Automatic incremental model learning for scene interpretation

J. Hartz; L. Hotz; B. Neumann; K. Terzić

Automatic incremental model learning for scene interpretation

J. Hartz^*, L. Hotz, B. Neumann, K. Terzić

^*Corresponding author for this work

School of Computer Science

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

Abstract

In this paper, we investigate automatic model learning for the interpretation of complex scenes with structured objects. We present a learning, interpretation, and evaluation cycle for processing such scenes. By including learning and interpretation in one framework, an evaluation and feedback learning is enabled that takes interpretation challenges like context and combination of diverse types of structured objectes into account. The framework is tested with the interpretation of terrestrial images of man-made structures.

Original language	English
Title of host publication	Proceedings of the IASTED International Conference on Computational Intelligence, CI 2009
Pages	68-74
Number of pages	7
Publication status	Published - 1 Dec 2009
Event	IASTED International Conference on Computational Intelligence, CI 2009 - Honolulu, HI, United States Duration: 17 Aug 2009 → 19 Aug 2009

Conference

Conference	IASTED International Conference on Computational Intelligence, CI 2009
Country/Territory	United States
City	Honolulu, HI
Period	17/08/09 → 19/08/09

Keywords

Computer vision
Image understanding
Machine learning
Ontologies

Cite this

@inproceedings{6a78fc33d6da4b9f90bff8178ad58d7e,

title = "Automatic incremental model learning for scene interpretation",

abstract = "In this paper, we investigate automatic model learning for the interpretation of complex scenes with structured objects. We present a learning, interpretation, and evaluation cycle for processing such scenes. By including learning and interpretation in one framework, an evaluation and feedback learning is enabled that takes interpretation challenges like context and combination of diverse types of structured objectes into account. The framework is tested with the interpretation of terrestrial images of man-made structures.",

keywords = "Computer vision, Image understanding, Machine learning, Ontologies",

author = "J. Hartz and L. Hotz and B. Neumann and K. Terzi{\'c}",

year = "2009",

month = dec,

day = "1",

language = "English",

isbn = "9780889868069",

pages = "68--74",

booktitle = "Proceedings of the IASTED International Conference on Computational Intelligence, CI 2009",

note = "IASTED International Conference on Computational Intelligence, CI 2009 ; Conference date: 17-08-2009 Through 19-08-2009",

}

TY - GEN

T1 - Automatic incremental model learning for scene interpretation

AU - Hartz, J.

AU - Hotz, L.

AU - Neumann, B.

AU - Terzić, K.

PY - 2009/12/1

Y1 - 2009/12/1

N2 - In this paper, we investigate automatic model learning for the interpretation of complex scenes with structured objects. We present a learning, interpretation, and evaluation cycle for processing such scenes. By including learning and interpretation in one framework, an evaluation and feedback learning is enabled that takes interpretation challenges like context and combination of diverse types of structured objectes into account. The framework is tested with the interpretation of terrestrial images of man-made structures.

AB - In this paper, we investigate automatic model learning for the interpretation of complex scenes with structured objects. We present a learning, interpretation, and evaluation cycle for processing such scenes. By including learning and interpretation in one framework, an evaluation and feedback learning is enabled that takes interpretation challenges like context and combination of diverse types of structured objectes into account. The framework is tested with the interpretation of terrestrial images of man-made structures.

KW - Computer vision

KW - Image understanding

KW - Machine learning

KW - Ontologies

UR - http://www.scopus.com/inward/record.url?scp=77954026074&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77954026074

SN - 9780889868069

SP - 68

EP - 74

BT - Proceedings of the IASTED International Conference on Computational Intelligence, CI 2009

T2 - IASTED International Conference on Computational Intelligence, CI 2009

Y2 - 17 August 2009 through 19 August 2009

ER -

Automatic incremental model learning for scene interpretation

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this