Development of an Advanced Driver Assistance System Using RGB-D Camera

In recent years, the automotive industry has shown increased interest in Advanced Driver Assistance Systems (ADAS), especially those based on bio-signals. Recent advances in RGB-D technologies have provided effective solutions for tracking human activity based on depth data. In this paper is presented an ADAS system based on Kinect RGB-D camera for the identification of the driver's distraction. Using depth and colour information the proposed ADAS system is be able to identify the driver's head orientation and eye position. Based on this data, the driver's inattention is detected and the driver is warned by audio signals. The proposed ADAS system was evaluated using a Virtual Reality driver simulator for manual and visual distraction. The results show accurate recognition of driver's distraction.