Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network
Background and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the Hajj. In order to maintain the security of the pilgrims, the Saudi government has installed about 5000 closed circuit television (CCTV) cameras to monitor crowd activity efficiently. Problem: As a resul...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/24/8291 |
_version_ | 1797500832877379584 |
---|---|
author | Shabana Habib Altaf Hussain Waleed Albattah Muhammad Islam Sheroz Khan Rehan Ullah Khan Khalil Khan |
author_facet | Shabana Habib Altaf Hussain Waleed Albattah Muhammad Islam Sheroz Khan Rehan Ullah Khan Khalil Khan |
author_sort | Shabana Habib |
collection | DOAJ |
description | Background and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the Hajj. In order to maintain the security of the pilgrims, the Saudi government has installed about 5000 closed circuit television (CCTV) cameras to monitor crowd activity efficiently. Problem: As a result, these cameras generate an enormous amount of visual data through manual or offline monitoring, requiring numerous human resources for efficient tracking. Therefore, there is an urgent need to develop an intelligent and automatic system in order to efficiently monitor crowds and identify abnormal activity. Method: The existing method is incapable of extracting discriminative features from surveillance videos as pre-trained weights of different architectures were used. This paper develops a lightweight approach for accurately identifying violent activity in surveillance environments. As the first step of the proposed framework, a lightweight CNN model is trained on our own pilgrim’s dataset to detect pilgrims from the surveillance cameras. These preprocessed salient frames are passed to a lightweight CNN model for spatial features extraction in the second step. In the third step, a Long Short Term Memory network (LSTM) is developed to extract temporal features. Finally, in the last step, in the case of violent activity or accidents, the proposed system will generate an alarm in real time to inform law enforcement agencies to take appropriate action, thus helping to avoid accidents and stampedes. Results: We have conducted multiple experiments on two publicly available violent activity datasets, such as Surveillance Fight and Hockey Fight datasets; our proposed model achieved accuracies of 81.05 and 98.00, respectively. |
first_indexed | 2024-03-10T03:09:32Z |
format | Article |
id | doaj.art-3f530aa861e347e9bf8cc127ad2d9e86 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T03:09:32Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-3f530aa861e347e9bf8cc127ad2d9e862023-11-23T10:29:26ZengMDPI AGSensors1424-82202021-12-012124829110.3390/s21248291Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural NetworkShabana Habib0Altaf Hussain1Waleed Albattah2Muhammad Islam3Sheroz Khan4Rehan Ullah Khan5Khalil Khan6Department of Information Technology, College of Computer, Qassim University, Buraydah 52571, Saudi ArabiaInstitute of Management Sciences (IMSciences), Peshawar 25000, PakistanDepartment of Information Technology, College of Computer, Qassim University, Buraydah 52571, Saudi ArabiaDepartment of Electrical Engineering, College of Engineering and Information Technology, Unaizah Colleges, Unaizah 56447, Saudi ArabiaDepartment of Electrical Engineering, College of Engineering and Information Technology, Unaizah Colleges, Unaizah 56447, Saudi ArabiaDepartment of Information Technology, College of Computer, Qassim University, Buraydah 52571, Saudi ArabiaDepartment of Information Technology and Computer Science, Pak-Austria Fachhochschule Institute of Applied Sciences and Technology, Haripur 22620, PakistanBackground and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the Hajj. In order to maintain the security of the pilgrims, the Saudi government has installed about 5000 closed circuit television (CCTV) cameras to monitor crowd activity efficiently. Problem: As a result, these cameras generate an enormous amount of visual data through manual or offline monitoring, requiring numerous human resources for efficient tracking. Therefore, there is an urgent need to develop an intelligent and automatic system in order to efficiently monitor crowds and identify abnormal activity. Method: The existing method is incapable of extracting discriminative features from surveillance videos as pre-trained weights of different architectures were used. This paper develops a lightweight approach for accurately identifying violent activity in surveillance environments. As the first step of the proposed framework, a lightweight CNN model is trained on our own pilgrim’s dataset to detect pilgrims from the surveillance cameras. These preprocessed salient frames are passed to a lightweight CNN model for spatial features extraction in the second step. In the third step, a Long Short Term Memory network (LSTM) is developed to extract temporal features. Finally, in the last step, in the case of violent activity or accidents, the proposed system will generate an alarm in real time to inform law enforcement agencies to take appropriate action, thus helping to avoid accidents and stampedes. Results: We have conducted multiple experiments on two publicly available violent activity datasets, such as Surveillance Fight and Hockey Fight datasets; our proposed model achieved accuracies of 81.05 and 98.00, respectively.https://www.mdpi.com/1424-8220/21/24/8291CCTVCNNLSTMlightweightHajj pilgrims monitoringviolent activity recognition |
spellingShingle | Shabana Habib Altaf Hussain Waleed Albattah Muhammad Islam Sheroz Khan Rehan Ullah Khan Khalil Khan Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network Sensors CCTV CNN LSTM lightweight Hajj pilgrims monitoring violent activity recognition |
title | Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network |
title_full | Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network |
title_fullStr | Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network |
title_full_unstemmed | Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network |
title_short | Abnormal Activity Recognition from Surveillance Videos Using Convolutional Neural Network |
title_sort | abnormal activity recognition from surveillance videos using convolutional neural network |
topic | CCTV CNN LSTM lightweight Hajj pilgrims monitoring violent activity recognition |
url | https://www.mdpi.com/1424-8220/21/24/8291 |
work_keys_str_mv | AT shabanahabib abnormalactivityrecognitionfromsurveillancevideosusingconvolutionalneuralnetwork AT altafhussain abnormalactivityrecognitionfromsurveillancevideosusingconvolutionalneuralnetwork AT waleedalbattah abnormalactivityrecognitionfromsurveillancevideosusingconvolutionalneuralnetwork AT muhammadislam abnormalactivityrecognitionfromsurveillancevideosusingconvolutionalneuralnetwork AT sherozkhan abnormalactivityrecognitionfromsurveillancevideosusingconvolutionalneuralnetwork AT rehanullahkhan abnormalactivityrecognitionfromsurveillancevideosusingconvolutionalneuralnetwork AT khalilkhan abnormalactivityrecognitionfromsurveillancevideosusingconvolutionalneuralnetwork |