Generation of driver monitoring ground truth dataset – drowsiness

Dedicated driving simulator dataset collection campaign for generating ground truth datasets drowsiness detection. Our team applied combination of eye closure metrics, driving performance and physiological data analysis (ECG and EEG).

Domain: Interior sensing
Service: Methodology preparation, dataset collection and analysis


Our Tier 2 Partner needed ground truth dataset for the development of novel driver drowsiness detection algorithms as part of their driver monitoring product. Our team had to combine multiple measures including: driving performance, detailed eye-tracking and physiological data (EEG and ECG) to reference drowsiness levels. As driver drowsiness is a safety-critical state, our team proposed a safe and standardised solution that also enabled to generate relevant dataset.

The team developed proprietary methodology for collecting and referencing drivers’ drowsiness data while driving using a high-end driving simulator as well as a dedicated EEG and ECG setup. The study was conducted with human drivers from multiple ethnicities and age groups to meet requirements of international automotive standards.


  • Methodology of inducing drowsiness through sleep deprivation and accounting for circadian rhythm as well as applying monotonous driving conditions.
  • Using proprietary signal processing algorithms for driving performance and physiological data analysis.
  • Setting up dedicated 500 Hz physiological setup EEG and ECG and constant monitoring of signal quality.
  • Programming the high-end driving simulator.
  • Synchronising of multiple data acquisition systems.

Expertise fields

  • Biomedical physics
  • Signal processing
  • Data analysis
  • Cognitive and transport psychology
  • Software engineering (driving simulator and synchronising)

Also check

  • Interior sensing

    Generation of driver monitoring ground truth dataset – distraction

    Prepared and applied full laboratory setup for generating highly accurate ground truth datasets for vehicle interior sensing including driver monitoring in reference to distraction detection. We used a high-end motion capture system in the manufactured vehicle mock-up.

    Read more
  • Robotics

    Simulation module: ROS2-Unity3D

    We developed a ROS2 module that allows to integrate the Robot Operating System 2 with Unity3D for performance-oriented AV/ADAS simulation.

    Read more