Discovering Local Binary Pattern Equation for Foreground Object Removal in Videos

TL;DR

This paper introduces a symbolic regression method to automatically discover Local Binary Pattern formulas for effective foreground object removal in videos, reducing reliance on expert knowledge and trial-and-error.

Contribution

It presents a novel automated approach to generate LBP formulas, improving background subtraction performance in urban scene videos.

Findings

Discovered LBPs outperform previous descriptors qualitatively.

Discovered LBPs outperform previous descriptors quantitatively.

Method effective across various outdoor urban conditions.

Abstract

Designing a novel Local Binary Pattern (LBP) process usually relies heavily on human experts' knowledge and experience in the area. Even experts are often left with tedious episodes of trial and error until they identify an optimal LBP for a particular dataset. To address this problem, we present a novel symbolic regression able to automatically discover LBP formulas to remove the moving parts of a scene by segmenting it into a background and a foreground. Experimental results conducted on real videos of outdoor urban scenes under various conditions show that the LBPs discovered by the proposed approach significantly outperform the previous state-of-the-art LBP descriptors both qualitatively and quantitatively. Our source code and data will be available online.