Abstract

Driver Monitoring is emerging as an essential requirement for Advanced Driving Assistance and Autonomous Driving systems. In this paper I have propose a real-time, IR camera- based driver monitoring system. Basic driver monitoring features include head tracking, gaze tracking, eye state analysis – blink rate, blink duration, eye open/close all of which can be used to implement driver safety applications like driver distraction and driver drowsiness detection. I propose a system where all these modules have been developed using deep learning which has made the solution more robust to different ethnicities, gender, lighting conditions and occlusions. I have also optimized the solution to run on any embedded platform (ARM, DSP, ASICs etc) without the need of GPU or cloud support during runtime. This helps in lowering power consumption and cost making the solution amenable for use in automotive.

More About DMS

Please read my attached Research Paper below.

Built With

Share this project:

Updates