Interpreting structures in man-made scenes: Combining low-level and high-level structure sources

Kasim Terzić; Lothar Hotz; Jan Šochman

Interpreting structures in man-made scenes: Combining low-level and high-level structure sources

Kasim Terzić^*, Lothar Hotz, Jan Šochman

^*Corresponding author for this work

School of Computer Science

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

Abstract

Recognizing structure is an important aspect of interpreting many computer vision domains. Structure can manifest itself both visually, in terms of repeated low-level phenomena, and conceptually, in terms of a high-level compositional hierarchy. In this paper, we demonstrate an approach for combining a low-level repetitive structure detector with a logical high-level interpretation system. We evaluate the performance on a set of images from the building facade domain.

Original language	English
Title of host publication	ICAART 2010 - 2nd International Conference on Agents and Artificial Intelligence, Proceedings
Pages	357-364
Number of pages	8
Volume	1
Publication status	Published - 9 Sept 2010
Event	2nd International Conference on Agents and Artificial Intelligence, ICAART 2010 - Valencia, Spain Duration: 22 Jan 2010 → 24 Jan 2010

Conference

Conference	2nd International Conference on Agents and Artificial Intelligence, ICAART 2010
Country/Territory	Spain
City	Valencia
Period	22/01/10 → 24/01/10

Keywords

Computer vision
High-level vision
Image processing
Scene interpretation

Cite this

@inproceedings{a22665cd89d64a098d1ecbef8983d91e,

title = "Interpreting structures in man-made scenes: Combining low-level and high-level structure sources",

abstract = "Recognizing structure is an important aspect of interpreting many computer vision domains. Structure can manifest itself both visually, in terms of repeated low-level phenomena, and conceptually, in terms of a high-level compositional hierarchy. In this paper, we demonstrate an approach for combining a low-level repetitive structure detector with a logical high-level interpretation system. We evaluate the performance on a set of images from the building facade domain.",

keywords = "Computer vision, High-level vision, Image processing, Scene interpretation",

author = "Kasim Terzi{\'c} and Lothar Hotz and Jan {\v S}ochman",

year = "2010",

month = sep,

day = "9",

language = "English",

isbn = "9789896740221",

volume = "1",

pages = "357--364",

booktitle = "ICAART 2010 - 2nd International Conference on Agents and Artificial Intelligence, Proceedings",

note = "2nd International Conference on Agents and Artificial Intelligence, ICAART 2010 ; Conference date: 22-01-2010 Through 24-01-2010",

}

TY - GEN

T1 - Interpreting structures in man-made scenes

T2 - 2nd International Conference on Agents and Artificial Intelligence, ICAART 2010

AU - Terzić, Kasim

AU - Hotz, Lothar

AU - Šochman, Jan

PY - 2010/9/9

Y1 - 2010/9/9

N2 - Recognizing structure is an important aspect of interpreting many computer vision domains. Structure can manifest itself both visually, in terms of repeated low-level phenomena, and conceptually, in terms of a high-level compositional hierarchy. In this paper, we demonstrate an approach for combining a low-level repetitive structure detector with a logical high-level interpretation system. We evaluate the performance on a set of images from the building facade domain.

AB - Recognizing structure is an important aspect of interpreting many computer vision domains. Structure can manifest itself both visually, in terms of repeated low-level phenomena, and conceptually, in terms of a high-level compositional hierarchy. In this paper, we demonstrate an approach for combining a low-level repetitive structure detector with a logical high-level interpretation system. We evaluate the performance on a set of images from the building facade domain.

KW - Computer vision

KW - High-level vision

KW - Image processing

KW - Scene interpretation

UR - http://www.scopus.com/inward/record.url?scp=77956296212&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77956296212

SN - 9789896740221

SN - 9789896740214

VL - 1

SP - 357

EP - 364

BT - ICAART 2010 - 2nd International Conference on Agents and Artificial Intelligence, Proceedings

Y2 - 22 January 2010 through 24 January 2010

ER -

Interpreting structures in man-made scenes: Combining low-level and high-level structure sources

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this