Anomaly detection in surveillance video based on bidirectional prediction
作者：
Highlights：
• Network for anomaly detection in surveillance video with remarkable stability and accuracy
• Bidirectional prediction network making better use of the temporal and spatial information
• Specific strategy of loss function to utilize the correlation between the forward and the backward predictions
• Valuble sliding window scheme for anomaly score calculation
摘要
•Network for anomaly detection in surveillance video with remarkable stability and accuracy•Bidirectional prediction network making better use of the temporal and spatial information•Specific strategy of loss function to utilize the correlation between the forward and the backward predictions•Valuble sliding window scheme for anomaly score calculation
论文关键词：Anomaly detection,Bidirectional prediction,Sliding window,U-Net
论文评审过程：Received 18 March 2020, Accepted 1 April 2020, Available online 13 April 2020, Version of Record 29 April 2020.
论文官网地址：https://doi.org/10.1016/j.imavis.2020.103915
