Normality Learning in Multispace for Video Anomaly Detection
- 23 November 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 31 (9) , 3694-3706
Abstract
Video anomaly detection is a challenging task owing to the rare and diverse nature of abnormal events. However, most of the existing methods only learn the normality in a single space, focusing on low-level detailed features, which is easily affected by unimportant pixels. To address this issue, in this study, we propose a semi-supervised method based on the generative adversarial network and frame prediction, wherein the normality is learned in both the original image space and latent space, and the events deviating from the normality are detected as anomalies. In particular, given a video clip, we first predict a future frame and minimize the prediction errors between the generated frame and its ground truth. Thereafter, we encode the predicted frames and their ground truths in the latent space and minimize their differences. In the testing phase, we calculate the normal scores of each frame in both the image and latent spaces to obtain a comprehensive evaluation. Utilizing the multispace can capture more normality distribution information of the data, which can benefit anomaly detection. The results of experiments on three benchmark datasets demonstrate the effectiveness of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (61671274, 61876098, 61906107)
- Special Funds for Distinguished Professors of Shandong Jianzhu University
- Natural Science Foundation of Shandong Province of China (ZR2019BF010)
This publication has 54 references indexed in Scilit:
- A Discriminative Framework for Anomaly Detection in Large Videos2016
- Toward Abnormal Trajectory and Event Detection in Video SurveillanceIEEE Transactions on Circuits and Systems for Video Technology, 2016
- Spherical torus-based video hashing for near-duplicate video detectionScience China Information Sciences, 2016
- FlowNet: Learning Optical Flow with Convolutional Networks2015
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Abnormal Event Detection at 150 FPS in MATLAB2013
- Sparse reconstruction cost for abnormal event detection2011
- Online detection of unusual events in videos via dynamic sparse coding2011
- Anomaly detectionACM Computing Surveys, 2009
- Long Short-Term MemoryNeural Computation, 1997