Utilising Deep Learning Models for the Surface Registration Problem in HoloNav

Utilising Deep Learning Models for the Surface Registration Problem in HoloNav

Cicimen, Alp (TU Delft Electrical Engineering, Mathematics and Computer Science)

Marroquim, Ricardo (mentor)
Thabit, Abdullah (mentor)
Hanjalic, A. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2022-06-22

Surface Registration is a registration problem that handles the registration of two similar surfaces. In most research that utilises Deep Learning (DL) models to handle surface registration two theories are investigated; the first being whether surfaces sampled from the same origin can be registered together, and the second theory being whether the models can register Point Clouds with low overlapping data for utilisation in Simultaneous Localisation and Mapping (SLAM) applications. However, the surface registration to be utilised in the HoloNav Augmented Reality (AR) navigation system will utilise Point Clouds sampled from different origins with a high overlap ratio. This research, therefore, aims to determine the viability of DL methods for surface registration in HoloNav data. To determine the viability, rotation and translation errors in the match were used, with the aforementioned metrics later being evaluated manually with the utilisation of a visualiser. The results indicate that the models can generalise on the navigator data for an initial Euler angle difference of 45 degrees, but due to the difference in sampling density on the utilised point clouds can not provide accurate matches. Therefore, the utilisation of DL models can be considered to be viable if the navigator data has a sampling density similar to the pre-operative model.

HoloLens
Deep Learning
Point Cloud Registration

http://resolver.tudelft.nl/uuid:58d12d23-d106-4993-923b-a3dad58b34d2

https://github.com/alpcicimen/holonav-dl-registration The link to the github repository containing the utilised dataset, scripts, as well as the modified DL models RPMNet and PREDATOR.

Student theses

bachelor thesis

© 2022 Alp Cicimen