FALL BEHAVIOR IDENTIFICATION METHOD BASED ON VIDEO CLASSIFICATION AND ELECTRONIC DEVICE

The present invention relates to the technical field of video monitoring, provides a fall behavior identification method based on video classification and an electronic device, and solves the problem of low identification accuracy of fall detection technology. The method comprises: detecting human skeleton key points in a video frame image to be identified; tracking a human target on the basis of the human skeleton key points, and acquiring a motion trajectory of the human target and the motion change process of the human skeleton key points; identifying a fall behavior in a human skeleton sequence diagram by using an ST-GCN model to obtain a first identification result; identifying a fall behavior in a video sequence by using an S3DFAST double-flow model to obtain a second identification result; and carrying out comprehensive judgment on the first identification result and the second identification result to obtain a final fall identification result. La présente invention se rapporte au domaine technique de