Rotational Alignment of IMU-camera Systems with 1-Point RANSAC

Guan Banglei, Ang Su, Zhang Li, Friedrich Fraundorfer

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

Abstract

In this paper we present a minimal solution for the rotational alignment of IMU-camera systems based on a homography formulation. The image correspondences between two views are related by homography when the motion of the camera can be effectively approximated as a pure rotation. By exploiting the rotational angles of the features obtained by e.g. the SIFT detector, we compute the rotational alignment of IMU-camera systems with only 1 feature correspondence. The novel minimal case solution allows us to cope with feature mismatches efficiently and robustly within a random sample consensus (RANSAC) scheme. Our method is evaluated on both synthetic and real scene data, demonstrating that our method is suited for the rotational alignment of IMU-camera systems.
Originalspracheenglisch
TitelPattern Recognition and Computer Vision
Redakteure/-innenZ. Lin
ErscheinungsortCham
Herausgeber (Verlag)Springer
Seiten172-183
ISBN (Print)978-3-030-31725-6
DOIs
PublikationsstatusVeröffentlicht - 2019
VeranstaltungChines Conference on Pattern Recognition and Computer Vision: PRCV 2019 - Xi'an, China
Dauer: 8 Nov. 20199 Nov. 2019

Publikationsreihe

NameLecture Notes in Computer Science
Nummer11859

Konferenz

KonferenzChines Conference on Pattern Recognition and Computer Vision
KurztitelPRCV 2019
Land/GebietChina
OrtXi'an
Zeitraum8/11/199/11/19

Fingerprint

Untersuchen Sie die Forschungsthemen von „Rotational Alignment of IMU-camera Systems with 1-Point RANSAC“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren