Abstract
Image-to-geometry registration is the basis of many applications for texturing and interpreting 3D surface models. Feature-based matching is an established, automatic approach which creates 2D–3D correspondences based on salient points and their radiometric neighbourhood. This paper presents an experimental approach for assessing the accuracy of several matching algorithms in challenging imaging environments that are subject to significant outdoor illumination variations. Furthermore, a collection of accuracy assessment metrics and quality heuristics emerge from the presented approach to guide a user during the examination of registration results. As a result of the experiments, two novel salient point descriptor matching combinations outperform the standard scale-invariant feature transform (SIFT) operator on the task of image-to-image and image-to-geometry registration under varying illumination conditions.
Original language | English |
---|---|
Pages (from-to) | 93-118 |
Number of pages | 26 |
Journal | Photogrammetric Record |
Volume | 32 |
Issue number | 158 |
Early online date | 14 Jun 2017 |
DOIs | |
Publication status | Published - Jun 2017 |
Bibliographical note
AcknowledgementsThis research is part of the VOM2MPS project (no. 234111/E30), funded by the Research Council of Norway (RCN) and the FORCE consortium through Petromaks 2 and SAFARI. Data are collected and provided in the framework of SAFARI (www.safaridb.com).
Keywords
- feature-based registration
- illumination variances
- image-to-geometry
- interest operators
- mobile device imagery
- outdoor environments