., SIFT, features. We derive a new linear constraint relating the unknown elements of the fundamental matrix and the orientation and scale. This equation can be used together with the well-known epipolar constraint to, e.g., estimate the fundamental matrix from four SIFT correspondences, essential matrix from three, and to solve the semi-calibrated case from three correspondences. Requiring fewer correspondences than the well-known point-based approaches (e.g., 5PT, 6PT and 7PT solvers) for epipolar geometry estimation makes RANSAC-like randomized robust estimation significantly faster. The proposed constraint is tested on a number of problems in a synthetic environment and on publicly available real-world datasets on more than 800 00 image pairs. It is superior to the state-of-the-art in terms of processing time while often leading more accurate results. The solvers are included in GC-RANSAC at https://github.com/danini/graph-cut-ransac.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computer Vision – ECCV 2022, Part XXXII

ISBN

978-3-031-19823-6

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

16

Strana od-do

454-469

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Tel Aviv

Datum konání akce

23. 10. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000903565400027