Enhanced Adversarial Learning Based Video Anomaly Detection with Object Confidence and Position

Video anomaly detection is to identify the abnormal objects, positions and behaviours during the video sequences. It is an important but challenging problem in intelligent video surveillance. Nowadays, there is much concern about the generative adversarial networks (GAN) to detect anomalies which contains two parts: generator and discriminator. However, the two networks of this model are hard to train well at the same time in practical use. In this paper, we propose to exploit object detection to enhance the adversarial learning model and to improve classification method to distinguish anomalies in a semi-supervised manner. We also detect object position anomaly in our proposed model which can not be done in generative adversarial learning models separately. The proposed framework is evaluated on dataset UCSD Ped1 and Ped2 using two criteria: area under the curve (AUC) and equal error rate (EER). The results confirm that our proposed method can effectively improve object variety anomaly performance and detect object position anomaly and is also superior to the baseline. Our approach also achieves improved performance compared with recent state-of-the-art methods.