Anomaly-Driven Video Anomaly Detection Based on Depth-Separable Convolution
Video anomaly detection has become a hot issue in current research with profound practical application value.Aiming at the prob-lems of high computational complexity of 3D convolution in video anomaly detection,difficulty in training,and easy overfitting by utilizing on-ly normal data when using reconstruction methods for detection,a novel deeply deparable convolutional anomaly-driven network is proposed.The network firstly extracts jump frames as pseudo-anomaly samples through manual feature extraction to assist training,secondly designs the deeply deparable convolutional network to reduce the number of computational parameters for 3D convolution,and finally allows the network to learn to differentiate between anomalous and normal data by minimizing the reconstruction error of normal data and maximizing the anoma-lous data.Experimental results show that the model exhibits competitive performance on all major public datasets,with accuracy rates of 91.3%,99.2%,87.4%and 98.6%on UCSDped1,UCSDped2,Avenue and UMN datasets,respectively.In addition,the model has strong sensitivity to anomaly detection,and has strong generalization ability and robustness.
国家科技期刊平台
NSTL
万方数据
