Future Frame Prediction Using Convolutional VRNN for Anomaly Detection
It addresses the problem of detecting anomalies in videos for surveillance and security applications, offering a novel approach that incorporates temporal information.
The paper tackles anomaly detection in videos by proposing a sequential generative model for future frame prediction, achieving superior performance compared to state-of-the-art methods on three benchmark datasets.
Anomaly detection in videos aims at reporting anything that does not conform the normal behaviour or distribution. However, due to the sparsity of abnormal video clips in real life, collecting annotated data for supervised learning is exceptionally cumbersome. Inspired by the practicability of generative models for semi-supervised learning, we propose a novel sequential generative model based on variational autoencoder (VAE) for future frame prediction with convolutional LSTM (ConvLSTM). To the best of our knowledge, this is the first work that considers temporal information in future frame prediction based anomaly detection framework from the model perspective. Our experiments demonstrate that our approach is superior to the state-of-the-art methods on three benchmark datasets.