Discovering Local Binary Pattern Equation for Foreground Object Removal in Videos
This work addresses the tedious and expert-dependent process of LBP design for video segmentation, offering an automated solution that is incremental in improving existing methods.
The paper tackled the problem of manually designing Local Binary Pattern (LBP) processes for foreground object removal in videos by introducing a symbolic regression method to automatically discover LBP formulas, resulting in significant qualitative and quantitative improvements over previous state-of-the-art LBP descriptors in experiments on outdoor urban scenes.
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.