AI and ML Enabled Video Analysis and Interpretation for Advanced Threat Detection in High-Security Zones
Main Article Content
Abstract
Project Traditional video. Looking into what happened after an event rely heavily on people watching the footage. Human operators have to look at hours of footage on screens to find threats or people who should not be there. This way of doing things is very likely to result in mistakes because people get tired and their attention wanders. As more and more surveillance cameras are put up in places and high-security areas it becomes impossible for people to watch all the footage.
This research paper talks about "AI and ML Enabled Video Analysis and Interpretation for Advanced Threat Detection in High-Security Zones" a way of using artificial intelligence and machine learning to analyze video that is specifically made for high-security places like the National Security Guard. Our system uses intelligence to replace people watching the footage. It is a system that can process video footage and is very good at finding weapons and firearms.
Using this system means that people do not have to watch the footage so there are no mistakes. It can process video files quickly and can even pick out the important parts of the video. The system also makes reports that can be downloaded away. This research shows how using intelligence can make security analysis better and more efficient and it is not limited by what people can do.
The Project "AI and ML Enabled Video Analysis and Interpretation for Advanced Threat Detection in High-Security Zones" system is an improvement over traditional video surveillance and post-event investigations. It uses intelligence and machine learning to analyze video footage, which makes it much faster and more accurate than people watching the footage. The system is also very good at finding weapons and firearms which makes it perfect for high-security places, like the National Security Guard.
Article Details
Section
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.
References
Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLOv8. GitHub. Retrieved from https://github.com/ultralytics/ultralytics. (Primary reference for the core AI object detection model used in the engine).
2. Carrara, F., Amato, G., Falchi, F., & Gennaro, C. (2021). Real-Time Firearm Detection in Video Surveillance using Deep Learning. International Conference on Computer Vision and Security (ICCVS), 112-120.
3. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779-788. (Foundational paper for the YOLO architecture).
4. Newman, S. (2021). Building Microservices: Designing Fine-Grained Systems (2nd ed.). O'Reilly Media. (Reference for the decoupled React, Node.js, and Flask architecture implemented in the system).
5. Bradski, G. (2000). The OpenCV Library. Dr. Dobb's Journal of Software Tools. (Reference for the computer vision library used for frame extraction and bounding box plotting).
6. Tilkov, S., & Vinoski, S. (2010). Node.js: Using JavaScript to Build High-Performance Network Programs. IEEE Internet Computing, 14(6), 80-83. (Reference for the backend Application Gateway handling the heavy video file ingestion).
7. Facebook Open Source. (2023). React – A JavaScript library for building user interfaces. Retrieved from https://reactjs.org. (Reference for the client-side dashboard and forensic PDF generation methodology).
8. Bhatti, M. T., & Khan, M. A. (2022). Automated Threat Detection in Smart City CCTV Networks using Convolutional Neural Networks. Journal of Artificial Intelligence and Surveillance Systems, 8(3), 45-59.
9. B. R. Ardabili et al., “Understanding Policy and Technical Aspects of AI-enabled Smart Video Surveillance to Address Public Safety,” Computational Urban Science, vol. 3, no. 21, May 2023.
10. M. Cabanillas-Carbonell, J. S. Rivera, and J. S. Muñoz, “Artificial Intelligence in Video Surveillance Systems for Suspicious Activity Detection and Incident Response: A Systematic Review,” Advances in Science and Technology Research Journal, vol. 19, no. 3, pp. 389–405, 2025.
11. G. Sreenu and M. A. Saleem Durai, “Intelligent Video Surveillance: A Review through Deep Learning Techniques for Crowd Analysis,” Journal of Big Data, vol. 6, no. 48, 2019.
12. P. K. L. Mahima et al., “AI Surveillance and Crime Detection: A Literature Review,” International Journal of Advanced Research in Computer and Communication Engineering, vol. 14, no. 10, Oct. 2025.
13. G. F. Shidik et al., “A Systematic Review of Intelligent Video Surveillance: Trends, Techniques, Frameworks, and Datasets,” IEEE Access, pp. 170457–170473, 2019.
14. J. Kukade and P. Panse, “Advanced Deep Learning Model for Anomaly Detection Based Video Surveillance System,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 5s, pp. 477–485, 2024.
15. K. Merit and M. Beladgham, “AI-based Violent Incident Detection in Surveillance Videos to Enhance Public Safety,” Journal of Telecommunications and Information Technology, vol. 102, no. 4, pp. 77–89, Dec. 2025.
16. H. Kim et al., “Intelligent Video Surveillance System with Abnormal Behavior Recognition and Metadata Retrieval,” IEIE Transactions on Smart Processing and Computing, vol. 13, no. 6, pp. 541–552, 2024.
17. P. S. Hanwate and A. T. Bhise, “Review of Technologies and Uses of Video Surveillance,” International Engineering Journal for Research & Development, 2024.
18. M. Asad et al., “An Analysis of Artificial Intelligence Techniques in Surveillance Video Anomaly Detection: A Comprehensive Survey,” Applied Sciences, vol. 13, no. 8, 2023.
19. V. K. Maurya, D. Kumar, K. Kishnawat, A. Lalawat, “ProExamina: Smart Quiz Platform for Online Assessment,” Journal of Emerging Technologies and Innovative Research (JETIR), 2025.