Non-linear parametric Bayesian regression for robust background subtraction
Federico Tombari, Luigi Di Stefano, Alessandro Lanza, Stefano Mattoccia · 2009
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.