Human body abnormal behavior recognition method and device

The invention discloses a human body abnormal behavior recognition method and device, and the method comprises the steps of obtaining training video data in a security check scene, carrying out the framing preprocessing, obtaining a training video frame image set, carrying out the classification of each training video frame image, endowing each training video frame image with label information, and taking the classified training video frame images as a training sample set; building a generator according to a first residual error network built by the generator residual error block, and building a discriminator according to a second residual error network built by the discriminator residual error block, training a generative adversarial network constructed by the generator and the discriminator according to the training sample set, a preset first loss function and a preset optimization function to obtain an optimized discriminator model; constructing a classifier according to the optimized discriminator model,