A fall detection method based on skeletal feature points
Aiming at the problem that the accuracy of behavior detection using Spatio-Temporal Graph Convolutional Network(ST-GCN)in the existing fall detection methods needs to be improved,and the time information is not enough uti-lized,a fall detection method based on lightweight YOLOv3 human target detection model combined with human skeletal fea-ture points is proposed.In this method,the AlphaPose algorithm is used to obtain the information of human skeletal feature points in real time.On the basis,combined with the improved ST-GCN model,the enhanced behavioral spatio-temporal infor-mation is extracted,so as to detect falls more accurately.The test results on the general data set and the self-built data set show that the method is effective in fall detection.
万方数据
维普
