Video Anomaly Detection Using the Optimization-Enabled Deep Convolutional Neural Network. (13th January 2021)

• Record Type: Journal Article
• Authors: Philip, Felix M; V, Jayakrishnan; F, Ajesh; P, Haseena
• Is Part Of: Computer journal. Volume 65:Number 5(2022)
• Page Start: 1272
• Page End: 1292
• Publication Date: 2021-01-13
• Subjects: video surveillance -- anomaly detection -- dragonfly-rider optimization algorithm -- deep convolutional neural network -- Histograms of Optical Flow Orientation -- magnitude; Computers -- Periodicals; 005.1
• DOI: 10.1093/comjnl/bxaa177
• Languages: English
• ISSNs: 0010-4620

Abstract

Abstract: In video surveillance, automatic detection of the anomalies is the active research area in computer technology. Even though various video anomaly detection methods are introduced, detecting anomalous events, such as illegal actions and crimes, is a major challenging issue in video surveillance. Thus, an effective automatic video anomaly detection strategy based on the deep convolutional neural network (deep CNN) is developed in this research. Initially, the input video surveillance is passed into the spatiotemporal feature descriptor, named Histograms of Optical Flow Orientation and Magnitude. The features obtained from the descriptor provide the optical flow details with the aspect of normal patterns from the scene. These patterns are further subjected to the deep CNN, which is trained using the proposed dragonfly-rider optimization algorithm (DragROA) to assure the classification either as an anomalous activity or normal. The proposed DragROA is the combination of the standard dragonfly optimization algorithm and the standard rider optimization algorithm. The implementation of the proposed DragROA-based deep CNN is carried out using two datasets, namely anomaly detection dataset and UMN dataset; the performance is analyzed using the metrics, namely accuracy, sensitivity and specificity. From the analysis, it is depicted that the proposed method obtains the maximum accuracy, sensitivity and specificity of 0.9922, 0.9809 and 1, respectively, for the UCSD dataset.