Learning semantic scene models from observing activity in visual surveillance

Dimitios Makris; Tim Ellis

doi:10.1109/TSMCB.2005.846652

Learning semantic scene models from observing activity in visual surveillance

Dimitios Makris
, Tim Ellis

Kingston University

Research output: Contribution to journal › Article › peer-review

2 Downloads (Pure)

Abstract

This paper considers the problem of automatically learning an activity-based semantic scene model from a stream of video data. A scene model is proposed that labels regions according to an identifiable activity in each region, such as entry/exit zones, junctions, paths, and stop zones. We present several unsupervised methods that learn these scene elements and present results that show the efficiency of our approach. Finally, we describe how the models can be used to support the interpretation of moving objects in a visual surveillance environment.

Original language	English
Pages (from-to)	397-408
Journal	IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume	35
Issue number	3
DOIs	https://doi.org/10.1109/TSMCB.2005.846652
Publication status	Published - Jun 2005

Bibliographical note

Note: This work was supported by the Engineering and Physical Sciences Research Council [grant number GR/M58030].

Keywords

Computer science and informatics

Access to Document

10.1109/TSMCB.2005.846652

Makris-D-782Other version, 4.43 MBLicence: Unspecified

http://dx.doi.org/doi:10.1109/TSMCB.2005.846652

Cite this

@article{92612123c65d431abf664d53c6886d8b,

title = "Learning semantic scene models from observing activity in visual surveillance",

abstract = "This paper considers the problem of automatically learning an activity-based semantic scene model from a stream of video data. A scene model is proposed that labels regions according to an identifiable activity in each region, such as entry/exit zones, junctions, paths, and stop zones. We present several unsupervised methods that learn these scene elements and present results that show the efficiency of our approach. Finally, we describe how the models can be used to support the interpretation of moving objects in a visual surveillance environment.",

keywords = "Computer science and informatics",

author = "Dimitios Makris and Tim Ellis",

note = "Note: This work was supported by the Engineering and Physical Sciences Research Council [grant number GR/M58030].",

year = "2005",

month = jun,

doi = "10.1109/TSMCB.2005.846652",

language = "English",

volume = "35",

pages = "397--408",

journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",

issn = "1083-4419",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Learning semantic scene models from observing activity in visual surveillance

AU - Makris, Dimitios

AU - Ellis, Tim

N1 - Note: This work was supported by the Engineering and Physical Sciences Research Council [grant number GR/M58030].

PY - 2005/6

Y1 - 2005/6

N2 - This paper considers the problem of automatically learning an activity-based semantic scene model from a stream of video data. A scene model is proposed that labels regions according to an identifiable activity in each region, such as entry/exit zones, junctions, paths, and stop zones. We present several unsupervised methods that learn these scene elements and present results that show the efficiency of our approach. Finally, we describe how the models can be used to support the interpretation of moving objects in a visual surveillance environment.

AB - This paper considers the problem of automatically learning an activity-based semantic scene model from a stream of video data. A scene model is proposed that labels regions according to an identifiable activity in each region, such as entry/exit zones, junctions, paths, and stop zones. We present several unsupervised methods that learn these scene elements and present results that show the efficiency of our approach. Finally, we describe how the models can be used to support the interpretation of moving objects in a visual surveillance environment.

KW - Computer science and informatics

UR - http://www.ncbi.nlm.nih.gov/pubmed/15971910

U2 - 10.1109/TSMCB.2005.846652

DO - 10.1109/TSMCB.2005.846652

M3 - Article

C2 - 15971910

SN - 1083-4419

VL - 35

SP - 397

EP - 408

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

IS - 3

ER -

Learning semantic scene models from observing activity in visual surveillance

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this