메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색

논문 기본 정보

자료유형
학위논문
저자정보

채종민 (경북대학교, 경북대학교 대학원)

지도교수
최두현
발행연도
2023
저작권
경북대학교 논문은 저작권에 의해 보호받습니다.

이용수9

표지
AI에게 요청하기
추천
검색

이 논문의 연구 히스토리 (2)

초록· 키워드

오류제보하기
Today, there are many accidents caused by drowsy driving, which lead to serious casualties, not just minor injuries. Many studies are being conducted to prevent this situation, but most of them are difficult to commercialize or have not been recognized for their effectiveness. Therefore, in order to prevent this situation, systems, solutions, and products that are convenient for drivers to use and can reliably prevent drowsy driving are needed. This paper presents a process for detecting a driver''s sleepiness by using heart rate data and image data, respectively. In order to utilize heart rate data, a detection model was developed by measuring and collecting an individual''s heart rate and learning a neural network to distinguish between a normal state and a drowsy state. As a result of applying the corresponding detection model to the test dataset, the binary classification correct answer rate, which distinguishes the steady state from the drowsy state, achieved about 99.5%. In order to utilize image data, a GUI program that can measure and collect data was created using Python''s PyQt, and EAR and eye blinking are measured through detection of eye feature points. If the state of closing eyes for more than 3 seconds accumulates three times within 1 minute, an algorithm that judges it as sleepiness and gives a notification signal was applied, and the test showed an accuracy of about 75%. If the test process using heart rate and image data proposed in this paper is combined and the algorithm is advanced, it can lead to the development of a device that can be used in the future, which can be easily used to prevent drowsy driving.

목차

1. 서론 1
1.1 연구 배경 및 목적 1
1.2 관련 시장 및 연구 동향 4
2. 이론적 배경 8
2.1 심박수 기반 졸음 기준 8
2.2 얼굴 특징점 기반 졸음 기준 10
2.2.1 MediaPipe 10
2.2.2 Face Mesh 11
2.2.3 얼굴 특징점 활용 정보 12
2.2.4 EAR 14
2.2.5 PERCLOS 15
3. 연구 방법 16
3.1 심박수 데이터 16
3.2 영상 데이터 22
4. 실험 과정 및 결과 26
4.1 심박수 데이터 학습 및 테스트 진행 26
4.2 영상 데이터 기반 테스트 30
4.3 영상 데이터와 심박수 간의 연관성 분석 34
5. 결론 39
참고문헌 40
Abstract 41

최근 본 자료

전체보기

댓글(0)

0