Sumit Jha
Multimodal cues for Driver's Distraction
In the Multimodal Signal Processing lab at UT Dallas, I am working on modelling the driver's distraction which will help in designing active in-vehicle safety systems. By monitoring the driver's action his state of mind can be understood. This information can help warn about any impeding danger and save from potential accidents.
We are currently looking at the headpose of the driver to get information about the visual attention. Some of the questions we are looking to answer is, how much disparity is there between the driver's exact gaze direction and his headpose. How much does the head pose varies when the driver is looking in the certain direction. How well can the headpose be used to track the attention of the driver.