Multimodal Driver Response Data with Facial Video and EEG

EmoRoad is a multimodal dataset containing psychological, physiological, and behavioral responses collected from human subjects in diverse driving scenarios. The dataset includes identifiable facial video recordings, EEG signals, eye tracking, and other measures, requiring a signed Data Usage Agreement for controlled access. It was published by RCFCM Hong Kong and last updated in April 2026.

Use Cases

• Train multimodal models to correlate EEG signals and facial video recordings for real-time emotion detection in drivers.
• Analyze eye-tracking data alongside physiological measures to study attentional shifts and cognitive load during different driving scenarios.
• Develop fusion algorithms to integrate behavioral measures with physiological signals for predicting driver stress or fatigue levels.
• Validate models for human-vehicle interaction by using the synchronized multimodal responses as ground truth for driver state classification.

Strengths

• Dataset includes synchronized multimodal data streams (facial video, EEG, eye tracking) for holistic analysis.
• Access is governed by a formal Data Usage Agreement, ensuring controlled and ethical use of sensitive human-subject data.

Limitations

• Dataset contains identifiable personal data (facial video) that cannot be fully anonymized, limiting sharing and requiring strict access controls.
• The raw data is restricted and requires a manual request and approval process, which may delay research timelines.
• Specific sample size (number of participants, recordings) and temporal coverage are not provided in the available metadata.

Provenance

Source

RCFCM Hong Kong, published via figshare.

Collection Method

Collected from human subjects in driving scenarios using multimodal sensors.

Freshness

Last updated in April 2026, indicating recent maintenance.