To effectively monitor students’ online classroom fatigue, this paper uses the improved YOLOv5s target detection model and the Dlib library to detect students’ classroom fatigue. First, the improved YOLOv5s face detection model is used to detect faces instead of the detection model in Dlib, and then the detected face images are input to the official open source Dlib library, and key parts of students’ mouths, eyes and heads are extracted using 68 face key point detectors. Then the student’s visual localization and facial features are fused, followed by the PERCLOS algorithm to give the new metrics EAR (eye aspect ratio) and MAR (mouth aspect ratio) of the student’s subject fatigue. The EAR, MAR and HPE (Human Posture Estimation) algorithms are also combined to calculate the student’s eye area, mouth area and head posture parameters. Finally, according to the set thresholds, students are detected and alerted to fatigue from three indicators: blinking frequency, yawning frequency and nodding drowsiness frequency. The proposed method is an effective method for monitoring students’ online classroom fatigue.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.