Anomaly Detection in Surveillance Videos via Memory-augmented Frame Prediction

Anomaly detection in surveillance videos is a challenging task in computer vision, and can be defined as the detection of actions or events that do not conform to the expected behaviors. Most of the existing methods solve the task by minimizing the reconstruction errors between the ground-truth video frames and their reconstructed frames. However, these methods sometimes reconstruct anomalies well that results in high false detections and a decrease of the performance. Therefore, we propose a frame prediction method which is based on a memory-augmented scheme for anomaly detection. Our method regards anomaly detection as a frame prediction task, and uses a generative network to achieve the frame prediction. For generating high quality video frames, we embed a memory module into the generative network, which effectively improves the feature representation of normal events and reduces the representation of abnormal events. In addition, we adapt an attention mechanism to model the interdependence between feature channels. In order to evaluate our method, we introduce a new anomaly detection dataset that consists of real and multiscene surveillance videos. Extensive experiments on our dataset and publicly available datasets validate the effectiveness and robustness of our proposed method.