Robust Self-calibration of Focal Lengths from the Fundamental Matrix

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00380113" target="_blank" >RIV/68407700:21230/24:00380113 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/CVPR52733.2024.00499" target="_blank" >https://doi.org/10.1109/CVPR52733.2024.00499</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR52733.2024.00499" target="_blank" >10.1109/CVPR52733.2024.00499</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Robust Self-calibration of Focal Lengths from the Fundamental Matrix

Popis výsledku v původním jazyce

The problem of self-calibration of two cameras from a given fundamental matrix is one of the basic problems in geometric computer vision. Under the assumption of known principal points and square pixels, the Bougnoux formula offers a means to compute the two unknown focal lengths. However, in many practical situations, the formula yields inaccurate results due to commonly occurring singularities. Moreover, the estimates are sensitive to noise in the com-puted fundamental matrix and to the assumed positions of the principal points. In this paper, we therefore propose an efficient and robust iterative method to estimate the focal lengths along with the principal points of the cameras given a fundamental matrix and priors for the estimated camera intrinsics. In addition, we study a computationally efficient check of models generated within RANSAC that improves the accuracy of the estimated models while reducing the to-tal computational time. Extensive experiments on real and synthetic data show that our iterative method brings signifi-cant improvements in terms of the accuracy of the estimated focal lengths over the Bougnoux formula and other state-of-the-art methods, even when relying on inaccurate priors. The code for the methods and experiments is available at https://github.com/kocurvik/robust.self.calibration

Název v anglickém jazyce

Robust Self-calibration of Focal Lengths from the Fundamental Matrix

Popis výsledku anglicky

The problem of self-calibration of two cameras from a given fundamental matrix is one of the basic problems in geometric computer vision. Under the assumption of known principal points and square pixels, the Bougnoux formula offers a means to compute the two unknown focal lengths. However, in many practical situations, the formula yields inaccurate results due to commonly occurring singularities. Moreover, the estimates are sensitive to noise in the com-puted fundamental matrix and to the assumed positions of the principal points. In this paper, we therefore propose an efficient and robust iterative method to estimate the focal lengths along with the principal points of the cameras given a fundamental matrix and priors for the estimated camera intrinsics. In addition, we study a computationally efficient check of models generated within RANSAC that improves the accuracy of the estimated models while reducing the to-tal computational time. Extensive experiments on real and synthetic data show that our iterative method brings signifi-cant improvements in terms of the accuracy of the estimated focal lengths over the Bougnoux formula and other state-of-the-art methods, even when relying on inaccurate priors. The code for the methods and experiments is available at https://github.com/kocurvik/robust.self.calibration

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

<a href="/cs/project/GM22-23183M" target="_blank" >GM22-23183M: Nová generace algoritmů pro řešení problémů geometrie kamer</a><br>

Návaznosti

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

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

979-8-3503-5300-6

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

10

Strana od-do

5220-5229

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Seattle

Datum konání akce

16. 6. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001322555905059