Clock-modeled ternary spatial relations for visual scene analysis

Joanna Isabelle Olszewska

Clock-modeled ternary spatial relations for visual scene analysis

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The analysis and the description of complex visual scenes characterized by the presence of many objects of interests involve reasoning on spatial relations such as 'above', 'below', 'before', 'after' and 'between'. In this context, we have defined these semantic concepts in terms of ternary spatial relations and we have formalized them using the clock model which is based on the clock-face division and the semantic notions of hours to describe relative spatial positions. The presented approach has been efficiently applied for the automated understanding of spatial relations between multiple objects in real-world computer vision image datasets.

Original language	English
Title of host publication	Proceedings of the IWCS 2013 Workshop on Computational Models of Spatial Language Interpretation and Generation (CoSLI-3)
Editors	John Kelleher, Robert Ross, Simon Dobnik
Publisher	The Association for Computational Linguistics
Pages	20-30
Number of pages	11
Publication status	Published - 31 Mar 2013
Externally published	Yes

Keywords

ternary spatial relations
clock model
qualitative spatial reasoning
computer vision
visual scene understanding

Access to Document

https://www.aclweb.org/anthology/W13-0704/Licence: CC BY-NC-SA

Cite this

@inproceedings{01e811f7c62140ca818a90fa1476d13c,

title = "Clock-modeled ternary spatial relations for visual scene analysis",

abstract = "The analysis and the description of complex visual scenes characterized by the presence of many objects of interests involve reasoning on spatial relations such as 'above', 'below', 'before', 'after' and 'between'. In this context, we have defined these semantic concepts in terms of ternary spatial relations and we have formalized them using the clock model which is based on the clock-face division and the semantic notions of hours to describe relative spatial positions. The presented approach has been efficiently applied for the automated understanding of spatial relations between multiple objects in real-world computer vision image datasets.",

keywords = "ternary spatial relations, clock model, qualitative spatial reasoning, computer vision, visual scene understanding",

author = "Olszewska, {Joanna Isabelle}",

year = "2013",

month = mar,

day = "31",

language = "English",

pages = "20--30",

editor = "John Kelleher and Robert Ross and Simon Dobnik",

booktitle = "Proceedings of the IWCS 2013 Workshop on Computational Models of Spatial Language Interpretation and Generation (CoSLI-3)",

publisher = "The Association for Computational Linguistics",

address = "United States",

}

Clock-modeled ternary spatial relations for visual scene analysis. / Olszewska, Joanna Isabelle.
Proceedings of the IWCS 2013 Workshop on Computational Models of Spatial Language Interpretation and Generation (CoSLI-3). ed. / John Kelleher; Robert Ross; Simon Dobnik. The Association for Computational Linguistics, 2013. p. 20-30.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Clock-modeled ternary spatial relations for visual scene analysis

AU - Olszewska, Joanna Isabelle

PY - 2013/3/31

Y1 - 2013/3/31

N2 - The analysis and the description of complex visual scenes characterized by the presence of many objects of interests involve reasoning on spatial relations such as 'above', 'below', 'before', 'after' and 'between'. In this context, we have defined these semantic concepts in terms of ternary spatial relations and we have formalized them using the clock model which is based on the clock-face division and the semantic notions of hours to describe relative spatial positions. The presented approach has been efficiently applied for the automated understanding of spatial relations between multiple objects in real-world computer vision image datasets.

AB - The analysis and the description of complex visual scenes characterized by the presence of many objects of interests involve reasoning on spatial relations such as 'above', 'below', 'before', 'after' and 'between'. In this context, we have defined these semantic concepts in terms of ternary spatial relations and we have formalized them using the clock model which is based on the clock-face division and the semantic notions of hours to describe relative spatial positions. The presented approach has been efficiently applied for the automated understanding of spatial relations between multiple objects in real-world computer vision image datasets.

KW - ternary spatial relations

KW - clock model

KW - qualitative spatial reasoning

KW - computer vision

KW - visual scene understanding

M3 - Conference contribution

SP - 20

EP - 30

BT - Proceedings of the IWCS 2013 Workshop on Computational Models of Spatial Language Interpretation and Generation (CoSLI-3)

A2 - Kelleher, John

A2 - Ross, Robert

A2 - Dobnik, Simon

PB - The Association for Computational Linguistics

ER -

Clock-modeled ternary spatial relations for visual scene analysis

Abstract

Keywords

Access to Document

Fingerprint

Cite this