# Rejection-Cascade of Gaussians: Real-time adaptive background subtraction framework

## TL;DR

This paper introduces a real-time adaptive background subtraction framework called Rejection-Cascade of Gaussians (CoG), which significantly improves speed and accuracy over traditional GMM methods by employing a cascade approach inspired by Viola-Jones.

## Contribution

The paper proposes a novel cascade decomposition of Gaussian Mixture Models for background subtraction, achieving faster processing and higher accuracy, and demonstrates its application to deep learning models like VAE.

## Key findings

- Achieved 4-5x speed-up over baseline GMM.
- Realized 17% average accuracy improvement on Wallflowers datasets.
- Demonstrated applicability to deep architectures with initial results on CDW-2014.

## Abstract

Background-Foreground classification is a well-studied problem in computer vision. Due to the pixel-wise nature of modeling and processing in the algorithm, it is usually difficult to satisfy real-time constraints. There is a trade-off between the speed (because of model complexity) and accuracy. Inspired by the rejection cascade of Viola-Jones classifier, we decompose the Gaussian Mixture Model (GMM) into an adaptive cascade of Gaussians(CoG). We achieve a good improvement in speed without compromising the accuracy with respect to the baseline GMM model. We demonstrate a speed-up factor of 4-5x and 17 percent average improvement in accuracy over Wallflowers surveillance datasets. The CoG is then demonstrated to over the latent space representation of images of a convolutional variational autoencoder(VAE). We provide initial results over CDW-2014 dataset, which could speed up background subtraction for deep architectures.