James Head-­Mears

Human Interface Technology: Accurate Wide Area Tracking

NZ UC James Head Mears
Supervisor (Academic)
Mark Billinghurst & Adrian Clark, HITLab NZ/University of Canterbury
Supervisor (Industry)
Michael Giudici & Nicholas Davies, Lester-Franks
Projects
mysite
Employment
Geospatial Surveyor at Lester Franks
Thesis Abstract

Augmented Reality (AR) is a powerful tool for the visualisation of, and interaction with, digital information, and has been successfully deployed in a number of consumer applications. Despite this, AR has had limited success in industrial applications as the combined precision, accuracy, scalability and robustness of the systems are not up to industry standards. With these characteristics in mind, we present a concept Industrial AR (IAR) framework for use in outdoor environments.

Within this concept IAR framework, we focus on the improving the precision and accuracy of consumer level devices by focusing on the issue of localisation, utilising LiDAR based point clouds generated as part of normal surveying and engineering workflow. We evaluate key design points to optimise the localisation solution, including the impact of increased eld of view on feature matching performance, the filtering of feature matches between real imagery and an observed point cloud, and how pose can be estimated from 2D to 3D point correspondences. The overall accuracy of this localisation algorithm with respect to groundtruth observations is determined, with unltered results indicating an on par horizontal accuracy and signicantly improved vertical accuracy with bestcase
consumer GNSS solutions. When additional ltering is applied, results of localisation show a higher accuracy than best-case consumer GNSS.