Citation

Teoh, Tai Shie and Em, Poh Ping and Ab Aziz, Nor Azlina (2022) Development of Driver Drowsiness Detection System. In: 2nd FET PG Engineering Colloquium Proceedings 2022, 1-15 December 2022, Multimedia University, Malaysia. (Unpublished)

Text 18_Teoh Tai Shie_PPM Extended Abstract_Second Half 2022.pdf Restricted to Registered users only Download (92kB)

Abstract

The number of road accidents in Malaysia is unacceptably high. It has increased from 414421 cases in the year 2010 to 567516 cases in the year 2019. Among all the road accidents, it is estimated that 20% of road accidents were caused by drowsiness. Hence, several driver drowsiness detection (DDD) systems have been developed to tackle this problem. They are based on vehicle diagnostics and the driver's physiological and behavioral features. However, the vehicle-diagnostics-based system is not reliable and affected by road conditions. The physiological-based system is intrusive to the driver due to the signal measuring tools while the behavioral-based system is affected by the unexpected features on the face. Therefore, to tackle this problem, a novel DDD system based on remote sensing information is proposed. In this system, the 3D point cloud data of the surrounding is obtained through the LiDAR sensor. Then, the vehicle position and the road geometric are extracted from the point cloud data for drowsiness detection. The recurrent neural network is used in the system because it has a temporal characteristic that can be utilized to make predictions on driver’s drowsiness. For the data collection, it is done by requesting 36 test subjects to drive the instrumented car on the North-South Expressway, urban and rural areas of Malacca at 2 different time periods (afternoon post-lunch dip 1 – 4 pm and nighttime 4 – 6 am). Once the model is trained and tested, the test subjects are required to drive the instrumented car with the DDD system at 3 different locations, at 2 different time periods. After driving the car, a survey will be conducted among the test subjects to investigate the effectiveness of the DDD system in identifying drowsy driving. This research is expected to reduce road fatalities, especially the accidents that came from drowsy drivers.

Item Type:	Conference or Workshop Item (Other)
Uncontrolled Keywords:	Pattern recognition systems
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	16 Feb 2023 07:13
Last Modified:	16 Feb 2023 07:13
URII:	http://shdl.mmu.edu.my/id/eprint/10854

Downloads

Edit (login required)