A Robust Multi Descriptor Fusion with One-Class CNN for Detecting Anomalies in Video Surveillance
K Chidananda, Amit Kumar · International Journal of Safety and Security Engineering · 2023
In the domain of computer vision and machine learning, Video Anomaly Detection (VAD) has emerged as a pivotal area of inquiry, particularly relevant to security, surveillance, and video analytics.The extraction of pertinent features from video data constitutes a foundational aspect of VAD, enabling the discernment of anomalous patterns and structures.Features such as motion, texture, shape, and aesthetics are extracted and tailored according to the exigencies of the application and the intrinsic properties of the video content.The amalgamation of multiple features is often requisite for refining the accuracy of anomaly detection systems.Given the inherent high dimensionality of video data, dimensionality reduction techniques have been employed to mitigate computational demands and enhance the precision of the anomaly detection process.The present study delineates a novel approach centered on the deployment of a One-Class Convolutional Neural Network (CNN).This network is exclusively trained on normal events to establish a baseline representation of typicality.During the evaluation phase, the network is tasked with predicting the normality or abnormality of new video segments against this established norm.Moreover, this work introduces a novel fused feature descriptor, referred to as the Multiple Feature Descriptor (MFD), which is designed to encapsulate the spatiotemporal attributes of video data effectively.The proposed methodology has been subjected to rigorous testing against publicly available datasets, where it has demonstrated superior performance, outstripping numerous contemporary state-of-the-art methods in both accuracy and computational efficiency.