Abnormal Behavior Detection in Real-time for Advanced Driver Assistance System (ADAS) using YOLO

Nowadays, YOLO object detection algorithms are used to reduce the calculation time and to overcome the problem of the traditional method of calculation in detection such as noise removing, angle rotating, taking much time in calculation. Abnormal driving behavior detection is based on a system that...

Full description

Saved in:
Bibliographic Details
Main Authors: Soe, May Thu, Zaw Min, Aung, Kyaw, Hayma Thida, Min Paing, Myo, Htet, Sai Myo, Aye, Bawin
Format: Conference Proceeding
Language:English
Subjects:
Abnormal driving behavior
Alarm systems
Behavioral sciences
CNN
Detection
Detection algorithms
Drowsiness
Face recognition
Object detection
Real-time systems
Vibrations
YOLO
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Nowadays, YOLO object detection algorithms are used to reduce the calculation time and to overcome the problem of the traditional method of calculation in detection such as noise removing, angle rotating, taking much time in calculation. Abnormal driving behavior detection is based on a system that is one of the developing recognition systems in the field of technology and enterprise. Abnormal driving behavior detection is based on the detection of phone, face, smoking conditions while driving, and drowsiness. In our proposed system, we proposed YOLO based drowsiness and abnormal behavior detection algorithm to assist the driving system and to reduce traffic accidents. Experimental results show that our proposed system can detect drowsiness and abnormal behavior of drivers not only with an accuracy of over 95% but also in real-time.
ISSN:2472-7660
DOI:10.1109/ISIEA54517.2022.9873672