Fatigue detection system with haar cascade classifier

Nor Sany, Nor Saiful Amierrul and Mohd, Mohd Norzali (2021) Fatigue detection system with haar cascade classifier. Penerbit UTHM, UTHM.

Text P13488_43943fc69dd7a88945e47cd807505cff.pdf Restricted to Registered users only Download (976kB) | Request a copy

Abstract

Drowsy driving is one of the major contributing factors to Malaysia's rising accident statistics. Drowsiness may be caused by a few reasons including fatique. Therefore, this study proposes a design for image processing to detect fatique during driving using the Raspberry Pi 3 board. The Haar Cascade Classifier technique is used to recognize eyes and faces, while the Eye Aspect Ratio (EAR) algorithm is used to detect eyes blink (open and close) to fulfil the research's goal. The system's average EAR value ranged from 0.125 while the eyes were closed to 0.299 when the eyes were opened. This project is an upgraded version of a previous project that includes an LCD display with a touch panel and interaction between driver and system. For future improvement, a GPS can be implemented into the system so it can inform the driver the nearest Rest & Relaxation so they can go take a rest after receiving several warnings.

Item Type:	Other
Uncontrolled Keywords:	Fatigue detection system; drowsy driver; haar cascade classifier; eye aspect ratio
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions:	Faculty of Electrical and Electronic Engineering > Department of Electrical Engineering
Depositing User:	Mr. Abdul Rahim Mat Radzuan
Date Deposited:	14 Mar 2022 01:18
Last Modified:	14 Mar 2022 01:18
URI:	http://eprints.uthm.edu.my/id/eprint/6635

Actions (login required)

View Item