Representation, Analysis of Bayesian Refinement Approximation Network: A Survey

TL;DR

This paper surveys the use of a modified U-Net deep learning model to approximate Bayesian refinement for background subtraction, aiming to restore lost information and improve denoising results over traditional methods.

Contribution

It introduces a modified U-Net architecture that combines background subtraction results with source images to better approximate Bayesian refinement, enhancing denoising performance.

Findings

Deep learning outperforms traditional methods in detail preservation.

The modified U-Net effectively restores information lost during background subtraction.

The approach improves denoising accuracy in background subtraction tasks.

Abstract

After an artificial model background subtraction, the pixels have been labelled as foreground and background. Previous approaches to secondary processing the output for denoising usually use traditional methods such as the Bayesian refinement method. In this paper, we focus on using a modified U-Net model to approximate the result of the Bayesian refinement method and improve the result. In our modified U-Net model, the result of background subtraction from other models will be combined with the source image as input for learning the statistical distribution. Thus, the losing information caused by the background subtraction model can be restored from the source image. Moreover, since the part of the input image is already the output of the other background subtraction model, the feature extraction should be convenient, it only needs to change the labels of the noise pixels. Compare with traditional methods, using deep learning methods superiority in keeping details.