Universal Background Subtraction based on Arithmetic Distribution Neural Network

TL;DR

This paper introduces a novel neural network framework called Arithmetic Distribution Neural Network (ADNN) for universal background subtraction, leveraging distribution operations and Bayesian refinement to improve accuracy and efficiency.

Contribution

The paper presents the first neural network layers based on arithmetic distribution operations for background subtraction, with a simple architecture and superior performance.

Findings

Outperforms state-of-the-art traditional methods.

Uses probability density functions from histograms effectively.

Achieves promising results with a simple neural network architecture.

Abstract

We propose a universal background subtraction framework based on the Arithmetic Distribution Neural Network (ADNN) for learning the distributions of temporal pixels. In our ADNN model, the arithmetic distribution operations are utilized to introduce the arithmetic distribution layers, including the product distribution layer and the sum distribution layer. Furthermore, in order to improve the accuracy of the proposed approach, an improved Bayesian refinement model based on neighboring information, with a GPU implementation, is incorporated. In the forward pass and backpropagation of the proposed arithmetic distribution layers, histograms are considered as probability density functions rather than matrices. Thus, the proposed approach is able to utilize the probability information of the histogram and achieve promising results with a very simple architecture compared to traditional convolutional neural networks. Evaluations using standard benchmarks demonstrate the superiority of the proposed approach compared to state-of-the-art traditional and deep learning methods. To the best of our knowledge, this is the first method to propose network layers based on arithmetic distribution operations for learning distributions during background subtraction.