Real Time and Surveillance Weapon Detection using Deep learning

International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 2, pp. 28-38, February 2026.

https://doi.org/10.58482/ijersem.v2i2.5

This work is licensed under a Creative Commons Attribution 4.0 International License.

Real Time and Surveillance Weapon Detection using Deep learning

Full Text PDF

G. Hemalatha

K. Sudhakar

Department of CSE, Gokula Krishna College of Engineering, Sullurpet, India.

Abstract: Security and safety is a big concern for today’s modern world. For a country to be economically strong, it must ensure a safe and secure environment for investors and tourists. Having said that, Closed Circuit Television (CCTV) cameras are being used for surveillance and to monitor activities i.e. robberies but these cameras still require human supervision and intervention. We need a system that can automatically detect these illegal activities. Despite state-of-the-art deep learning algorithms, fast processing hardware, and advanced CCTV cameras, weapon detection in real-time is still a serious challenge. Observing angle differences, occlusions by the carrier of the firearm and persons around it further enhances the difficulty of the challenge. This work focuses on providing a secure place using CCTV footage as a source to detect harmful weapons by applying the state of the art open-source deep learning algorithms. We have implemented binary classification assuming pistol class as the reference class and relevant confusion objects inclusion concept is introduced to reduce false positives and false negatives. No standard dataset was available for real-time scenario so we made our own dataset by making weapon photos from our own camera, manually collected images from internet, extracted data from YouTube CCTV videos, through GitHub repositories, data by university of Granada and Internet Movies Firearms Database (IMFDB) imfdb.org. Two approaches are used i.e. sliding window/classification and region proposal/object detection. Some of the algorithms used are VGG16, Inception-V3, Inception-ResnetV2, SSDMobileNetV1, Faster-RCNN Inception-ResnetV2 (FRIRv2), YOLOv3, and YOLOv4. Precision and recall count the most rather than accuracy when object detection is performed so these entire algorithms were tested in terms of them. Yolov4 stands out best amongst all other algorithms and gave a F1-score of 91% along with a mean average precision of 91.73% higher than previously achieved.

Keywords: Real-Time Weapon Detection, CCTV Surveillance Analytics, Deep Learning-Based Object Detection, YOLOv4 and Region Proposal Networks, Confusion Object Inclusion Strategy.

References: 

  1. T. Santos, H. Oliveira, and A. Cunha, “Systematic review on weapon detection in surveillance footage through deep learning,” Computer Science Review, vol. 51, p. 100612, Dec. 2023, doi: 10.1016/j.cosrev.2023.100612.
  2. M. H. Faheem, Q. E. U. Haq, T. M. Khan, and J. H. Kim, “Deep-Learning-Based weapon detection using drones equipped with infrared and color cameras,” International Journal of Digital Crime and Forensics, vol. 17, no. 1, pp. 1–16, Nov. 2025, doi: 10.4018/ijdcf.393088.
  3. D. Berardini, L. Migliorelli, A. Galdelli, and M. J. Marín-Jiménez, “Edge artificial intelligence and super-resolution for enhanced weapon detection in video surveillance,” Engineering Applications of Artificial Intelligence, vol. 140, p. 109684, Nov. 2024, doi: 10.1016/j.engappai.2024.109684.
  4. P. Yadav, N. Gupta, and P. K. Sharma, “A comprehensive study towards high-level approaches for weapon detection using classical machine learning and deep learning methods,” Expert Systems With Applications, vol. 212, p. 118698, Aug. 2022, doi: 10.1016/j.eswa.2022.118698.
  5. A. Castillo, S. Tabik, F. Pérez, R. Olmos, and F. Herrera, “Brightness guided preprocessing for automatic cold steel weapon detection in surveillance videos with deep learning,” Neurocomputing, vol. 330, pp. 151–161, Nov. 2018, doi: 10.1016/j.neucom.2018.10.076.
  6. G. Wang, H. Ding, M. Duan, Y. Pu, Z. Yang, and H. Li, “Fighting against terrorism: A real-time CCTV autonomous weapons detection based on improved YOLO v4,” Digital Signal Processing, vol. 132, p. 103790, Oct. 2022, doi: 10.1016/j.dsp.2022.103790.
  7. R. Pravesh and B. C. Sahana, “A dual-stage deep learning framework for simultaneous fire and firearm detection in smart surveillance systems,” Results in Engineering, vol. 27, p. 106330, Jul. 2025, doi: 10.1016/j.rineng.2025.106330.
  8. A. S. V. Rao, S. Kainth, A. Bhattacharya, and T. Amgoth, “An efficient weapon detection system using NSGCU-DCNN classifier in surveillance,” Expert Systems With Applications, vol. 255, p. 124800, Jul. 2024, doi: 10.1016/j.eswa.2024.124800.
  9. P. Yadav, N. Gupta, and P. K. Sharma, “Robust weapon detection in dark environments using Yolov7-DarkVision,” Digital Signal Processing, vol. 145, p. 104342, Dec. 2023, doi: 10.1016/j.dsp.2023.104342.
  10. H. Martinez, F. J. Rodriguez-Lozano, F. León-García, J. M. Palomares, and J. Olivares, “Distributed Fog computing system for weapon detection and face recognition,” Journal of Network and Computer Applications, vol. 232, p. 104026, Sep. 2024, doi: 10.1016/j.jnca.2024.104026.
  11. K. G. Dhuri and S. Patil, “Crime prediction against women in surveillance videos using deep learning models: A review,” Computers & Electrical Engineering, vol. 128, p. 110651, Sep. 2025, doi: 10.1016/j.compeleceng.2025.110651.
  12. S. Solak, B. Cetin, and M. H. B. Ucar, “Real-time theft detection in urban surveillance: A comparative analysis of YOLO-based approach,” Journal of Engineering Research, Nov. 2025, doi: 10.1016/j.jer.2025.11.009.
  •  
Download PDF

This article is part of Volume 2, Issue 2 (February 2026)