Design of an Embedded System to assess the level of Alertness in Human Drivers

Principal Investigator: Dr. Aurobinda Routray

Co-Principal Investigator: Dr. Pranab Kumar Dutta

Sponsor: Ministry of Electronics and Information Technology, Government of India

Co-researchers: Dr. Anjith George, Dr. Aritra Chaudhuri, Dr. SL Happy

On-board monitoring of the alertness level of an automotive driver has been a challenging research in transportation safety and management. In this project, we have developed a robust real-time embedded platform to monitor the loss of attention of the driver during day as well as night driving conditions based on image and speech signals.

The top right panel shows the near infra-red (NIR) LED panel, which is powered during the night driving, as well as during low lighting. The switch gets activated by an LDR. The LEDs are Gallium-Arsenide LEDs.

The camera is visible inside the gap of the steering wheel. The camera captures the facial images of the driver in real-time. It is connected to an Intel ARK Single Board Computer via USB.

There is also a small microphone connected beneath the camera. This is used for speech signal-based analysis of drowsiness.

A small display is mounted on the dashboard, which shows the drowsiness index of the driver in real-time.