Ontology-supported object and event extraction with a genetic algorithms approach for object classification

Yakup Yildirim, Turgay Yilmaz, Adnan Yazici

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Current solutions are still far from reaching the ultimate goal, namely to enable users to retrieve the desired video clip among massive amounts of visual data in a semantically meaningful manner. With this study we propose a video database model (OVDAM) that provides automatic object, event and concept extraction. By using training sets and expert opinions, low-level feature values for objects and relations between objects are determined. N-Cut image segmentation algorithm is used to determine segments in video keyframes and the genetic algorithm-based classifier is used to make classification of segments (candidate objects) to objects. At the top level ontology of objects, events and concepts are used. Objects and/or events use all these information to generate events and concepts. The system has a reliable video data model, which gives the user the ability to make ontology-supported fuzzy querying. RDF is used to represent metadata. OWL is used to represent ontology and RDQL is used for querying. Queries containing objects, events, spatio-temporal clauses, concepts and low-level features are handled.

Original languageEnglish
Title of host publicationProceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007
Pages202-209
Number of pages8
DOIs
Publication statusPublished - Dec 14 2007
Event6th ACM International Conference on Image and Video Retrieval, CIVR 2007 - Amsterdam, Netherlands
Duration: Jul 9 2007Jul 11 2007

Publication series

NameProceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007

Conference

Conference6th ACM International Conference on Image and Video Retrieval, CIVR 2007
CountryNetherlands
CityAmsterdam
Period7/9/077/11/07

Fingerprint

Ontology
Genetic algorithms
Metadata
Image segmentation
Data structures
Classifiers

Keywords

  • Content-based retrieval
  • Event extraction
  • Fuzziness
  • Genetic algorithm
  • Object extraction
  • Ontology
  • OWL
  • RDF
  • Video model

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science(all)

Cite this

Yildirim, Y., Yilmaz, T., & Yazici, A. (2007). Ontology-supported object and event extraction with a genetic algorithms approach for object classification. In Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007 (pp. 202-209). (Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007). https://doi.org/10.1145/1282280.1282314

Ontology-supported object and event extraction with a genetic algorithms approach for object classification. / Yildirim, Yakup; Yilmaz, Turgay; Yazici, Adnan.

Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007. 2007. p. 202-209 (Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yildirim, Y, Yilmaz, T & Yazici, A 2007, Ontology-supported object and event extraction with a genetic algorithms approach for object classification. in Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007. Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007, pp. 202-209, 6th ACM International Conference on Image and Video Retrieval, CIVR 2007, Amsterdam, Netherlands, 7/9/07. https://doi.org/10.1145/1282280.1282314
Yildirim Y, Yilmaz T, Yazici A. Ontology-supported object and event extraction with a genetic algorithms approach for object classification. In Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007. 2007. p. 202-209. (Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007). https://doi.org/10.1145/1282280.1282314
Yildirim, Yakup ; Yilmaz, Turgay ; Yazici, Adnan. / Ontology-supported object and event extraction with a genetic algorithms approach for object classification. Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007. 2007. pp. 202-209 (Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007).
@inproceedings{356a96719e2e4b8ca9664d2d7c1eb8aa,
title = "Ontology-supported object and event extraction with a genetic algorithms approach for object classification",
abstract = "Current solutions are still far from reaching the ultimate goal, namely to enable users to retrieve the desired video clip among massive amounts of visual data in a semantically meaningful manner. With this study we propose a video database model (OVDAM) that provides automatic object, event and concept extraction. By using training sets and expert opinions, low-level feature values for objects and relations between objects are determined. N-Cut image segmentation algorithm is used to determine segments in video keyframes and the genetic algorithm-based classifier is used to make classification of segments (candidate objects) to objects. At the top level ontology of objects, events and concepts are used. Objects and/or events use all these information to generate events and concepts. The system has a reliable video data model, which gives the user the ability to make ontology-supported fuzzy querying. RDF is used to represent metadata. OWL is used to represent ontology and RDQL is used for querying. Queries containing objects, events, spatio-temporal clauses, concepts and low-level features are handled.",
keywords = "Content-based retrieval, Event extraction, Fuzziness, Genetic algorithm, Object extraction, Ontology, OWL, RDF, Video model",
author = "Yakup Yildirim and Turgay Yilmaz and Adnan Yazici",
year = "2007",
month = "12",
day = "14",
doi = "10.1145/1282280.1282314",
language = "English",
isbn = "1595937331",
series = "Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007",
pages = "202--209",
booktitle = "Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007",

}

TY - GEN

T1 - Ontology-supported object and event extraction with a genetic algorithms approach for object classification

AU - Yildirim, Yakup

AU - Yilmaz, Turgay

AU - Yazici, Adnan

PY - 2007/12/14

Y1 - 2007/12/14

N2 - Current solutions are still far from reaching the ultimate goal, namely to enable users to retrieve the desired video clip among massive amounts of visual data in a semantically meaningful manner. With this study we propose a video database model (OVDAM) that provides automatic object, event and concept extraction. By using training sets and expert opinions, low-level feature values for objects and relations between objects are determined. N-Cut image segmentation algorithm is used to determine segments in video keyframes and the genetic algorithm-based classifier is used to make classification of segments (candidate objects) to objects. At the top level ontology of objects, events and concepts are used. Objects and/or events use all these information to generate events and concepts. The system has a reliable video data model, which gives the user the ability to make ontology-supported fuzzy querying. RDF is used to represent metadata. OWL is used to represent ontology and RDQL is used for querying. Queries containing objects, events, spatio-temporal clauses, concepts and low-level features are handled.

AB - Current solutions are still far from reaching the ultimate goal, namely to enable users to retrieve the desired video clip among massive amounts of visual data in a semantically meaningful manner. With this study we propose a video database model (OVDAM) that provides automatic object, event and concept extraction. By using training sets and expert opinions, low-level feature values for objects and relations between objects are determined. N-Cut image segmentation algorithm is used to determine segments in video keyframes and the genetic algorithm-based classifier is used to make classification of segments (candidate objects) to objects. At the top level ontology of objects, events and concepts are used. Objects and/or events use all these information to generate events and concepts. The system has a reliable video data model, which gives the user the ability to make ontology-supported fuzzy querying. RDF is used to represent metadata. OWL is used to represent ontology and RDQL is used for querying. Queries containing objects, events, spatio-temporal clauses, concepts and low-level features are handled.

KW - Content-based retrieval

KW - Event extraction

KW - Fuzziness

KW - Genetic algorithm

KW - Object extraction

KW - Ontology

KW - OWL

KW - RDF

KW - Video model

UR - http://www.scopus.com/inward/record.url?scp=36849008695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36849008695&partnerID=8YFLogxK

U2 - 10.1145/1282280.1282314

DO - 10.1145/1282280.1282314

M3 - Conference contribution

SN - 1595937331

SN - 9781595937339

T3 - Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007

SP - 202

EP - 209

BT - Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007

ER -