Fig. 3

Overview of our method. First, we use pretrained YOLOv3 [9] to detect the images we collected from classrooms. Results fall into two categories: one is the human body object provided for SE-HRNet pose estimation, and the other is the hunched posture object. Then the results of the hunched posture object are directly output, and the results of the human body object are cropped from the image. The cropped images are input into SE-HRNet for pose estimation. SE-HRNet detects the locations of 17 key points of the human body. The next step is to preprocess the data of output key points. We design an SVM classifier to classify the preprocessed key points of the human body. Then output the classification results. Finally, the proposed method applied to online detection of real surveillance images of the classroom