Non-linear parametric Bayesian regression for robust background subtraction

Authors:
Federico Tombari;Alessandro Lanza;Luigi Di Stefano;Stefano Mattoccia
Affiliations:
DEIS-ARCES, University of Bologna, Bologna, Italy;DEIS-ARCES, University of Bologna, Bologna, Italy;DEIS-ARCES, University of Bologna, Bologna, Italy;DEIS-ARCES, University of Bologna, Bologna, Italy
Venue:
WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Year:
2009

Citing 10
Cited 0

Illumination independent change detection for real world image sequences

Computer Vision, Graphics, and Image Processing
Non-parametric local transforms for computing visual correspondence

ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
Pfinder: Real-Time Tracking of the Human Body

IEEE Transactions on Pattern Analysis and Machine Intelligence
Ordinal Measures for Image Correspondence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Non-parametric Model for Background Subtraction

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Illumination-Invariant Change Detection Using a Statistical Colinearity Criterion

Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
An Intensity-augmented Ordinal Measure for Visual Correspondence

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
The use of the area under the ROC curve in the evaluation of machine learning algorithms

Pattern Recognition
Comparametric equations with practical applications in quantigraphic image processing

IEEE Transactions on Image Processing
Image change detection algorithms: a systematic survey

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel statistical method for background subtraction aimed at robustness with regards to common disturbance factors such as sudden illumination changes, variations of the camera parameters, noise. The proposed approach relies on a novel non-linear parametric model for the local effect of disturbance factors on a neighbourhood of pixel intensities. Assuming additive gaussian noise, we also propose Bayesian estimation of model parameters by means of a maximum-a-posteriori regression and a statistical change detection test. Experimental results demonstrate that the proposed approach is state-of-the-art in sequences where disturbance factors yield linear as well as non-linear intensity transformations.