Decoupled Localization and Sensing with HMD-based AR for Interactive Scene Acquisition

Søren Kelstrup Skovsen, Harald Haraldsson, Abe Davis, Henrik Karstoft, Serge Belongie

Publikation: Bidrag til bog/antologi/rapport/proceedingKonferencebidrag i proceedingsForskningpeer review

Abstract

Real-Time tracking and visual feedback offer interactive AR-Assisted capture systems as a convenient and low-cost alternative to specialized sensor rigs and robotic gantries. We present a simple strategy for decoupling localization and visual feedback in these applications from the primary sensor being used to capture the scene. Our strategy is to use an AR HMD and 6-DOF controller for tracking and feedback, synchronized with a separate primary sensor for capturing the scene. This approach allows for convenient real-Time localization of sensors that cannot do their own localization (e.g., microphones). In this poster paper, we present a prototype implementation of this strategy and investigate the accuracy of decoupled tracking by mounting a high resolution camera as the primary sensor, and comparing decoupled runtime pose estimates to the pose estimates of a high-resolution offline structure from motion.

OriginalsprogEngelsk
Titel2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)
Antal sider5
ForlagIEEE
Publikationsdatonov. 2020
Sider167-171
Artikelnummer9288396
ISBN (Elektronisk)978-1-7281-7675-8
DOI
StatusUdgivet - nov. 2020
Begivenhed19th IEEE International Symposium on Mixed and Augmented Reality - Virtual conference
Varighed: 9 nov. 202013 nov. 2020

Konference

Konference19th IEEE International Symposium on Mixed and Augmented Reality
ByVirtual conference
Periode09/11/202013/11/2020

Fingeraftryk

Dyk ned i forskningsemnerne om 'Decoupled Localization and Sensing with HMD-based AR for Interactive Scene Acquisition'. Sammen danner de et unikt fingeraftryk.

Citationsformater