Steer Clear

Skill LevelArea of FocusOperating System
IntermediateComputer Vision,
Healthcare, IoT,
Sensors, Smart Cities

The goal of Steer Clear is to help reduce the number of drivers that fall asleep at the wheel. Using computer vision and Eye Aspect Ratio (E.A.R) metrics to detect eye blinking, we can determine when the driver is drowsy and wake the driver through a combination of audio and tactile alerts. This computer vision technology has the potential to revolutionize the automotive industry, and it’s all thanks to the power of the DragonBoard™ 410c.

To help reduce traffic accidents and improve vehicle safety.

Detecting Drowsiness with the DragonBoard™ 410c “Detecting

Materials Required / Parts List / Tools

Source Code / Source Examples / Application Executable

Additional Resources

Build / Assembly

  • Install the latest version of Debian Linux on DragonBoard
  • Update the Dragonboard, Install dependencies and OpenCV on DragonBoard
  • $ sudo apt-get update
    $ sudo apt-get upgrade -y
    $ sudo apt-get dist-upgrade -u -y
    $ sudo apt-get clean
    $ sudo apt-get autoremove
    $ sudo apt-get install -y python3-pip
    $ sudo apt-get install -y python3-dev python3-tk python3-numpy
    $ sudo apt-get install -y python3-scipy
    $ sudo apt-get install -y python-opencv
    $ sudo apt-get install -y libopencv-dev
  • Download the source code from the Github Repository
  • Run the script from the terminal window
  • $ python


PDF icon steerclear.pdf709.24 KB