A wellness platform for stereoscopic 3D video systems using EEG-based visual discomfort evaluation technology.

Area of Science:

• Neuroscience and Brain-Computer Interfaces
• Human-Computer Interaction
• Display Technology

Background:

• Three-dimensional (3D) video technology offers immersive experiences but often suffers from visual discomfort (VD).
• Electroencephalography (EEG) is a valuable tool in cognitive neuroscience for monitoring brain activity.
• Existing 3D systems lack effective methods to objectively measure and mitigate viewer discomfort.

Purpose of the Study:

• To develop a novel wellness platform leveraging EEG to quantify visual discomfort (VD) during stereoscopic 3D (S3D) video viewing.
• To create an automated system for detecting severe VD perception using machine learning and EEG.
• To enable adaptive S3D content reconstruction for enhanced viewer comfort.

Main Methods:

• Identification of specific EEG signal features indicative of VD perception.
• Development of a machine learning-based brain-computer interface (BCI) framework for automated VD detection.
• Integration of the EEG-based VD index with adjustable stereo baseline S3D video systems.

Main Results:

• Demonstrated the feasibility of using EEG signals as a practical index for VD perception in S3D displays.
• Successfully developed a framework for automatic detection of severe VD based on EEG features.
• Established a system capable of adjusting S3D content parameters to minimize viewer discomfort.

Conclusions:

• The proposed EEG-based wellness platform offers a promising solution for mitigating visual discomfort in S3D viewing.
• This technology can be integrated with advanced S3D systems to personalize content and improve user experience.
• Further research is needed to address technical challenges and explore broader applications in S3D industries.