Intelligent video anomaly detection and classification using faster RCNN with deep reinforcement learning model

Abstract

Recently, intelligent video surveillance applications have become essential in public security by the use of computer vision technologies to investigate and understand long video streams. Anomaly detection and classification are considered a major element of intelligent video surveillance. The aim of anomaly detection is to automatically determine the existence of abnormalities in a short time period. Deep reinforcement learning (DRL) techniques can be employed for anomaly detection, which integrates the concepts of reinforcement learning and deep learning enabling the artificial agents in learning the knowledge and experience from actual data directly. With this motivation, this paper presents an Intelligent Video Anomaly Detection and Classification using Faster RCNN with Deep Reinforcement Learning Model, called IVADC-FDRL model. The presented IVADC-FDRL model operates on two major stages namely anomaly detection and classification. Firstly, Faster RCNN model is applied as an object detector with Residual Network as a baseline model, which detects the anomalies as objects. Besides, deep Q-learning (DQL) based DRL model is employed for the classification of detected anomalies. In order to validate the effective anomaly detection and classification performance of the IVADC-FDRL model, an extensive set of experimentations were carried out on the benchmark UCSD anomaly dataset. The experimental results showcased the better performance of the IVADC-FDRL model over the other compared methods with the maximum accuracy of 98.50% and 94.80% on the applied Test004 and Test007 dataset respectively.

Empirical Study on Classifiers for Earlier Prediction of COVID-19 Infection Cure and Death Rate in the Indian States

“…The work was based on Fuzzy Multilevel Image thresholding using an improved Coyote Optimization Algorithm [ 54 ]. The techniques like deep reinforcement learning are employed in areas like anomaly detection that combine reinforcement learning and deep learning, which enables artificial agents to learn knowledge and experience actual data directly [ 55 ]. Further, big data analytical techniques are becoming ubiquitous for achieving optimized results and improving classification performances [ 56 ].…”

Intelligent deep learning-enabled autonomous small ship detection and classification model

“…Remarkably, the object identification in the channel is an essential part of safety control and navigation aids of autonomous ships. Ship detection through Synthetic Aperture Radar, surveillance video systems, and Satellite remote sensing (SAR) [4][5][6][7][8] gained considerable interest over the last few years, whereas the latter two could be applied directly in autonomous ships voyage.…”

A Cascade Attention Based Facial Expression Recognition Network by Fusing Multi-Scale Spatio-Temporal Features

“…Fortunately, deep reinforcement learning (DRL) techniques have recently been proposed, which enables the artificial agents to learn both the knowledge and experience directly from the actual data. As demonstrated in [25], DRL, which integrates the concepts of reinforcement learning and deep learning, can lead to better application results in anomaly detection. In other words, DRL can augment spatial features in multi-layer convolutional networks, which illuminated the idea of this study initially.…”