Generative Neural Networks for Anomaly Detection in Crowded Scenes

Security surveillance is critical to social harmony and people's peaceful life. It has a great impact on strengthening social stability and life safeguarding. Detecting anomaly timely, effectively and efficiently in video surveillance remains challenging. This paper proposes a new approach, called S-2-VAE, for anomaly detection from video data. The S-2-VAE consists of two proposed neural networks: a Stacked Fully Connected Variational AutoEncoder (S-F-VAE) and a Skip Convolutional VAE (S-C-VAE). The S-F-VAE is a shallow generative network to obtain a model like Gaussian mixture to fit the distribution of the actual data. The S-C-VAE, as a key component of S(2-)VAE, is a deep generative network to take advantages of CNN, VAE and skip connections. Both S-F-VAE and S-C-VAE are efficient and effective generative networks and they can achieve better performance for detecting both local abnormal events and global abnormal events. The proposed S-2-VAE is evaluated using four public datasets. The experimental results show that the S-2-VAE outperforms the state-of-the-art algorithms. The code is available publicly at https://github.com/tianwangbuaa/.