Abnormal Event Detection In Videos Using Hybrid Spatio-Temporal Autoencoder

The LSTM Encoder-Decoder framework is used to learn representation of video sequences and applied for detect abnormal event in complex environment. However, it generally fails to account for the global context of the learned representation with a fixed dimension representation and the learned representation is crucial for decoder phase. Based on the LSTM Encoder-Decoder and the Convolutional Autoencoder, we explore a hybrid autoencoder architecture, which not only extracts better spatio-temporal context, but also improves the extrapolate capability of the corresponding decoder with the shortcut connection. The experimental results demonstrate that our approach outperforms lots of state-of-the-art methods on benchmark datasets.