GreenEye: Development of Real-Time Traffic Signal Recognition System for Visual Impairments

TL;DR

GreenEye is a real-time system designed to assist visually impaired pedestrians by accurately recognizing traffic signal colors and estimating crossing times, overcoming previous limitations of recognizing only red and green signals.

Contribution

The paper introduces GreenEye, a novel real-time traffic signal recognition system that handles multiple classes with high accuracy through improved data balancing techniques.

Findings

Initial training achieved 74.6% precision for traffic signals.

Data imbalance affected recognition accuracy, especially for less common classes.

After data stabilization, all classes achieved 99.5% precision.

Abstract

Recognizing a traffic signal, determining if the signal is green or red, and figuring out the time left to cross the crosswalk are significant challenges to visually impaired people. Previous research has focused on recognizing only two traffic signals, green and red lights, using machine learning techniques. The proposed method developed a GreenEye system that recognizes the traffic signals' color and tells the time left for pedestrians to cross the crosswalk in real-time. GreenEye's first training showed the highest precision of 74.6%; four classes reported 40% or lower recognition precision in this training session. The data imbalance caused low precision; thus, extra labeling and database formation were performed to stabilize the number of images between different classes. After the stabilization, all 14 classes showed excelling precision rate of 99.5%.