Variational Bayesian learning for background subtraction based on local fusion feature

To resist the adverse effect of shadow interference, illumination changes, indigent texture and scenario jitter in object detection and improve performance, a background modelling method based on local fusion feature and variational Bayesian learning is proposed. First, U-LBSP (uniform-local binary...

Full description

Saved in:
Bibliographic Details
Published in:IET computer vision Vol. 10; no. 8; pp. 884 - 893
Main Authors: Yan, Junhua, Wang, Shunfei, Xie, Tianxia, Yang, Yong, Wang, Jiayi
Format: Journal Article
Language:English
Published: The Institution of Engineering and Technology 01.12.2016
Wiley
Subjects:
background modelling method
background subtraction
Bayes methods
Bayesian analysis
computational complexity
distribution parameter optimisation
expectation-maximisation algorithm
Gaussian components
Gaussian mixture model based on local fusion feature
Illumination
illumination changes
image colour analysis
image fusion
image texture
indigent texture
Jitter
lab colour
learning (artificial intelligence)
LFGMM
location feature
Mathematical models
object detection
optimisation
Research Article
Resists
scenario jitter
shadow disturbances
shadow interference effect
Shadows
Surface layer
Texture
U-LBSP texture feature
uniform-local binary similarity pattern texture feature
variational Bayesian learning
variational expectation maximisation algorithm
variational techniques
Gaussian mixture model based on local fusion feature
image fusion
distribution parameter optimisation
object detection
variational expectation maximisation algorithm
illumination changes
shadow disturbances
optimisation
variational techniques
image colour analysis
learning (artificial intelligence)
lab colour
location feature
LFGMM
uniform-local binary similarity pattern texture feature
U-LBSP texture feature
Gaussian components
background modelling method
shadow interference effect
indigent texture
image texture
scenario jitter
jitter
variational Bayesian learning
expectation-maximisation algorithm
Bayes methods
background subtraction
computational complexity
ISSN:1751-9632, 1751-9640, 1751-9640
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To resist the adverse effect of shadow interference, illumination changes, indigent texture and scenario jitter in object detection and improve performance, a background modelling method based on local fusion feature and variational Bayesian learning is proposed. First, U-LBSP (uniform-local binary similarity patterns) texture feature, lab colour and location feature are used to construct local fusion feature. U-LBSP is modified from local binary patterns in order to reduce computational complexity and better resist the influence of shadow and illumination changes. Joint colour and location feature are introduced to deal with the problem of indigent texture and scenario jitter. Then, LFGMM (Gaussian mixture model based on local fusion feature) is updated and learned by variational Bayes. In order to adapt to dynamic changing scenarios, the variational expectation maximisation algorithm is applied for distribution parameters optimisation. In this way, the optimal number of Gaussian components as well as their parameters can be automatically estimated with less time expended. Experimental results show that the authors’ method achieves outstanding detection performance especially under conditions of shadow disturbances, illumination changes, indigent texture and scenario jitter. Strong robustness and high accuracy have been achieved.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1751-9632
1751-9640
1751-9640
DOI:10.1049/iet-cvi.2016.0075