A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts
<p>Abstract</p> <p>For the purposes of foreground estimation, the true background model is unavailable in many practical circumstances and needs to be estimated from cluttered image sequences. We propose a sequential technique for static background estimation in such conditions, wi...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2011-01-01
|
Series: | EURASIP Journal on Image and Video Processing |
Online Access: | http://jivp.eurasipjournals.com/content/2011/164956 |
id |
doaj-072daf72adca4f05b7a52b11599bcc5a |
---|---|
record_format |
Article |
spelling |
doaj-072daf72adca4f05b7a52b11599bcc5a2020-11-25T00:40:32ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-51761687-52812011-01-0120111164956A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance ContextsReddy VikasSanderson ConradLovell BrianC<p>Abstract</p> <p>For the purposes of foreground estimation, the true background model is unavailable in many practical circumstances and needs to be estimated from cluttered image sequences. We propose a sequential technique for static background estimation in such conditions, with low computational and memory requirements. Image sequences are analysed on a block-by-block basis. For each block location a representative set is maintained which contains distinct blocks obtained along its temporal line. The background estimation is carried out in a Markov Random Field framework, where the optimal labelling solution is computed using iterated conditional modes. The clique potentials are computed based on the combined frequency response of the candidate block and its neighbourhood. It is assumed that the most appropriate block results in the smoothest response, indirectly enforcing the spatial continuity of structures within a scene. Experiments on real-life surveillance videos demonstrate that the proposed method obtains considerably better background estimates (both qualitatively and quantitatively) than median filtering and the recently proposed "intervals of stable intensity" method. Further experiments on the Wallflower dataset suggest that the combination of the proposed method with a foreground segmentation algorithm results in improved foreground segmentation.</p>http://jivp.eurasipjournals.com/content/2011/164956 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Reddy Vikas Sanderson Conrad Lovell BrianC |
spellingShingle |
Reddy Vikas Sanderson Conrad Lovell BrianC A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts EURASIP Journal on Image and Video Processing |
author_facet |
Reddy Vikas Sanderson Conrad Lovell BrianC |
author_sort |
Reddy Vikas |
title |
A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts |
title_short |
A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts |
title_full |
A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts |
title_fullStr |
A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts |
title_full_unstemmed |
A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts |
title_sort |
low-complexity algorithm for static background estimation from cluttered image sequences in surveillance contexts |
publisher |
SpringerOpen |
series |
EURASIP Journal on Image and Video Processing |
issn |
1687-5176 1687-5281 |
publishDate |
2011-01-01 |
description |
<p>Abstract</p> <p>For the purposes of foreground estimation, the true background model is unavailable in many practical circumstances and needs to be estimated from cluttered image sequences. We propose a sequential technique for static background estimation in such conditions, with low computational and memory requirements. Image sequences are analysed on a block-by-block basis. For each block location a representative set is maintained which contains distinct blocks obtained along its temporal line. The background estimation is carried out in a Markov Random Field framework, where the optimal labelling solution is computed using iterated conditional modes. The clique potentials are computed based on the combined frequency response of the candidate block and its neighbourhood. It is assumed that the most appropriate block results in the smoothest response, indirectly enforcing the spatial continuity of structures within a scene. Experiments on real-life surveillance videos demonstrate that the proposed method obtains considerably better background estimates (both qualitatively and quantitatively) than median filtering and the recently proposed "intervals of stable intensity" method. Further experiments on the Wallflower dataset suggest that the combination of the proposed method with a foreground segmentation algorithm results in improved foreground segmentation.</p> |
url |
http://jivp.eurasipjournals.com/content/2011/164956 |
work_keys_str_mv |
AT reddyvikas alowcomplexityalgorithmforstaticbackgroundestimationfromclutteredimagesequencesinsurveillancecontexts AT sandersonconrad alowcomplexityalgorithmforstaticbackgroundestimationfromclutteredimagesequencesinsurveillancecontexts AT lovellbrianc alowcomplexityalgorithmforstaticbackgroundestimationfromclutteredimagesequencesinsurveillancecontexts AT reddyvikas lowcomplexityalgorithmforstaticbackgroundestimationfromclutteredimagesequencesinsurveillancecontexts AT sandersonconrad lowcomplexityalgorithmforstaticbackgroundestimationfromclutteredimagesequencesinsurveillancecontexts AT lovellbrianc lowcomplexityalgorithmforstaticbackgroundestimationfromclutteredimagesequencesinsurveillancecontexts |
_version_ |
1725289529265356800 |