A saliency-based framework for 2D-3D registration
Conference paper
Brown, M., Guillemaut, J. and Windridge, D. 2014. A saliency-based framework for 2D-3D registration. 9th International Conference on Computer Vision Theory and Applications (VISAPP 2014). Lisbon, Portugal 05 - 08 Jan 2014 SciTePress. pp. 265-273 https://doi.org/10.5220/0004675402650273
Type | Conference paper |
---|---|
Title | A saliency-based framework for 2D-3D registration |
Authors | Brown, M., Guillemaut, J. and Windridge, D. |
Abstract | Here we propose a saliency-based filtering approach to the problem of registering an untextured 3D object to a single monocular image. The principle of saliency can be applied to a range of modalities and domains to find intrinsically descriptive entities from amongst detected entities, making it a rigorous approach to multi-modal registration. We build on the Kadir-Brady saliency framework due to its principled information-theoretic approach which enables us to naturally extend it to the 3D domain. The salient points from each domain are initially aligned using the SoftPosit algorithm. This is subsequently refined by aligning the silhouette with contours extracted from the image. Whereas other point based registration algorithms focus on corners or straight lines, our saliency-based approach is more general as it is more widely applicable e.g. to curved surfaces where a corner detector would fail. We compare our salient point detector to the Harris corner and SIFT keypoint detectors and show it generally achieves superior registration accuracy. |
Conference | 9th International Conference on Computer Vision Theory and Applications (VISAPP 2014) |
Page range | 265-273 |
Proceedings Title | Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP |
ISBN | |
Hardcover | 9789897580031 |
Publisher | SciTePress |
Publication dates | |
Jun 2014 | |
Publication process dates | |
Deposited | 22 Apr 2016 |
Accepted | 10 Jan 2014 |
Output status | Published |
Accepted author manuscript | File Access Level Restricted |
Digital Object Identifier (DOI) | https://doi.org/10.5220/0004675402650273 |
Scopus EID | 2-s2.0-84906907235 |
Language | English |
https://repository.mdx.ac.uk/item/864x3
63
total views0
total downloads0
views this month0
downloads this month