In order to improve the accuracy of video anomaly behavior detection, a new detection method based on generative adversarial networks for video foreground areas is proposed. First, the foreground and background masks of the ground truth video frame are extracted, to determine the foreground areas of the output video frames from generative adversarial networks. For the foreground areas under consideration, the foreground area peak signal-to-noise ratio (F-PSNR) is used to calculate the detection score of anomaly behaviors. The experimental results show that the proposed method can effectively improve the detection accuracy of video anomaly behaviors with a reduced detection time for the Avenue dataset, UCSD-Ped1 dataset and UCSD-Ped2 dataset.

In order to solve the challenges of video anomaly behavior detection, a new detection algorithm model is proposed based on masked convolution and external attention mechanism convolutional neural network. On the one hand, by masked convolution, it can restrict the effective regions of convolution to make the neural network efficiently learn, so as to model the positive moderate that is effective in the feathers of normal behavior. On the other hand, by combining with lightweight external attention mechanisms, the modeling quality of interested regions is improved. Convolutional neural network in reconstruction or predictive architectures is added in feature reconstruction loss to improve the detection accuracy of video abnormal behavior detection. The experimental results show that the proposed method can effectively improve the detection performance of video anomaly behaviors by 2.86%, 2.54% and 0.56% on the Avenue dataset, UCSD-Ped1 dataset and UCSD-Ped2 dataset, respectively.