Video anomaly detection system using deep convolutional and recurrent models

Automatic identification of anomalies in video surveillance is an interesting research field. Even though interactive multimedia anomaly detection algorithms have been developed, it is still hard for video surveillance to find unusual things like illegal activities and crimes. In this study, a deep...

Full description

Saved in:
Bibliographic Details
Published inResults in engineering Vol. 18; p. 101026
Main Authors Qasim, Maryam, Verdu, Elena
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.06.2023
Elsevier
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:Automatic identification of anomalies in video surveillance is an interesting research field. Even though interactive multimedia anomaly detection algorithms have been developed, it is still hard for video surveillance to find unusual things like illegal activities and crimes. In this study, a deep convolutional neural network (CNN) and a simple recurrent unit (SRU) are used to build an automated system that can find anomalies in videos. The ResNet architecture takes high-level feature representations from the video frames that come in, while the SRU collects temporal features. The SRU has expressive recurrence and allows for highly parallelized implementation, which makes the video anomaly detection system more accurate. In the study, three models to detect anomalies are suggested as ResNet18 + SRU, ResNet34 + SRU, and ResNet50 + SRU, respectively. The suggested models are examined using the UCF-Crime dataset. This study made a clear distinction between normal and unusual actions, showing that CNN + SRU were able to put each unusual action in the right category. Using the UCF-Crime dataset, ResNet18 + SRU achieved 88.92% accuracy, ResNet34 + SRU achieved 89.34% accuracy, and ResNet50 + SRU achieved 91.24% accuracy. Furthermore, the proposed models demonstrated significantly higher performance accuracy and outscored the comparable deep learning models. •Suggests leveraging a combined deep learning model to identify anomalous behavior from a multiple-learning approach.•ResNet-18/34/50 has been used as CNN models in the proposed system for anomaly detection.•SRU is supplied with spatial features extracted presenting recurrence and enables highly parallelized implementation.
ISSN:2590-1230
2590-1230
DOI:10.1016/j.rineng.2023.101026