Semantic and geometric enrichment of 3D geo-spatial models with captioned photos and labelled illustrations

Jones, Christopher Bernard ORCID: https://orcid.org/0000-0001-6847-7575, Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884 and Slade, Jonathan David 2014. Semantic and geometric enrichment of 3D geo-spatial models with captioned photos and labelled illustrations. Presented at: Workshop on Vision and Language, 25th International Conference on Computational Linguistics, Coling 2014,, Dublin, Ireland, 23 August 2014.

Preview

PDF - Submitted Pre-Print Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

There are many 3D digital models of buildings with cultural heritage interest, but most of them lack semantic annotation that could be used to inform users of mobile and desktop applications about their origins and architectural features. We describe methods in an ongoing project for enriching 3D models with generic annotation, derived from examples of images of building components and from labelled plans and diagrams, and with object-specific descriptions obtained from photo captions. This is the first stage of research that aims to annotate 3D models with facts extracted from the text of authoritative architectural guides.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Completion
Status:	Unpublished
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Related URLs:	https://vision.cs.bath.ac.uk/VL_2014/ind...
Last Modified:	14 Jun 2023 06:23
URI:	https://orca.cardiff.ac.uk/id/eprint/67993

Citation Data

Cited 4 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item