Abnormal Event Detection Using Recurrent Neural Network
Xu-Gang Zhou, Liqing Zhang · 2015
In this paper, we introduce a simple but novel model to detect abnormal event in surveillance video using sparse autoencoder and recurrent neuron network. In this model, we first train a sparse autoencoder to extract features and use a sequence of temporal continuous features to train a recurrent neuron network to predict the subsequent features. We classify the frame as normal and abnormal based on the prediction error of recurrent neuron network. Experimental result on a crowd activity dataset verifies the effectiveness of our model and the implication of recurrent neural networks in abnormal detection is also discussed.