Performance Enhancement of an SSVEP-Based Brain-Computer Interface in Augmented Reality through Adaptive Color Adjustment of Visual Stimuli for Optimal Background Contrast

Cheong-Un Kim , Seonghun Park , Chang-Hwan Im

IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society +

|

March 3, 2025

View abstract on PubMed

Summary

This study enhances brain-computer interface (BCI) systems in augmented reality (AR) by dynamically adjusting visual stimulus colors for better contrast. This novel approach significantly boosts performance, even in varied lighting conditions.

Area Of Science

Neuroscience
Computer Science
Human-Computer Interaction

Background

Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) offer a promising אך often limited interaction method.
Augmented reality (AR) environments present unique challenges for BCI visual stimuli due to transparent displays and dynamic backgrounds.
Optimizing visual stimulus presentation is crucial for improving BCI performance in AR.

Purpose Of The Study

To develop an SSVEP-BCI system with improved performance in AR environments.
To introduce a novel method for dynamically adjusting visual stimulus colors to maximize contrast against AR backgrounds.
To evaluate the effectiveness of this adaptive color strategy in both offline and online settings.

Main Methods

A novel algorithm was developed to extract background color information in AR environments.
The Hue, Saturation, Value (HSV) color model was employed to calculate and apply optimal stimulus colors for enhanced contrast.
Offline experiments compared different color determination strategies, followed by online experiments in indoor and outdoor conditions to assess feasibility.

Main Results

The proposed dynamic color adjustment strategy achieved a 95.0% classification performance in offline AR experiments with 17 participants (3.5s window size).
This performance significantly surpassed the conventional black-and-white stimulus color strategy.
Online experiments confirmed the strategy's robustness, showing no substantial performance degradation between indoor and outdoor environments.

Conclusions

Dynamically adjusting visual stimulus colors based on AR background contrast is a highly effective method for enhancing SSVEP-BCI performance.
The proposed method offers a significant improvement over traditional approaches, making BCIs more practical for AR applications.
The system demonstrates reliable performance across diverse environmental conditions, paving the way for more immersive and accessible AR-BCI integration.