Affiliation:
1. Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
2. Shanghai AI Laboratory, Shanghai 200232, China
Abstract
High-speed detection of abnormal frames in surveillance videos is essential for security. This paper proposes a new video anomaly–detection model, namely, feature trajectory–smoothed long short-term memory (FTS-LSTM). This model trains an LSTM autoencoder network to generate future frames on normal video streams, and uses the FTS detector and generation error (GE) detector to detect anomalies on testing video streams. FTS loss is a new indicator in the anomaly–detection area. In the training stage, the model applies a feature trajectory smoothness (FTS) loss to constrain the LSTM layer. This loss enables the LSTM layer to learn the temporal regularity of video streams more precisely. In the detection stage, the model utilizes the FTS loss and the GE loss as two detectors to detect anomalies. By cascading the FTS detector and the GE detector to detect anomalies, the model achieves a high speed and competitive anomaly-detection performance on multiple datasets.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference48 articles.
1. Learning to detect anomalies in surveillance video;Xiao;IEEE Signal Process. Lett.,2015
2. Anomaly detection;Prasad;Comput. Mater. Contin.,2009
3. Kim, I., Jeon, Y., Kang, J.W., and Gwak, J. (2022). RAG-PaDiM: Residual Attention Guided PaDiM for Defects Segmentation in Railway Tracks. J. Electr. Eng. Technol.
4. Recurrent Autoencoder Ensembles for Brake Operating Unit Anomaly Detection on Metro Vehicles;Kang;Comput. Mater. Contin.,2022
5. Kang, J., Kim, C.S., Kang, J.W., and Gwak, J. (2021). Anomaly detection of the brake operating unit on metro vehicles using a one-class lstm autoencoder. Appl. Sci., 11.