Deep anomaly detection through visual attention in surveillance videos
Authors:
Open Access
- 16 October 2020
- journal article
- research article
- Published by Springer Nature in Journal of Big Data
- Vol. 7 (1) , 1-17
Abstract
This paper describes a method for learning anomaly behavior in the video by finding an attention region from spatiotemporal information, in contrast to the full-frame learning. In our proposed method, a robust background subtraction (BG) for extracting motion, indicating the location of attention regions is employed. The resulting regions are finally fed into a three-dimensional Convolutional Neural Network (3D CNN). Specifically, by taking advantage of C3D (Convolution 3-dimensional), to completely exploit spatiotemporal relation, a deep convolution network is developed to distinguish normal and anomalous events. Our system is trained and tested against a large-scale UCF-Crime anomaly dataset for validating its effectiveness. This dataset contains 1900 long and untrimmed real-world surveillance videos and splits into 950 anomaly events and 950 normal events, respectively. In total, there are approximately ~ 13 million frames are learned during the training and testing phase. As shown in the experiments section, in terms of accuracy, the proposed visual attention model can obtain 99.25 accuracies. From the industrial application point of view, the extraction of this attention region can assist the security officer on focusing on the corresponding anomaly region, instead of a wider, full-framed inspection.Keywords
Funding Information
- Kementerian Riset, Teknologi dan Pendidikan Tinggi (90/UN11.2.1/PT.01.03/DPRM/2020)
This publication has 43 references indexed in Scilit:
- Video anomaly detection based on locality sensitive hashing filtersPattern Recognition, 2016
- Video anomaly detection and localization using hierarchical feature representation and Gaussian process regression2015
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Action Localization with Tubelets from Motion2014
- Illumination-insensitive texture discrimination based on illumination compensation and enhancementInformation Sciences, 2014
- Real-time background modeling based on a multi-level texture descriptionInformation Sciences, 2014
- Abnormal Event Detection at 150 FPS in MATLAB2013
- Efficient adaptive density estimation per image pixel for the task of background subtractionPattern Recognition Letters, 2006
- Traffic monitoring and accident detection at intersectionsIEEE Transactions on Intelligent Transportation Systems, 2000
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997