Content-based Video Retrieval by Integrating Spatio-Temporal and Stochastic Recognition of Events

M. Petkovic; Willem Jonker

doi:10.1109/EVENT.2001.938869

Content-based Video Retrieval by Integrating Spatio-Temporal and Stochastic Recognition of Events

M. Petkovic, Willem Jonker

Databases (Former)

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

45 Citations (Scopus)

359 Downloads (Pure)

Abstract

As amounts of publicly available video data grow the need to query this data efficiently becomes significant. Consequently content-based retrieval of video data turns out to be a challenging and important problem. We address the specific aspect of inferring semantics automatically from raw video data. In particular, we introduce a new video data model that supports the integrated use of two different approaches for mapping low-level features to high-level concepts. Firstly, the model is extended with a rule-based approach that supports spatio-temporal formalization of high-level concepts, and then with a stochastic approach. Furthermore, results on real tennis video data are presented, demonstrating the validity of both approaches, as well us advantages of their integrated use

Original language	Undefined
Title of host publication	Proceedings IEEE Workshop on Detection and Recognition of Events in Video
Place of Publication	Vancouver, Canada
Publisher	IEEE
Pages	82-
Number of pages	75
ISBN (Print)	0-7695-1293-3
DOIs	https://doi.org/10.1109/EVENT.2001.938869
Publication status	Published - 2001
Event	IEEE Workshop on Detection and Recognition of Events in Video, EVENT 2001 - Vancouver, Canada, Vancouver, Canada Duration: 8 Jul 2001 → 8 Jul 2001

Publication series

Name
Publisher	IEEE

Conference

Conference	IEEE Workshop on Detection and Recognition of Events in Video, EVENT 2001
Abbreviated title	EVENT 2001
Country/Territory	Canada
City	Vancouver
Period	8/07/01 → 8/07/01
Other	8 July 2001

Keywords

METIS-202294
IR-36548

Access to Document

10.1109/EVENT.2001.938869

00938869

Cite this

@inproceedings{f67f854be5394d7499ae6a48e9f63a14,

title = "Content-based Video Retrieval by Integrating Spatio-Temporal and Stochastic Recognition of Events",

abstract = "As amounts of publicly available video data grow the need to query this data efficiently becomes significant. Consequently content-based retrieval of video data turns out to be a challenging and important problem. We address the specific aspect of inferring semantics automatically from raw video data. In particular, we introduce a new video data model that supports the integrated use of two different approaches for mapping low-level features to high-level concepts. Firstly, the model is extended with a rule-based approach that supports spatio-temporal formalization of high-level concepts, and then with a stochastic approach. Furthermore, results on real tennis video data are presented, demonstrating the validity of both approaches, as well us advantages of their integrated use",

keywords = "METIS-202294, IR-36548",

author = "M. Petkovic and Willem Jonker",

note = "Project DMW ; IEEE Workshop on Detection and Recognition of Events in Video, EVENT 2001 ; Conference date: 08-07-2001 Through 08-07-2001",

year = "2001",

doi = "10.1109/EVENT.2001.938869",

language = "Undefined",

isbn = "0-7695-1293-3",

publisher = "IEEE",

pages = "82--",

booktitle = "Proceedings IEEE Workshop on Detection and Recognition of Events in Video",

address = "United States",

}

Petkovic, M & Jonker, W 2001, Content-based Video Retrieval by Integrating Spatio-Temporal and Stochastic Recognition of Events. in Proceedings IEEE Workshop on Detection and Recognition of Events in Video. IEEE, Vancouver, Canada, pp. 82-, IEEE Workshop on Detection and Recognition of Events in Video, EVENT 2001, Vancouver, British Columbia, Canada, 8/07/01. https://doi.org/10.1109/EVENT.2001.938869

TY - GEN

T1 - Content-based Video Retrieval by Integrating Spatio-Temporal and Stochastic Recognition of Events

AU - Petkovic, M.

AU - Jonker, Willem

N1 - Project DMW

PY - 2001

Y1 - 2001

N2 - As amounts of publicly available video data grow the need to query this data efficiently becomes significant. Consequently content-based retrieval of video data turns out to be a challenging and important problem. We address the specific aspect of inferring semantics automatically from raw video data. In particular, we introduce a new video data model that supports the integrated use of two different approaches for mapping low-level features to high-level concepts. Firstly, the model is extended with a rule-based approach that supports spatio-temporal formalization of high-level concepts, and then with a stochastic approach. Furthermore, results on real tennis video data are presented, demonstrating the validity of both approaches, as well us advantages of their integrated use

AB - As amounts of publicly available video data grow the need to query this data efficiently becomes significant. Consequently content-based retrieval of video data turns out to be a challenging and important problem. We address the specific aspect of inferring semantics automatically from raw video data. In particular, we introduce a new video data model that supports the integrated use of two different approaches for mapping low-level features to high-level concepts. Firstly, the model is extended with a rule-based approach that supports spatio-temporal formalization of high-level concepts, and then with a stochastic approach. Furthermore, results on real tennis video data are presented, demonstrating the validity of both approaches, as well us advantages of their integrated use

KW - METIS-202294

KW - IR-36548

U2 - 10.1109/EVENT.2001.938869

DO - 10.1109/EVENT.2001.938869

M3 - Conference contribution

SN - 0-7695-1293-3

SP - 82-

BT - Proceedings IEEE Workshop on Detection and Recognition of Events in Video

PB - IEEE

CY - Vancouver, Canada

T2 - IEEE Workshop on Detection and Recognition of Events in Video, EVENT 2001

Y2 - 8 July 2001 through 8 July 2001

ER -