Driver Head Pose Estimation for Attention Monitoring

• Main Author: Mohammad Farhaan, Iqbal
• Format: Final Year Project Report
• Language: English
• Published: Universiti Malaysia Sarawak (UNIMAS) 2020
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://ir.unimas.my/id/eprint/34246/2/Mohammad%20Farhaan%20Iqbal.pdf; http://ir.unimas.my/id/eprint/34246/

Head pose estimation proves to be increasingly important for driver attention monitoring as well as for various human-computer interaction tasks in the car systems. An adoption of head pose estimation method is proposed to overcome difficulties of existing solutions, often built from custom bespoke hardware and sensor array, and achieve one that more closely and with less friction combines to the automotive industry in the vehicle environment application shaped around the drivers. The method is studied to adapt to lightweight processing on mobile devices to allow for a large potential user group. The proposed method implements cloud computing for further refined head pose estimation and facial analysis coupled with local pre-processing of the image sequence and initial detection. Head pose estimation is employed to help drivers correct their attention and keep focus on the road and primary tasks during drives. The project is proposed as a framework to be adopted in multiple application and run in the background and offer auditive corrective warnings to the driver.