Automated Mathematical Equation Structure Discovery for Visual Analysis

TL;DR

This paper introduces a novel AI framework for automatic equation discovery in visual analysis, reducing human bias and improving feature extraction for tasks like background subtraction in videos.

Contribution

The proposed method automates equation discovery with minimal human intervention using generative networks, advancing applications in computer vision and scene analysis.

Findings

Effective in distinguishing moving objects from background

Reduces human bias in equation design

Demonstrates potential in real-world video analysis

Abstract

Finding the best mathematical equation to deal with the different challenges found in complex scenarios requires a thorough understanding of the scenario and a trial and error process carried out by experts. In recent years, most state-of-the-art equation discovery methods have been widely applied in modeling and identification systems. However, equation discovery approaches can be very useful in computer vision, particularly in the field of feature extraction. In this paper, we focus on recent AI advances to present a novel framework for automatically discovering equations from scratch with little human intervention to deal with the different challenges encountered in real-world scenarios. In addition, our proposal can reduce human bias by proposing a search space design through generative network instead of hand-designed. As a proof of concept, the equations discovered by our framework are used to distinguish moving objects from the background in video sequences. Experimental results show the potential of the proposed approach and its effectiveness in discovering the best equation in video sequences. The code and data are available at: https://github.com/carolinepacheco/equation-discovery-scene-analysis