|
Title
|
|
|
|
Not far away from home : a relational distance-based approach to understanding images of houses
| |
|
Author
|
|
|
|
| |
|
Abstract
|
|
|
|
| Augmenting vision systems with high-level knowledge and reasoning can improve lower-level vision processes, by using richer and more structured information. In this paper we tackle the problem of delimiting conceptual elements of street views based on spatial relations between lower-level components, e. g. the element 'house' is composed of windows and a door in a spatial arrangement. We use structured data: each concept can be seen as a graph representing spatial relations between components, e. g. in terms of right, up, close. We employ a distance-based approach between logical interpretations to match parts of images with known examples and provide an experimental evaluation on real images. |
| |
|
Language
|
|
|
|
English
| |
|
Source (journal)
|
|
|
|
Lecture notes in computer science. - Berlin, 1973, currens
| |
|
Source (book)
|
|
|
|
20th International Conference on Inductive Logic Programming (ILP), JUN 27-30, 2010, Florence, ITALY
| |
|
Publication
|
|
|
|
Berlin
:
Springer-verlag berlin
,
2011
| |
|
ISBN
|
|
|
|
978-3-642-21294-9
978-3-642-21295-6
| |
|
Volume/pages
|
|
|
|
6489
(2011)
, p. 22-29
| |
|
ISI
|
|
|
|
000325925600006
| |
|