http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
영상 인식 및 생체 신호를 이용한 운전자 졸음 감지 시스템
이민혜,신성윤 한국정보통신학회 2022 한국정보통신학회논문지 Vol.26 No.6
Drowsy driving, one of the biggest causes of traffic accidents every year, is accompanied by various factors. As a general method to check whether or not there is drowsiness, a method of identifying a driver's expression and driving pattern, and a method of analyzing bio-signals are being studied. This paper proposes a driver fatigue detection system using deep learning technology and bio-signal measurement technology. As the first step in the proposed method, deep learning is used to detect the driver's eye shape, yawning presence, and body movement to detect drowsiness. In the second stage, it was designed to increase the accuracy of the system by identifying the driver's fatigue state using the pulse wave signal and body temperature. As a result of the experiment, it was possible to reliably determine the driver's drowsiness and fatigue in real-time images. 매년 교통사고의 가장 큰 원인으로 손꼽히는 졸음운전은 운전자의 수면 부족, 산소 부족, 긴장감의 저하, 신체의 피로 등과 같은 다양한 요인을 동반한다. 졸음 유무를 확인하는 일반적인 방법으로 운전자의 표정과 주행패턴을 파악하는 방법, 심전도, 산소포화도, 뇌파와 같은 생체신호를 분석하는 방법들이 연구되고 있다. 본 논문은 영상을 검출하는 딥러닝 모델과 생체 신호 측정 기술을 이용한 운전자 피로 감지 시스템을 제안한다. 제안 방법은 일차적으로 딥러닝을 이용하여 운전자의 눈 모양과 하품 유무, 졸음으로 예상되는 신체 동작을 파악하여 졸음 상태를 감지한다. 이차적으로 맥파 신호와 체온을 이용하여 운전자의 피로 상태를 파악하여 시스템의 정확도를 높이도록 설계하였다. 실험 결과, 실시간 영상에서 운전자의 졸음 유무 판별이 안정적으로 가능하였으며 각성상태와 졸음 상태에서의 분당 심박수와 체온을 비교하여 본 연구의 타당성을 확인할 수 있었다.
교통사고 저감을 위한 인공지능 기반 인캐빈 모니터링 시스템
이영우,강창우,김철중,이가영 한국디지털콘텐츠학회 2023 한국디지털콘텐츠학회논문지 Vol.24 No.11
Vision contains the majority of the information necessary for humans to interact with their surrounding environment. For these reasons, visually impaired individuals face significant limitations in terms of information access compared to non-visually impaired individuals. This paper proposes a system to enhance information accessibility for the visually impaired by extracting and translating text from images into Braille, enabling real-time implementation. The proposed system utilizes optical character recognition technology, specifically EasyOCR, and a Korean language recognition model to recognize and digitize text after separating phonemes. The hardware-implemented system operates through a relay and solenoid-based Braille system, allowing individuals with visual impairments to recognize the outputted Braille using tactile senses. This approach aims to reduce barriers to information access for the visually impaired, providing them with equal opportunities in various aspects compared to sighted individuals and fostering their active participation in society.
운전자 졸음 및 각성 상태 시 ECG신호 처리를 통한 심장박동 신호 특성 연구
이은지(EunJi Lee),이미래(Mirae Lee),김민수(Minsoo Kim),김윤년(Yoonnyun Kim),정지욱(Jiuk Jung),오성호(Sungho Oh),이재열(JeaYeol Lee),허윤석(Yunseok Heo) 한국자동차공학회 2013 한국자동차공학회 학술대회 및 전시회 Vol.2013 No.11
Traffic accident increase from carelessness driving is a serious problem in society with falling asleep at the wheel being responsible of about 23% of all traffic accidents. Distinct features in heart rate signals during the driver’s wake and sleep states could provide an initiative for the development of a safe driving systems such as drowsiness detecting sensor in a smart wheel. We measured ECG from 5 adult subjects during the wake and sleep states. After detecting R-peaks in ECG signal, heart rate signal was obtained. Heart rate variability was investigated for three different frequency regions; very-low-frequency (VLF), low-frequency (LF), and high-frequency (HF). The average power in VLF and LF frequency band increased from 14% to 21.6% and 38.87% to 40.53% respectively, while for HF band it reduced from 47.2% to 37.83%. The LF/HF ratio for sleep state (1.126) was larger than for wake state (0.082). In conclusion, there are changes in heart rate from wake to sleep that are potentially to be detected. The results in our study could be useful for the development of drowsiness detection sensors for effective real-time monitoring.