Enhanced Geometric Techniques for Point Marking in Model-Free Augmented Reality

被引：0

作者：

Lages, Wallace S. ^{[1
]}

Li, Yuan ^{[1
]}

Lisle, Lee ^{[1
]}

Lu, Feiyu ^{[1
]}

Hollerer, Tobias ^{[2
]}

Bowman, Doug A. ^{[1
]}

机构：

[1] Virginia Tech, Ctr Human Comp Interact, Blacksburg, VA 24061 USA

[2] Univ Calif Santa Barbara, Comp Sci, Santa Barbara, CA 93106 USA

来源：

2019 26TH IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES (VR) | 2019年

关键词：

Human-centered computing-Mixed / augmented reality; Human-centered computing-Pointing; Human-centered computing-User interface design;

D O I：

10.1109/ismar.2019.00028

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Specifying points in three-dimensional space is essential in AR applications. Geometric triangulation is a straightforward way to specify points, but its naive implementation has low precision. We designed two enhanced geometric techniques for 3D point marking: VectorCloud, which uses multiple rays to reduce jittering, and ImageRefinement, which allows 3D ray refinement to improve precision. Our experiments, conducted in both simulated and real AR, demonstrate that both techniques improve the precision of 3D point marking, and that ImageRefinement is superior to VectorCloud overall. These results are particularly relevant in the design of mobile AR systems for large outdoor areas.

引用

下载

页码：1036 / 1037

页数：2

共 50 条

[21] Model-free iterative learning of time-optimal point-to-point motions for LTI systems
Janssens, Pieter
Pipeleers, Goele
Swevers, Jan
2011 50TH IEEE CONFERENCE ON DECISION AND CONTROL AND EUROPEAN CONTROL CONFERENCE (CDC-ECC), 2011, : 6031 - 6036
[22] Comparison of accuracy between augmented reality/mixed reality techniques and conventional techniques for epidural anesthesia using a practice phantom model kit
Tatsuya Hayasaka
Kazuharu Kawano
Yu Onodera
Hiroto Suzuki
Masaki Nakane
Masafumi Kanoto
Kaneyuki Kawamae
BMC Anesthesiology, 23
[23] Comparison of accuracy between augmented reality/mixed reality techniques and conventional techniques for epidural anesthesia using a practice phantom model kit
Hayasaka, Tatsuya
Kawano, Kazuharu
Onodera, Yu
Suzuki, Hiroto
Nakane, Masaki
Kanoto, Masafumi
Kawamae, Kaneyuki
BMC ANESTHESIOLOGY, 2023, 23 (01)
[24] MODEL-FREE OPTIMAL DE-DRIFTING AND ENHANCED DETECTION IN FMRI DATA
Shah, Adnan
Seghouane, Abd-Krim
2013 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2013,
[25] Model-Free Sliding Mode Enhanced Proportional, Integral, and Derivative (SMPID) Control
Zhu, Quanmin
AXIOMS, 2023, 12 (08)
[26] Model-free data-driven computational mechanics enhanced by tensor voting
Eggersmann, Robert
Stainier, Laurent
Ortiz, Michael
Reese, Stefanie
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2021, 373
[27] Verification: model-free phasing with enhanced predicted models in ARCIMBOLDO_SHREDDER
Medina, Ana
Jimenez, Elisabet
Caballero, Iracema
Castellvi, Albert
Trivino Valls, Josep
Alcorlo, Martin
Molina, Rafael
Hermoso, Juan A.
Sammito, Massimo D.
Borges, Rafael
Uson, Isabel
ACTA CRYSTALLOGRAPHICA SECTION D-STRUCTURAL BIOLOGY, 2022, 78 : 1283 - 1293
[28] NEWMA: A New Method for Scalable Model-Free Online Change-Point Detection
Keriven, Nicolas
Garreau, Damien
Poli, Iacopo
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2020, 68 : 3515 - 3528
[29] Data-driven set-point tuning of model-free adaptive control
Lin, Na
Chi, Ronghu
Liu, Yang
Hou, Zhongsheng
Huang, Biao
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2023, 33 (13) : 7667 - 7686
[30] A conceptual model for studying the immersive mobile augmented reality application-enhanced experience
Vo Kim Nhan
Le Thanh Tam
Ho Tien Dung
Nguyen Thanh Vu
HELIYON, 2022, 8 (08)

← 1 2 3 4 5 →