Effective close-range accuracy comparison of microsoft hololens generation one and two using vuforia imagetargets

Jonas S.I. Rieder*, Danielle H. Van Tol, Doris Aschenbrenner

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

6 Citations (Scopus)
117 Downloads (Pure)

Abstract

This paper analyzes the effective accuracy for close-range operations for the first and the second generation of Microsoft HoloLens in combination with Vuforia Image Targets in a black-box approach. The implementation of Augmented Reality (AR) on optical see-through (OST), head-mounted devices (HMDs) has been proven viable for a variety of tasks, such as assembly, maintenance, or educational purposes. For most of these applications, minor localization errors are tolerated since no accurate alignment between the artificial and the real parts is required. For other potential applications, these accuracy errors represent a major obstacle. The "realistically achievable"accuracy remains largely unknown for close-range usages (e.g. within "arms-reach"of a user) for both generations of Microsoft HoloLens.Thus, the authors developed a method to benchmark and compare the applicability of these devices for tasks that demand a higher accuracy like composite manufacturing or medical surgery assistance. Furthermore, the method can be used for a broad variety of devices, establishing a platform for bench-marking and comparing these and future devices. This paper analyzes the performance of test users, which were asked to pinpoint the perceived location of holographic cones. The image recognition software package "Vuforia"was used to determine the spatial transform of the predefined ImageTarget. By comparing the user-markings with the algorithmic locations, a mean deviation of 2.59 ±1.79 [mm] (HL 1) and 1.11 ±0.98 [mm] (HL 2) has been found, which means that the mean accuracy improved by 57.1% and precision by 45.4%. The highest mean accuracy of a single test user has been measured with 0.47 ±1.683 [mm] (HL 1) and 0.085 ± 0.567 [mm] (HL 2).

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2021
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages552-553
Number of pages2
ISBN (Electronic)9780738113678
DOIs
Publication statusPublished - 2021
Event2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2021 - Virtual, Lisbon, Portugal
Duration: 27 Mar 20213 Apr 2021

Publication series

NameProceedings - 2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2021

Conference

Conference2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2021
Country/TerritoryPortugal
CityVirtual, Lisbon
Period27/03/213/04/21

Keywords

  • Empirical studies in visualization
  • Human computer interaction (HCI)
  • Human-centered computing
  • Interaction paradigms
  • Mixed / augmented reality
  • Visualization

Fingerprint

Dive into the research topics of 'Effective close-range accuracy comparison of microsoft hololens generation one and two using vuforia imagetargets'. Together they form a unique fingerprint.

Cite this