Artificial Intelligence and IoT Integration for Real-Time Violence Monitoring

Year : 2026 | Volume : 13 | Issue : 01 | Page : 39 45
    By

    Omkar Prakash Warkhade,

  • Sanchit Sanjay Khandalkar,

  • Siddharth Santosh Shinde,

  • Ankit Sudarshan Jawale,

  • Shiv Rajendra Margaje,

  • Sumit Hanmant Thombare,

  1. Student, Department of Computer Science and Engineering, Shri Chhatrapati Shivajiraje College of Engineering, Dhangawadi, Pune, Maharashtra, India
  2. Student, Department of Computer Science and Engineering, Shri Chhatrapati Shivajiraje College of Engineering, Dhangawadi, Pune, Maharashtra, India
  3. Student, Department of Computer Science and Engineering, Shri Chhatrapati Shivajiraje College of Engineering, Dhangawadi, Pune, Maharashtra, India
  4. Student, Department of Computer Science and Engineering, Shri Chhatrapati Shivajiraje College of Engineering, Dhangawadi, Pune, Maharashtra, India
  5. Student, Department of Computer Science and Engineering, Shri Chhatrapati Shivajiraje College of Engineering, Dhangawadi, Pune, Maharashtra, India
  6. Student, Department of Computer Science and Engineering, Shri Chhatrapati Shivajiraje College of Engineering, Dhangawadi, Pune, Maharashtra, India

Abstract

The peace and tranquility of any place can be affected greatly by the insurgence of violence and violent attacks that are perpetrated by individuals with malicious and nefarious intentions. These individuals terrorize the areas and can cause a lot of harm and damage to people and public property. The incidences of violence are undesirable and can be problematic to handle by the law enforcement agencies, as these acts are committed by finding a flaw in patrolling and striking when the officers are busy in another area. The lack of an automated mechanism for violence detection is noticed by the police forces due to the YOLO (you only look once) pressing need for integrating the various technological advancements to assist law enforcement in curbing the acts of violence through better and faster recognition. The main objective is to effectively capture the frames from the live video. To achieve the precise implementation of Deep Learning Models for the Inception Net for violence detection. The current approaches lack an effective framework to achieve effective detection of violence in real time, through the use of a live video stream. The primary goal of the suggested system is to use deep learning models to effectively record and analyze frames from live video broadcasts. Inception Net architecture, in particular, is used because of its shown capacity to identify subtle patterns suggestive of aggressive behavior and to extract complicated visual data. This AI-powered method can comprehend subtle visual cues and distinguish between normal and aggressive behaviors, in contrast to traditional systems that might only use motion detection or sound analysis. Because of processing power constraints, antiquated algorithms, or a lack of training datasets, current approaches frequently fail at real-time detection. However, a responsive, intelligent, and scalable violence detection system is now possible with the use of contemporary deep learning frameworks backed by IoT infrastructure. In addition to immediately alerting authorities, such a technology can aid in proactive crime prevention, improving public safety, and bringing peace back to places that are at risk.

Keywords: Crime prevention, inception net, law enforcement in curbing, live video, smart monitoring systems, violence and violent attacks, Yolo deep learning models

[This article belongs to Journal of Artificial Intelligence Research & Advances ]

How to cite this article:
Omkar Prakash Warkhade, Sanchit Sanjay Khandalkar, Siddharth Santosh Shinde, Ankit Sudarshan Jawale, Shiv Rajendra Margaje, Sumit Hanmant Thombare. Artificial Intelligence and IoT Integration for Real-Time Violence Monitoring. Journal of Artificial Intelligence Research & Advances. 2026; 13(01):39-45.
How to cite this URL:
Omkar Prakash Warkhade, Sanchit Sanjay Khandalkar, Siddharth Santosh Shinde, Ankit Sudarshan Jawale, Shiv Rajendra Margaje, Sumit Hanmant Thombare. Artificial Intelligence and IoT Integration for Real-Time Violence Monitoring. Journal of Artificial Intelligence Research & Advances. 2026; 13(01):39-45. Available from: https://journals.stmjournals.com/joaira/article=2026/view=237197


References

  1. Naik AJ, Gopalakrishna MT. Deep-violence: individual person violent activity detection in video. Multimed Tools Appl. 2021;80:18365–18380. doi:10.1007/s11042-021-10682-w.
  2. Patel M. Real-time violence detection using CNN-LSTM. [Preprint]. 2021. arXiv:2107.07578: doi:10.48550/arXiv.2107.07578.
  3. Peixoto B, Lavi B, Pereira Martin JP, Avila S, Dias Z, Rocha A. Toward subjective violence detection in videos. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2019 May 12–17; Brighton, UK. Piscataway (NJ): IEEE; 2019. p. 8276–8280. doi:10.1109/ICASSP.2019.8682833.
  4. AlDahoul N, Karim HA, Datta R, Gupta S, Agrawal K, Albunni A. Convolutional neural network–long short-term memory based IoT node for violence detection. 2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), Kota Kinabalu, Malaysia. 2021. p. 1–6. doi:10.1109/IICAIET51634.2021.9573691.
  5. Sernani P, Falcionelli N, Tomassini S, Contardo P, Dragoni AF. Deep learning for automatic violence detection: tests on the AIRTLab dataset. IEEE Access. 2021;9:160580–160595. doi:10.1109/ACCESS.2021.3131315.
  6. Kang MS, Park RH, Park HM. Efficient spatio-temporal modeling methods for real-time violence recognition. IEEE Access. 2021;9:76270–76285. doi:10.1109/ACCESS.2021.3083273.
  7. Moaaz MM, Mohamed EH. Violence detection in surveillance videos using deep learning. Al-Nashrah Al-Ma‘lūmātiyyah fī al-Ḥāsibāt wa al-Ma‘lūmāt. 2020;2(2):1–6.
  8. Vosta S, Yow KC. KianNet: a violence detection model using an attention-based CNN-LSTM structure. IEEE Access. 2024;12:2198–2209. doi:10.1109/ACCESS.2023.3339379.
  9. Ye L, Liu T, Han T, Ferdinando H, Seppänen T, Alasaarela E. Campus violence detection based on artificial intelligent interpretation of surveillance video sequences. Remote Sens. 2021;13(4):628. doi:10.3390/rs13040628.
  10. Vijeikis R, Raudonis V, Dervinis G. Efficient violence detection in surveillance. Sensors (Basel). 2022;22(6):2216. doi:10.3390/s22062216.
  11.  Nadeem MS, Franqueira VN, Kurugollu F, Zhai X. WVD: a new synthetic dataset for video-based violence detection. In: Proceedings of the International Conference on Innovative Techniques and Applications of Artificial Intelligence; 2019 Nov 19–21. Cham: Springer; 2019. p. 158–164.
  12. Huszár VD, Adhikarla VK, Négyesi I, Krasznay C. Toward fast and accurate violence detection for automated video surveillance applications. IEEE Access. 2023;11:18772–18793. doi:10.1109/ACCESS.2023.3245521.
  13. Aldehim G, Asiri MM, Aljebreen M, Mohamed A, Assiri M, Ibrahim SS. Tuna swarm algorithm with deep learning enabled violence detection in smart video surveillance systems. IEEE Access. 2023;11:95104–95113. doi:10.1109/ACCESS.2023.3310885.
  14. Abbass MAB, Kang HS. Violence detection enhancement by involving convolutional block attention modules into various deep learning architectures: comprehensive case study for UBI-Fights dataset. IEEE Access. 2023;11:37096–37107. doi:10.1109/ACCESS.2023.3267409.
Regular Issue Subscription Review Article
Volume 13
Issue 01
Received 05/04/2025
Accepted 19/07/2025
Published 19/02/2026
Publication Time 320 Days
84

Login


My IP

PlumX Metrics