Efficient Lines Detection for Robot Soccer

TL;DR

This paper introduces a fast, lightweight line detection method for robot soccer that combines ELSED with color classification and PSO-based calibration, achieving real-time performance comparable to deep learning models on low-power robots.

Contribution

The paper presents a novel, efficient line detection pipeline that integrates ELSED, RGB color analysis, and PSO calibration, optimized for real-time robot soccer applications.

Findings

Achieves high detection accuracy similar to deep learning models.

Operates efficiently on low-power robotic hardware.

Provides a robust calibration method requiring few annotations.

Abstract

Self-localization is essential in robot soccer, where accurate detection of visual field features, such as lines and boundaries, is critical for reliable pose estimation. This paper presents a lightweight and efficient method for detecting soccer field lines using the ELSED algorithm, extended with a classification step that analyzes RGB color transitions to identify lines belonging to the field. We introduce a pipeline based on Particle Swarm Optimization (PSO) for threshold calibration to optimize detection performance, requiring only a small number of annotated samples. Our approach achieves accuracy comparable to a state-of-the-art deep learning model while offering higher processing speed, making it well-suited for real-time applications on low-power robotic platforms.