A survey on deep learning-based real-time crowd anomaly detection for secure distributed video surveillance

Rezaee, Khosro; Rezakhani, Sara; Khosravi, Mohammad R.; Moghimi, Mohammad Kazem

doi:10.1007/s00779-021-01586-5

Cited by 64 publications

(26 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 135 ] showcases various techniques based on convolutional neural networks (CNNs) for anomaly detection in crowd behavior, whereas [ 99 ] opts for the analysis of a single scene in videos. With the recent advancements in deep learning (DL), [ 101 ] presents a real-time analysis of crowd anomaly detection in video surveillance and [ 85 ] provides a review of the techniques used in deep learning for anomaly detection. The recent surveys on anomaly detection and automated video surveillance are listed in Table 2 .…”

Section: Recent Surveys For Anomalies In Different Contextmentioning

confidence: 99%

Anomaly detection using edge computing in video surveillance system: review

Patrikar

Parate

2022

Int J Multimed Info Retr

View full text Add to dashboard Cite

The current concept of smart cities influences urban planners and researchers to provide modern, secured and sustainable infrastructure and gives a decent quality of life to its residents. To fulfill this need, video surveillance cameras have been deployed to enhance the safety and well-being of the citizens. Despite technical developments in modern science, abnormal event detection in surveillance video systems is challenging and requires exhaustive human efforts. In this paper, we focus on evolution of anomaly detection followed by survey of various methodologies developed to detect anomalies in intelligent video surveillance. Further, we revisit the surveys on anomaly detection in the last decade. We then present a systematic categorization of methodologies for anomaly detection. As the notion of anomaly depends on context, we identify different objects-of-interest and publicly available datasets in anomaly detection. Since anomaly detection is a time-critical application of computer vision, we explore the anomaly detection using edge devices and approaches explicitly designed for them. The confluence of edge computing and anomaly detection for real-time and intelligent surveillance applications is also explored. Further, we discuss the challenges and opportunities involved in anomaly detection using the edge devices.

show abstract

Section: Recent Surveys For Anomalies In Different Contextmentioning

confidence: 99%

Anomaly detection using edge computing in video surveillance system: review

Patrikar

Parate

2022

Int J Multimed Info Retr

View full text Add to dashboard Cite

show abstract

“…Crowd monitoring aims to attain a high-level understanding of crowd behavior by processing the scene in a global or local manner [30]. Macroscopic methods such as crowd density, crowd counting, and flow estimation, neglect the local features and focus on the scene as a whole [31,32].…”

Section: Crowd Monitoringmentioning

confidence: 99%

A Social Distance Estimation and Crowd Monitoring System for Surveillance Cameras

Al-Sa'D

Kıranyaz

Ahmad

et al. 2022

Sensors

View full text Add to dashboard Cite

Social distancing is crucial to restrain the spread of diseases such as COVID-19, but complete adherence to safety guidelines is not guaranteed. Monitoring social distancing through mass surveillance is paramount to develop appropriate mitigation plans and exit strategies. Nevertheless, it is a labor-intensive task that is prone to human error and tainted with plausible breaches of privacy. This paper presents a privacy-preserving adaptive social distance estimation and crowd monitoring solution for camera surveillance systems. We develop a novel person localization strategy through pose estimation, build a privacy-preserving adaptive smoothing and tracking model to mitigate occlusions and noisy/missing measurements, compute inter-personal distances in the real-world coordinates, detect social distance infractions, and identify overcrowded regions in a scene. Performance evaluation is carried out by testing the system’s ability in person detection, localization, density estimation, anomaly recognition, and high-risk areas identification. We compare the proposed system to the latest techniques and examine the performance gain delivered by the localization and smoothing/tracking algorithms. Experimental results indicate a considerable improvement, across different metrics, when utilizing the developed system. In addition, they show its potential and functionality for applications other than social distancing.

show abstract

“…Most research focuses on forecasting crowd activity in a public place using deep learning such as in [8] where researchers propose a new architecture called AHU-CROWD based on deep learning and CNNs for counting crowd from still images. [21] presents a review of the various studies for crowd counting using deep learning. Most of the surveillance applications are focused on the crowd's activity and predicting violent behavior using deep learning, but few aim to enhance security by automating the detection of non-permissible items in public places.…”

Section: Literature Reviewmentioning

confidence: 99%

Comparative Analysis of Pre-Trained Deep Neural Networks for Vision-Based Security Systems on a Novel Dataset

Sinha

Lalit

2021

2021 IEEE/ACM 8th International Conference on Big Data Computing, Applications and Technologies (BDCAT '21)

View full text Add to dashboard Cite

The era of neural networks has changed the world of automation by introducing smarter and more capable machines that can learn complex features from data. Transfer learning refers to using knowledge gained by a model and utilizing it for another machine learning task. In this research, the authors perform comparative analysis for feature extraction of several state-of-the-art neural networks. The authors also introduce a self-curated dataset and test the performance of Xception, VGG16, VGG19, ResNet50, InceptionV3, Incep-tionResNetV2, MobileNet and DenseNet121 pre-trained models as feature extractors on the dataset. On these extracted features, the researchers train a convolutional neural network and compare their performance and computational complexities. DenseNet121 and In-ceptionResNetV2 achieve the best performance but take longer time to train compared to other models. VGG16 and VGG19 architectures are computationally expensive due to their large number of parameters. We propose our system as a security application for public places where we need a bifurcation between the permissibility of toddlers and pets. Future work is centered around data security by employing federated learning algorithms and introducing new categories and expanding the data for a wider application.

show abstract

A survey on deep learning-based real-time crowd anomaly detection for secure distributed video surveillance

Cited by 64 publications

References 103 publications

Anomaly detection using edge computing in video surveillance system: review

Anomaly detection using edge computing in video surveillance system: review

A Social Distance Estimation and Crowd Monitoring System for Surveillance Cameras

Comparative Analysis of Pre-Trained Deep Neural Networks for Vision-Based Security Systems on a Novel Dataset

Contact Info

Product

Resources

About