Bidirectional Spatio-Temporal Feature Learning With Multiscale Evaluation for Video Anomaly Detection
- 13 July 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (12) , 8285-8296
Abstract
Video anomaly detection aims to detect the segments containing abnormal events from video sequence, which is a current research hotspot due to the importance in maintaining social security. Recent detection methods tend to build frame reconstruction or frame prediction model based on deep learning to learn features of events. The reconstruction-based methods reproduce the input frame one-to-one, inevitably losing some temporal features. The prediction-based methods predict frames according to the natural time order, but ignore the reverse time information, causing the deviation in information learning. Besides, anomaly evaluation methods based on patch-level error neglect the diversity of object sizes in complex scenes, and it is difficult to determine the optimal size of the error patch accurately. For these issues, we propose a bidirectional spatio-temporal feature learning framework with multi-scale anomaly evaluation strategy. A video sequence is input to a double-encoder double-decoder network, and bidirectional spatio-temporal features are obtained for bidirectional prediction by fusing forward and backward features extracted from the two encoders. The multi-scale anomaly evaluation method is implemented based on error pyramid and mean pooling, which effectively detects target objects with different sizes. Experiments on several publicly video datasets show that our method outperforms most of existing methods.Keywords
Funding Information
- Special Project of Technological Innovation and Application Development of Chongqing (cstc2019jscx-msxmX0167)
- National Natural Science Foundation of China (61501069)
This publication has 42 references indexed in Scilit:
- Detecting anomalous events in videos by learning deep representations of appearance and motionComputer Vision and Image Understanding, 2017
- Object Detection Networks on Convolutional Feature MapsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Learning Temporal Regularity in Video Sequences2016
- Analyzing Tracklets for the Detection of Abnormal Crowd Behavior2015
- Abnormal Event Detection at 150 FPS in MATLAB2013
- Sparse reconstruction cost for abnormal event detection2011
- A system for learning statistical motion patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Human Detection Using Oriented Histograms of Flow and Appearance2006
- Semi-Supervised Adapted HMMs for Unusual Event Detection2005
- Histograms of Oriented Gradients for Human Detection2005