Smart City Gnosys

Smart city article details

Title	Deepguard: Enhancing Violence Detection In Smart Cities Through Deep Learning
ID_Doc	18135
Authors	Al-Mamun Provath M.; Rahman M.; Deb K.; Kumar Dhar P.; Shimamura T.
Year	2025
Published	IEEE Access, 13
DOI	http://dx.doi.org/10.1109/ACCESS.2025.3541059
Abstract	Video violence detection is essential to ensure public safety in smart cities, particularly in the context of political violence. Existing datasets and traditional methods for video violence detection often fall short of capturing the complexities of political violence, limiting the effectiveness of current models. To address these gaps, we propose a comprehensive approach that includes the development of a new dataset specifically focused on political violence, comprising 480 labeled video clips across four distinct categories. This dataset provides a broader understanding of political violence and is a benchmark for future research. We fine-tuned the Mobile Video Network (MoViNet-A0) to achieve an accuracy of 92.86% with 1.904M parameters. In addition, a custom keyframe extraction algorithm was designed, using temporal and pixel-level features to improve stability and accuracy. Our approach outperforms state-of-the-art methods, demonstrating high accuracy across multiple benchmark datasets. These results underscore the effectiveness of our system in detecting political violence, which offers significant implications for improving security measures and informing policy decision-making. © 2013 IEEE.
Author Keywords	keyframe extraction; political violence; security; Smart cities; video violence detection

Similar Articles

Id	Similarity	Authors	Title	Published
3466	0.914	Elzein A.; Basaran E.; Yang Y.D.; Qaraqe M.	A Novel Multi-Scale Violence And Public Gathering Dataset For Crowd Behavior Classification	Frontiers in Computer Science, 6 (2024)
61134	0.9	Khan H.; Yuan X.; Qingge L.; Roy K.	Violence Detection From Industrial Surveillance Videos Using Deep Learning	IEEE Access, 13 (2025)
7918	0.895	Khan M.; Gueaieb W.; Saddik A.E.; De Masi G.; Karray F.	An Efficient Violence Detection Approach For Smart Cities Surveillance System	Proceedings of 2023 IEEE International Smart Cities Conference, ISC2 2023 (2023)
4582	0.888	Baba, M; Gui, V; Cernazanu, C; Pescaru, D	A Sensor Network Approach For Violence Detection In Smart Cities Using Deep Learning	SENSORS, 19, 7 (2019)
8959	0.887	Mumtaz N.; Ejaz N.; Habib S.; Mohsin S.M.; Tiwari P.; Band S.S.; Kumar N.	An Overview Of Violence Detection Techniques: Current Challenges And Future Directions	Artificial Intelligence Review, 56, 5 (2023)
34805	0.884	Azzakhnini M.; Saidi H.; Azough A.; Tairi H.; Qjidaa H.	Lavid: A Lightweight And Autonomous Smart Camera System For Urban Violence Detection And Geolocation	Computers, 14, 4 (2025)
57685	0.883	Huszar V.D.; Adhikarla V.K.; Negyesi I.; Krasznay C.	Toward Fast And Accurate Violence Detection For Automated Video Surveillance Applications	IEEE Access, 11 (2023)
60873	0.883	Khan M.; Saddik A.E.; Gueaieb W.; De Masi G.; Karray F.	Vd-Net: An Edge Vision-Based Surveillance System For Violence Detection	IEEE Access, 12 (2024)
950	0.883	Ullah F.U.M.; Obaidat M.S.; Ullah A.; Muhammad K.; Hijji M.; Baik S.W.	A Comprehensive Review On Vision-Based Violence Detection In Surveillance Videos	ACM Computing Surveys, 55, 10 (2023)
22444	0.873	Ren X.; Fan W.; Wang Y.	Efficiently Adapting Large Pre-Trained Models For Real-Time Violence Recognition In Smart City Surveillance	Journal of Real-Time Image Processing, 21, 4 (2024)