An ontology based approach for activity recognition from video

Umut Akdemir, Pavan Turaga, Rama Chellappa

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

48 Citations (Scopus)

Abstract

Representation and recognition of human activities is an important problem for video surveillance and security applications. Considering the wide variety of settings in which surveillance systems are being deployed, it is necessary to create a common knowledge-base or ontology of human activities. Most current attempts at ontology design in computer vision for human activities have been empirical in nature. In this paper, we present a more systematic approach to address the problem of designing ontologies for visual activity recognition. We draw on general ontology design principles and adapt them to the specific domain of human activity ontologies. Then, we discuss qualitative evaluation principles and provide several examples from existing ontologies and how they can be improved upon. Finally, we demonstrate quantitatively in terms of recognition performance, the efficacy and validity of our approach for bank and airport tarmac surveillance domains.

Original languageEnglish (US)
Title of host publicationMM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops
Pages709-712
Number of pages4
DOIs
StatePublished - 2008
Externally publishedYes
Event16th ACM International Conference on Multimedia, MM '08 - Vancouver, BC, Canada
Duration: Oct 26 2008Oct 31 2008

Other

Other16th ACM International Conference on Multimedia, MM '08
CountryCanada
CityVancouver, BC
Period10/26/0810/31/08

Fingerprint

Ontology
Airports
Computer vision

Keywords

  • Activity ontologies
  • Visual surveillance

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Akdemir, U., Turaga, P., & Chellappa, R. (2008). An ontology based approach for activity recognition from video. In MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops (pp. 709-712) https://doi.org/10.1145/1459359.1459466

An ontology based approach for activity recognition from video. / Akdemir, Umut; Turaga, Pavan; Chellappa, Rama.

MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops. 2008. p. 709-712.

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

Akdemir, U, Turaga, P & Chellappa, R 2008, An ontology based approach for activity recognition from video. in MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops. pp. 709-712, 16th ACM International Conference on Multimedia, MM '08, Vancouver, BC, Canada, 10/26/08. https://doi.org/10.1145/1459359.1459466
Akdemir U, Turaga P, Chellappa R. An ontology based approach for activity recognition from video. In MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops. 2008. p. 709-712 https://doi.org/10.1145/1459359.1459466
Akdemir, Umut ; Turaga, Pavan ; Chellappa, Rama. / An ontology based approach for activity recognition from video. MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops. 2008. pp. 709-712
@inproceedings{ce17569524b148c2b170f861d0846a4a,
title = "An ontology based approach for activity recognition from video",
abstract = "Representation and recognition of human activities is an important problem for video surveillance and security applications. Considering the wide variety of settings in which surveillance systems are being deployed, it is necessary to create a common knowledge-base or ontology of human activities. Most current attempts at ontology design in computer vision for human activities have been empirical in nature. In this paper, we present a more systematic approach to address the problem of designing ontologies for visual activity recognition. We draw on general ontology design principles and adapt them to the specific domain of human activity ontologies. Then, we discuss qualitative evaluation principles and provide several examples from existing ontologies and how they can be improved upon. Finally, we demonstrate quantitatively in terms of recognition performance, the efficacy and validity of our approach for bank and airport tarmac surveillance domains.",
keywords = "Activity ontologies, Visual surveillance",
author = "Umut Akdemir and Pavan Turaga and Rama Chellappa",
year = "2008",
doi = "10.1145/1459359.1459466",
language = "English (US)",
isbn = "9781605583037",
pages = "709--712",
booktitle = "MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops",

}

TY - GEN

T1 - An ontology based approach for activity recognition from video

AU - Akdemir, Umut

AU - Turaga, Pavan

AU - Chellappa, Rama

PY - 2008

Y1 - 2008

N2 - Representation and recognition of human activities is an important problem for video surveillance and security applications. Considering the wide variety of settings in which surveillance systems are being deployed, it is necessary to create a common knowledge-base or ontology of human activities. Most current attempts at ontology design in computer vision for human activities have been empirical in nature. In this paper, we present a more systematic approach to address the problem of designing ontologies for visual activity recognition. We draw on general ontology design principles and adapt them to the specific domain of human activity ontologies. Then, we discuss qualitative evaluation principles and provide several examples from existing ontologies and how they can be improved upon. Finally, we demonstrate quantitatively in terms of recognition performance, the efficacy and validity of our approach for bank and airport tarmac surveillance domains.

AB - Representation and recognition of human activities is an important problem for video surveillance and security applications. Considering the wide variety of settings in which surveillance systems are being deployed, it is necessary to create a common knowledge-base or ontology of human activities. Most current attempts at ontology design in computer vision for human activities have been empirical in nature. In this paper, we present a more systematic approach to address the problem of designing ontologies for visual activity recognition. We draw on general ontology design principles and adapt them to the specific domain of human activity ontologies. Then, we discuss qualitative evaluation principles and provide several examples from existing ontologies and how they can be improved upon. Finally, we demonstrate quantitatively in terms of recognition performance, the efficacy and validity of our approach for bank and airport tarmac surveillance domains.

KW - Activity ontologies

KW - Visual surveillance

UR - http://www.scopus.com/inward/record.url?scp=70350637511&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350637511&partnerID=8YFLogxK

U2 - 10.1145/1459359.1459466

DO - 10.1145/1459359.1459466

M3 - Conference contribution

AN - SCOPUS:70350637511

SN - 9781605583037

SP - 709

EP - 712

BT - MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops

ER -