Decoupled Localization and Sensing with HMD-based AR for Interactive Scene Acquisition
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Decoupled Localization and Sensing with HMD-based AR for Interactive Scene Acquisition. / Skovsen, Soren K.; Haraldsson, Harald; Davis, Abe; Karstoft, Henrik; Belongie, Serge.
In: Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020, 11.2020, p. 167-171.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Decoupled Localization and Sensing with HMD-based AR for Interactive Scene Acquisition
AU - Skovsen, Soren K.
AU - Haraldsson, Harald
AU - Davis, Abe
AU - Karstoft, Henrik
AU - Belongie, Serge
N1 - Funding Information: This work was supported in part by Stibofonden’s IT Travel Grant for PhD students and by Innovation Fund Denmark. Publisher Copyright: © 2020 IEEE.
PY - 2020/11
Y1 - 2020/11
N2 - 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.
AB - 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.
KW - concepts and models
KW - HCI theory
KW - Human computer interaction (HCI)
KW - Human-centered computing
KW - Interaction paradigms
KW - Mixed / augmented reality
UR - http://www.scopus.com/inward/record.url?scp=85099546298&partnerID=8YFLogxK
U2 - 10.1109/ISMAR-Adjunct51615.2020.00053
DO - 10.1109/ISMAR-Adjunct51615.2020.00053
M3 - Conference article
AN - SCOPUS:85099546298
SP - 167
EP - 171
JO - Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020
JF - Adjunct Proceedings of the 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020
T2 - 2020 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2020
Y2 - 9 November 2020 through 13 November 2020
ER -
ID: 301817943