http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 백 태 균1, 이 상 록2 (검색결과 1 건)
- 무료
- 기관 내 무료
- 유료
-
얼굴 감지기반의 운전자 졸음 방지 시스템에서 영상 크기의 영향 분석
백 태 균1, 이 상 록2 신한대학교 2023 신한대학교 논문집 Vol.46 No.-
This paper analyze the system performance according to the image size at a driver drowsiness prevention system based on face detection. The driver’s face detection is performed using the Python Dlib library based on machine-learning. This system records a video with Full HD resolution and then adjusts the image size to the 4 types of resolution. And it applies HOG and linear SVM to detect the face area, and adopts the EAR criteria to determine driver’s drowsiness. The factors of performance evaluation are an average FPS and detection accuracy, and the performance is compared and analyzed according to 4 types of resolution. As a result of experimenting by applying the system on Raspberry Pi 4, it is possible to secure over 90% accuracy even at SD360 resolution. The average FPS of SD360 resolution is 20.44, which is more than 3 times improved compared to HD resolution. As a result, it is confirmed that it is possible to implement a real-time driver drowsiness prevention system based on face detection even with SD360 resolution of 640*360 size.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
