Biologically inspired features for scene classification in video surveillance

Kaiqi Huang*, Dacheng Tao, Yuan Yuan, Xuelong Li, Tieniu Tan

*Corresponding author for this work

Research output: Contribution to journalLetter

Abstract

Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective, and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper.

Original languageEnglish
Pages (from-to)307-313
Number of pages7
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume41
Issue number1
Early online date22 Jan 2010
DOIs
Publication statusPublished - 1 Feb 2011

Fingerprint

Cognition
Databases
Experiments

Keywords

  • biologically inspired
  • scene classification
  • video surveillance

Cite this

Huang, Kaiqi ; Tao, Dacheng ; Yuan, Yuan ; Li, Xuelong ; Tan, Tieniu. / Biologically inspired features for scene classification in video surveillance. In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics. 2011 ; Vol. 41, No. 1. pp. 307-313.
@article{09ab0fd6ab80467c9634efecfa3d167d,
title = "Biologically inspired features for scene classification in video surveillance",
abstract = "Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective, and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper.",
keywords = "biologically inspired, scene classification, video surveillance",
author = "Kaiqi Huang and Dacheng Tao and Yuan Yuan and Xuelong Li and Tieniu Tan",
year = "2011",
month = "2",
day = "1",
doi = "10.1109/TSMCB.2009.2037923",
language = "English",
volume = "41",
pages = "307--313",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",
issn = "1083-4419",
publisher = "IEEE",
number = "1",

}

Biologically inspired features for scene classification in video surveillance. / Huang, Kaiqi; Tao, Dacheng; Yuan, Yuan; Li, Xuelong; Tan, Tieniu.

In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 41, No. 1, 01.02.2011, p. 307-313.

Research output: Contribution to journalLetter

TY - JOUR

T1 - Biologically inspired features for scene classification in video surveillance

AU - Huang, Kaiqi

AU - Tao, Dacheng

AU - Yuan, Yuan

AU - Li, Xuelong

AU - Tan, Tieniu

PY - 2011/2/1

Y1 - 2011/2/1

N2 - Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective, and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper.

AB - Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective, and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper.

KW - biologically inspired

KW - scene classification

KW - video surveillance

UR - http://www.scopus.com/inward/record.url?scp=79551681231&partnerID=8YFLogxK

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5395619

U2 - 10.1109/TSMCB.2009.2037923

DO - 10.1109/TSMCB.2009.2037923

M3 - Letter

C2 - 20100675

AN - SCOPUS:79551681231

VL - 41

SP - 307

EP - 313

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

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

SN - 1083-4419

IS - 1

ER -