Real-time Weapon Detection in Surveillance Video Using YOLOv3-based Deep Learning Framework

International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 3, pp. 25-32, March 2026.

https://doi.org/10.58482/ijersem.v2i3.4

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

Real-time Weapon Detection in Surveillance Video Using YOLOv3-based Deep Learning Framework

Full Text PDF

Nallamari Dharani

Masi Reddy Santhi

Bandi Harshavardhan Reddy

G. Krishna Prasad Reddy

Chitti Boyina Siva Krishna

Department of CAD, Siddartha Institute of Science and Technology, Puttur, India.

Abstract: The rise in security threats has emphasized the need for intelligent surveillance systems capable of automatically detecting weapons in public and restricted areas. This paper presents a real-time weapon detection framework based on the YOLOv3 deep learning architecture. The model is trained and tested on a custom dataset containing firearms and knives captured from CCTV footage, ensuring robustness under diverse illumination and occlusion conditions. The framework performs end-to-end object detection without requiring manual feature extraction, thus achieving high speed and accuracy suitable for real-time applications. Experimental results demonstrate an average precision of 93.8% and inference speed exceeding 30 frames per second on standard GPU hardware, making it practical for deployment in smart surveillance environments. The system successfully identifies and localizes multiple weapons in crowded scenes, thereby enhancing situational awareness and aiding proactive security response.

Keywords: CCTV Analytics, Intelligent Security Systems, Object Detection, Real-time Surveillance, Weapon Detection.

References: 

  1. R. Girshick, J. Donahue, T. Darrell and J. Malik, “Region-Based Convolutional Networks for Accurate Object Detection and Segmentation,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 1, pp. 142-158, 1 Jan. 2016, doi: 10.1109/TPAMI.2015.2437384.
  2. N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA, 2005, pp. 886-893 vol. 1, doi: 10.1109/CVPR.2005.177.
  3. Sayyed Nagulmeera, Nagul Shareef Shaik, G.Minni, B Bhagya Lakshmi, “Early Detection of Alzheimer’s Disease with Deep Learning,” International Journal of Emerging Research in Engineering, Science, and Management, vol. 3, no. 3, pp. 20-25, 2024. doi: 10.58482/ijeresm.v3i3.4.
  4. J. Redmon and A. Farhadi, “YOLOV3: an incremental improvement,” arXiv.org, Apr. 08, 2018. https://arxiv.org/abs/1804.02767
  5. W. Liu et al., “SSD: Single Shot MultiBox Detector,” in Lecture notes in computer science, 2016, pp. 21–37. doi: 10.1007/978-3-319-46448-0_2.
  6. M. T. Bhatti, M. G. Khan, M. Aslam and M. J. Fiaz, “Weapon Detection in Real-Time CCTV Videos Using Deep Learning,” in IEEE Access, vol. 9, pp. 34366-34382, 2021, doi: 10.1109/ACCESS.2021.3059170.
  7. Tomás Santos, Hélder Oliveira, António Cunha, “Systematic review on weapon detection in surveillance footage through deep learning,” Computer Science Review, vol. 51, February 2024, doi: 10.1016/j.cosrev.2023.100612.
  8. Kunda Hemalatha, E Sasikala Reddy, “An Image Processing-Driven System for Fake Currency Detection,” International Journal of Emerging Research in Engineering, Science, and Management, vol. 2, no. 2, pp. 10-15, 2023. doi: 10.58482/ijeresm.v2i2.2.
  9. Daniele Berardini, Lucia Migliorelli, Alessandro Galdelli, Manuel J. Marín-Jiménez, “Edge artificial intelligence and super-resolution for enhanced weapon detection in video surveillance,” Engineering Applications of Artificial Intelligence, vol. 140, 15 January 2025, 10.1016/j.engappai.2024.109684.
  10. Guanbo Wang, Hongwei Ding, Mingliang Duan, Yuanyuan Pu, Zhijun Yang, Haiyan Li, “Fighting against terrorism: A real-time CCTV autonomous weapons detection based on improved YOLO v4,” Digital Signal Processing, vol. 132, 2023, doi: 10.1016/j.dsp.2022.103790.
  11. Alberto Lamas, Siham Tabik, Antonio Cano Montes, Francisco Pérez-Hernández, Jorge García, Roberto Olmos, Francisco Herrera, “Human pose estimation for mitigating false negatives in weapon detection in video-surveillance,” Neurocomputing, vol. 489, 2022, doi: 10.1016/j.neucom.2021.12.059.
  12. Erssa Arif, Syed Khuram Shahzad, Muhammad Waseem Iqbal, Muhammad Arfan Jaffar, Abdullah S. Alshahrani, Ahmed Alghamdi, “Automatic Detection of Weapons in Surveillance Cameras Using Efficient-Net,” Computers, Materials and Continua, vol. 72, Issue 3, 2022, doi: 10.32604/cmc.2022.027571.
  13. Pavinder Yadav, Nidhi Gupta, Pawan Kumar 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, 2023, doi: 10.1016/j.eswa.2022.118698.
  14. Jesus Ruiz-Santaquiteria, Alberto Velasco-Mata, Noelia Vallez, Oscar Deniz, Gloria Bueno, “Improving handgun detection through a combination of visual features and body pose-based data,” Pattern Recognition, vol. 136, 2023, doi: 10.1016/j.patcog.2022.109252.
  15. Ram Pravesh, Bikash Chandra Sahana, “A dual-stage deep learning framework for simultaneous fire and firearm detection in smart surveillance systems,” Results in Engineering, vol. 27, 2025, doi: 10.1016/j.rineng.2025.106330.
  16. Chenji Keerthipriya, Mahammadi Nigar Shaik, “Machine Learning-Based Approach for Cardiovascular Disease Detection and Classification,” International Journal of Emerging Research in Engineering, Science, and Management, vol. 2, no. 2, pp. 16-22, 2023. doi: 10.58482/ijeresm.v2i2.3.
Download PDF

This article is part of Volume 2, Issue 3 (March 2026)