CHOSUN

외부조명 변화를 고려한 운전자 졸음 감지 시스템

Metadata Downloads
Author(s)
최원웅
Issued Date
2016
Keyword
안전운전보조시스템 졸음감지 졸음운전 조명변화
Abstract
Drowsy driving is the greatest part in the cause of car accidents, accounts for approximately 31% of car accidents that occurred on expressways for the last three years, and approximately 23% thereof resulted from failing to watch the road forward, causing casualties. The reason of drowsy driving to have a fatal impact on driving as described above is that it causes slow response speed and inaccurate decision making. It is thus necessary to develop a system for identifying the state of driver's drowsiness and alerting the driver of drowsiness to avoid car accidents for preventing drowsy driving resulting in the aforementioned risks.
Therefore, car manufacturers and government organizations have studied how to directly and indirectly obtain and analyze data about driver's drowsiness to prevent accidents due to drowsy driving in advance. Exemplary technologies to analyze driver's drowsiness include contacting driver's body to measure signals, analyzing driver's eyes, analyzing whether driver's eyes are open or closed, and analyzing car's movement to examine driver's state as an indirect method.
In this study, a system is proposed for analyzing whether driver's eyes are open or closed on the basis of images to determine driver's drowsiness. The proposed system converts eye areas detected by a camera to a color space area to effectively detect eyes in a dark situation, for example, tunnels, and a bright situation due to a backlight. In addition, the system used a thickness distribution of a detected eye area as a feature value to analyze whether eyes are open or closed through the Support Vector Machine(SVM), representing 90.09% of accuracy. In the experiment for the images of driver wearing glasses, 83.83% of accuracy was obtained. In addition, in a comparative experiment with the existing PCA method by using Eigen-eye and Pupil Measuring System the detection rate is shown improved. After the experiment, driver's drowsiness was identified accurately by using the method of summing up the state of driver's eyes open and closes over time and the method of detecting driver's eyes that continue to be closed to examine drowsy driving.
Alternative Title
System for Detecting Driver's Drowsiness Considering Variations of External Illumination
Alternative Author(s)
Choi, Wonwoong
Affiliation
조선대학교 산업기술융합대학원 소프트웨어융합공학과
Department
산업기술융합대학원 소프트웨어융합공학과
Advisor
신주현
Awarded Date
2016. 2
Table Of Contents
제1장 서 론 1
제1절 연구 배경 및 목적 1
제2절 연구 내용 및 구성 4
제2장 졸음 감지 시스템에 대한 관련연구 5
제1절 뇌파를 이용한 졸음 인식 시스템 5
제2절 심전도를 이용한 졸음운전 방지 시스템 7
제3절 영상 기반의 졸음 감지 시스템 7
제3장 제안하는 졸음 감지 시스템 11
제1절 Viola Jones 알고리즘을 이용한 얼굴 및 눈 검출 12
1. 적분 영상 12
2. Haar like feature 13
3. Adaboost 13
4. Cascade 구조 13
제2절 조명 정규화 14
1. CIE L*a*b* 색상 공간 14
2. 히스토그램 평활화 16
3. 최소-최대 명도값을 이용한 이진화 18
제3절 특징값 추출 19
1. 레이블링 19
2. 관심영역 설정 20
3. 두께분포를 이용한 특징값 추출 20
제4절 SVM을 이용한 눈 개폐상태 판단 21
1. 선형 SVM 21
2. 특징값을 이용한 SVM 실험 22
제5절 졸음 판단 시스템 24
1. 시간에 따른 눈 개폐상태 누적 값을 이용한 방법 25
2. 연속적인 폐안 상태를 이용한 방법 26
제4장 실험 및 결과분석 27
제1절 데이터 취득 및 실험 환경 27
제2절 조명정규화 실험 및 비교 결과 28
제3절 SVM을 이용한 눈 개폐상태 실험 및 비교 결과 32
제4절 졸음운전 판단 결과 34
제5장 결 론 35
Degree
Master
Publisher
조선대학교 산업기술융합대학원
Citation
최원웅. (2016). 외부조명 변화를 고려한 운전자 졸음 감지 시스템
Type
Dissertation
URI
https://oak.chosun.ac.kr/handle/2020.oak/1941
http://chosun.dcollection.net/common/orgView/200000265427
Appears in Collections:
Engineering > Theses(Master)(산업기술창업대학원)
Authorize & License
  • AuthorizeOpen
Files in This Item:

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.