VD-Net: An Edge Vision-Based Surveillance System for Violence Detection
The automation of surveillance systems, driven by the rapid development of computer vision technology, has significantly enhanced the analysis of surveillance videos, particularly in recognition of human activity, including behavior analysis and violence detection, thereby bolstering public and indu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10477487/ |
| _version_ | 1797236586621960192 |
|---|---|
| author | Mustaqeem Khan Abdulmotaleb El Saddik Wail Gueaieb Giulia De Masi Fakhri Karray |
| author_facet | Mustaqeem Khan Abdulmotaleb El Saddik Wail Gueaieb Giulia De Masi Fakhri Karray |
| author_sort | Mustaqeem Khan |
| collection | DOAJ |
| description | The automation of surveillance systems, driven by the rapid development of computer vision technology, has significantly enhanced the analysis of surveillance videos, particularly in recognition of human activity, including behavior analysis and violence detection, thereby bolstering public and industrial security. Despite these advancements, detecting and analyzing violent actions remains challenging, especially for real-time surveillance systems with limited computing power. We propose an artificial intelligence-based framework called VD-Net (Violence Detection Network), enabled by Intelligent Internet-of-Things (IIoT) to detect violent behavior in public and private spaces. The model utilizes lightweight special task temporal convolutional network (ST-TCN) blocks and several bottleneck layers to focus on salient features in the input sequence. The learned features passed from the classifier to discriminate between violent and nonviolent actions. Additionally, our system is supposed to trigger an alert if violence is detected, which is then communicated to relevant departments. We checked the robustness of our system by surveillance and non-surveillance datasets and ensured a 1-4 % improvement in State-of-The-Art (SoTA) accuracy. |
| first_indexed | 2024-04-24T17:06:13Z |
| format | Article |
| id | doaj.art-7d0755dc80344b4a92e829f5473d67f1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T17:06:13Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7d0755dc80344b4a92e829f5473d67f12024-03-28T23:00:25ZengIEEEIEEE Access2169-35362024-01-0112437964380810.1109/ACCESS.2024.338019210477487VD-Net: An Edge Vision-Based Surveillance System for Violence DetectionMustaqeem Khan0https://orcid.org/0000-0002-8020-3590Abdulmotaleb El Saddik1https://orcid.org/0000-0002-7690-8547Wail Gueaieb2https://orcid.org/0000-0001-6490-4648Giulia De Masi3https://orcid.org/0000-0003-3284-880XFakhri Karray4https://orcid.org/0000-0002-4217-1372Department of Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab EmiratesDepartment of Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab EmiratesSchool of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, CanadaTechnology Innovation Institute (TII), Abu Dhabi, United Arab EmiratesDepartment of Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab EmiratesThe automation of surveillance systems, driven by the rapid development of computer vision technology, has significantly enhanced the analysis of surveillance videos, particularly in recognition of human activity, including behavior analysis and violence detection, thereby bolstering public and industrial security. Despite these advancements, detecting and analyzing violent actions remains challenging, especially for real-time surveillance systems with limited computing power. We propose an artificial intelligence-based framework called VD-Net (Violence Detection Network), enabled by Intelligent Internet-of-Things (IIoT) to detect violent behavior in public and private spaces. The model utilizes lightweight special task temporal convolutional network (ST-TCN) blocks and several bottleneck layers to focus on salient features in the input sequence. The learned features passed from the classifier to discriminate between violent and nonviolent actions. Additionally, our system is supposed to trigger an alert if violence is detected, which is then communicated to relevant departments. We checked the robustness of our system by surveillance and non-surveillance datasets and ensured a 1-4 % improvement in State-of-The-Art (SoTA) accuracy.https://ieeexplore.ieee.org/document/10477487/Artificial intelligencecloud computingedge intelligenceInternet of Things (IoT)securitysmart city |
| spellingShingle | Mustaqeem Khan Abdulmotaleb El Saddik Wail Gueaieb Giulia De Masi Fakhri Karray VD-Net: An Edge Vision-Based Surveillance System for Violence Detection IEEE Access Artificial intelligence cloud computing edge intelligence Internet of Things (IoT) security smart city |
| title | VD-Net: An Edge Vision-Based Surveillance System for Violence Detection |
| title_full | VD-Net: An Edge Vision-Based Surveillance System for Violence Detection |
| title_fullStr | VD-Net: An Edge Vision-Based Surveillance System for Violence Detection |
| title_full_unstemmed | VD-Net: An Edge Vision-Based Surveillance System for Violence Detection |
| title_short | VD-Net: An Edge Vision-Based Surveillance System for Violence Detection |
| title_sort | vd net an edge vision based surveillance system for violence detection |
| topic | Artificial intelligence cloud computing edge intelligence Internet of Things (IoT) security smart city |
| url | https://ieeexplore.ieee.org/document/10477487/ |
| work_keys_str_mv | AT mustaqeemkhan vdnetanedgevisionbasedsurveillancesystemforviolencedetection AT abdulmotalebelsaddik vdnetanedgevisionbasedsurveillancesystemforviolencedetection AT wailgueaieb vdnetanedgevisionbasedsurveillancesystemforviolencedetection AT giuliademasi vdnetanedgevisionbasedsurveillancesystemforviolencedetection AT fakhrikarray vdnetanedgevisionbasedsurveillancesystemforviolencedetection |