Bayesian foreground and shadow detection in uncertain frame rate surveillance videos

Csaba Benedek, T. Szirányi

Research output: Contribution to journalArticle

90 Citations (Scopus)

Abstract

In in this paper, we propose a new model regarding foreground and shadow detection in video sequences. The model works without detailed a priori object-shape information, and it is also appropriate for low and unstable frame rate video sources. Contribution is presented in three key issues: 1) we propose a novel adaptive shadow model, and show the improvements versus previous approaches in scenes with difficult lighting and coloring effects; 2) we give a novel description for the foreground based on spatial statistics of the neighboring pixel values, which enhances the detection of background or shadow-colored object parts; 3) we show how microstructure analysis can be used in the proposed framework as additional feature components improving the results. Finally, a Markov random field model is used to enhance the accuracy of the separation. We validate our method on outdoor and indoor sequences including real surveillance videos and well-known benchmark test sets.

Original languageEnglish
Pages (from-to)608-621
Number of pages14
JournalIEEE Transactions on Image Processing
Volume17
Issue number4
DOIs
Publication statusPublished - Apr 2008

Fingerprint

Video Surveillance
Spatial Statistics
Coloring
Test Set
Model
Random Field
Colouring
Microstructure
Lighting
Pixel
Pixels
Unstable
Statistics
Benchmark
Object

Keywords

  • Foreground
  • Markov random field (MRF)
  • Shadow
  • Texture

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Graphics and Computer-Aided Design
  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition

Cite this

Bayesian foreground and shadow detection in uncertain frame rate surveillance videos. / Benedek, Csaba; Szirányi, T.

In: IEEE Transactions on Image Processing, Vol. 17, No. 4, 04.2008, p. 608-621.

Research output: Contribution to journalArticle

@article{aa8750ca208b44e691d2a2b987c2bb18,
title = "Bayesian foreground and shadow detection in uncertain frame rate surveillance videos",
abstract = "In in this paper, we propose a new model regarding foreground and shadow detection in video sequences. The model works without detailed a priori object-shape information, and it is also appropriate for low and unstable frame rate video sources. Contribution is presented in three key issues: 1) we propose a novel adaptive shadow model, and show the improvements versus previous approaches in scenes with difficult lighting and coloring effects; 2) we give a novel description for the foreground based on spatial statistics of the neighboring pixel values, which enhances the detection of background or shadow-colored object parts; 3) we show how microstructure analysis can be used in the proposed framework as additional feature components improving the results. Finally, a Markov random field model is used to enhance the accuracy of the separation. We validate our method on outdoor and indoor sequences including real surveillance videos and well-known benchmark test sets.",
keywords = "Foreground, Markov random field (MRF), Shadow, Texture",
author = "Csaba Benedek and T. Szir{\'a}nyi",
year = "2008",
month = "4",
doi = "10.1109/TIP.2008.916989",
language = "English",
volume = "17",
pages = "608--621",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Bayesian foreground and shadow detection in uncertain frame rate surveillance videos

AU - Benedek, Csaba

AU - Szirányi, T.

PY - 2008/4

Y1 - 2008/4

N2 - In in this paper, we propose a new model regarding foreground and shadow detection in video sequences. The model works without detailed a priori object-shape information, and it is also appropriate for low and unstable frame rate video sources. Contribution is presented in three key issues: 1) we propose a novel adaptive shadow model, and show the improvements versus previous approaches in scenes with difficult lighting and coloring effects; 2) we give a novel description for the foreground based on spatial statistics of the neighboring pixel values, which enhances the detection of background or shadow-colored object parts; 3) we show how microstructure analysis can be used in the proposed framework as additional feature components improving the results. Finally, a Markov random field model is used to enhance the accuracy of the separation. We validate our method on outdoor and indoor sequences including real surveillance videos and well-known benchmark test sets.

AB - In in this paper, we propose a new model regarding foreground and shadow detection in video sequences. The model works without detailed a priori object-shape information, and it is also appropriate for low and unstable frame rate video sources. Contribution is presented in three key issues: 1) we propose a novel adaptive shadow model, and show the improvements versus previous approaches in scenes with difficult lighting and coloring effects; 2) we give a novel description for the foreground based on spatial statistics of the neighboring pixel values, which enhances the detection of background or shadow-colored object parts; 3) we show how microstructure analysis can be used in the proposed framework as additional feature components improving the results. Finally, a Markov random field model is used to enhance the accuracy of the separation. We validate our method on outdoor and indoor sequences including real surveillance videos and well-known benchmark test sets.

KW - Foreground

KW - Markov random field (MRF)

KW - Shadow

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=41849102422&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41849102422&partnerID=8YFLogxK

U2 - 10.1109/TIP.2008.916989

DO - 10.1109/TIP.2008.916989

M3 - Article

C2 - 18390368

AN - SCOPUS:41849102422

VL - 17

SP - 608

EP - 621

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 4

ER -