Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts

Abstract: 

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.

up
1 user has voted: Conrad Sanderson

Paper Details

Authors:
Vikas Reddy, Conrad Sanderson, Brian C. Lovell
Submitted On:
23 February 2016 - 1:43pm
Short Link:
Type:
Research Manuscript

Document Files

cluttered_background_estimation.pdf

(639)

Subscribe

[1] Vikas Reddy, Conrad Sanderson, Brian C. Lovell, "A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/190. Accessed: Nov. 15, 2019.
@article{190-15,
url = {http://sigport.org/190},
author = {Vikas Reddy; Conrad Sanderson; Brian C. Lovell },
publisher = {IEEE SigPort},
title = {A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts},
year = {2015} }
TY - EJOUR
T1 - A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts
AU - Vikas Reddy; Conrad Sanderson; Brian C. Lovell
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/190
ER -
Vikas Reddy, Conrad Sanderson, Brian C. Lovell. (2015). A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts. IEEE SigPort. http://sigport.org/190
Vikas Reddy, Conrad Sanderson, Brian C. Lovell, 2015. A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts. Available at: http://sigport.org/190.
Vikas Reddy, Conrad Sanderson, Brian C. Lovell. (2015). "A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts." Web.
1. Vikas Reddy, Conrad Sanderson, Brian C. Lovell. A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/190