Object Detection: Surveillancing Cities for Citizens’ Safety and Protection Using Advanced Deep Learning Tools
DOI:
https://doi.org/10.21015/vtse.v14i1.2358Abstract
Weapon incidents result in casualties and loss of precious human lives every year. According to the Center for Disease Control (CDC) report, over 18500 people died in year 2025 in the USA due to gun violence. It is a well-known fact that the death rate from weaponization is increasing significantly. Firearm‑related violence affects every aspect of human security, from personal safety issues like domestic violence and road rage to broader social and financial consequences. It can also escalate into large‑scale armed conflicts that cause massive violence and account for many deaths. It is evident to surveillance our cities and societies for weapon objects using artificial intelligence (AI) and deep machine learning tools. The existing machine learning tools are not efficient at detecting different kinds of weapons. In this research, the contribution is threefold. Our first contribution is that we thoroughly investigated weapon detectio systems that uses deep learning and can based automated weapon detection system that allows the system to detect multiple weapons at the same time such as knife, handgun, and rifle automatically. We have used You Only Look Once (YOLO) v4 and Convolutional Neural network (CNN) for our experimentation. We have obtained several weapon images which are publicly available and have developed the datasets. Secondly, we have compared the performance of our deep learning models on multiple combinations of datasets (fewer images to several thousand images. The experimental evaluation has shown that the YOLOv4 outperformed the CNN. Lastly, we have proposed a method to improve the accuracy of the CNN and this has been accomplished by adding N number of CNN layers N times where N = {1,3,5,...19}. This has resulted in reducing the complexity of the model and improving the accuracy and efficiency. The proposed model can be applied on surveillance systems, closed-circuit televisions and other object detection systems and many human lives can be saved by timely detection of weapons.
References
A. Lamas et al., “Human pose estimation for mitigating false negatives in weapon detection in video-surveillance,” Neurocomputing, vol. 489, pp. 488–503, 2022, doi: 10.1016/j.neucom.2021.12.059.
S. Naz and F. Jabeen, “Towards improved assistive technologies: classification and evaluation of object detection techniques for users with visual impairments,” VAWKUM Transactions on Computer Sciences, vol. 12, no. 2, pp. 165–177, 2024.
A. Warsi, M. Abdullah, M. N. Husen, M. Yahya, S. Khan, and N. Jawaid, “Gun Detection System Using Yolov3,” 2019 IEEE 6th Int. Conf. Smart Instrumentation, Meas. Appl. ICSIMA 2019, no. August, pp. 27–29, 2019, doi: 10.1109/ICSIMA47653.2019.9057329.
Y. Huang, X. Fu, and Y. Zeng, “Anchor-Free Weapon Detection for X-Ray Baggage Security Images,” IEEE Access, vol. 10, no. August, pp. 97843–97855, 2022, doi: 10.1109/ACCESS.2022.3205593.
R. Reddy, K. Gyan Vallabh, and S. Sharan, “Multi-class weapon detection using multi contrast convolutional neural networks and faster region-based convolutional neural networks,” 2021 2nd Int. Conf. Emerg. Technol. INCET 2021, pp. 1–8, 2021, doi: 10.1109/INCET51464.2021.9456407.
M. Attique and M. Habib, “Weapons Detection for Security and Video Surveillance Using CNN and YOLO-V5s,” Comput. Mater. Contin., vol. 70, no. 2, pp. 2761–2775, 2022, doi: 10.32604/cmc.2022.018785.
A. Goenka, “Weapon Detection from Surveillance Images using Deep Learning,” 2022 3rd Int. Conf. Emerg. Technol., vol. 1, no. 1, pp. 1–6, 2022, doi: 10.1109/INCET54531.2022.98242.
H. Lokhande, “A review on weapon detection and alert system using deep neural networks,” Irjmets, vol. 4, no. 6, pp. 1–4, Jun. 2022.
N. Hnoohom, P. Chotivatunyu, N. Maitrichit, V. Sornlertlamvanich, S. Mekruksavanich and A. Jitpattanakul, “Weapon Detection Using Faster R-CNN Inception V2 for a CCTV Surveillance System,” 2021 25th International Computer Science and Engineering Conference (ICSEC), 2021, pp. 400-405, doi: 10.1109/ICSEC53205.2021.9684649.
U. V. Navalgund and P. K., “Crime Intention Detection System Using Deep Learning,” 2018 International Conference on Circuits and Systems in Digital Enterprise Technology (ICCSDET), 2018, pp. 1-6, doi: 10.1109/ICCSDET.2018.8821168.
Gelana and A. Yadav, “Firearm Detection from Surveillance Cameras Using Image Processing and Machine Learning Techniques,” Smart Innovations in Communication and Computational Sciences, pp. 25–34, Nov. 2018, doi: 10.1007/978-981-13-2414-7_3.
R. Reddy, K. Gyan Vallabh and S. Sharan, “Multiclass Weapon Detection using Multi Contrast Convolutional Neural Networks and Faster Region-Based Convolutional Neural Networks,” 2021 2nd International Conference for Emerging Technology (INCET), 2021, pp. 1-8, doi: 10.1109/INCET51464.2021.9456407.
N. U. Haq, M. M. Fraz, T. S. Hashmi, and M. Shahzad, “Orientation aware weapons detection in visual data: a benchmark dataset,” Computing, Jun. 2022, doi: 10.1007/s00607-022-01095-0.
G. Sidharth, “Weapon detection and suspicious activity using cnn and yolo 4,” Mar. 2022. [Online]. Available: http://dspace.srmist.edu.in/jspui/bitstream/123456789/45864/1/P12469.pdf
R. Olmos, S. Tabik, F. Perez-Hernandez, A. Lamas, and F. Herrera, “MULTICAST: MULTI Confirmation-level Alarm SysTem based on CNN and LSTM to mitigate false alarms for handgun detection in video-surveillance,” arXiv:2104.11653 [cs], May 2021.
A. Juneja, S. Juneja, and S. Jain, “Real Time Object Detection using CNN based Single Shot Detector Model,” Journal of Information Technology Management, vol. 13, no. 1, p. 63, 2021, doi: 10.22059/jitm.2021.80025.
S. Naz and F. Jabeen, “Towards Improved Assistive Technologies: Classification and Evaluation of Object Detection Techniques for Users with Visual Impairments,” VAWKUM Transactions on Computer Sciences, vol. 12, no. 2, pp. 165–177, Dec. 2024, doi: https://doi.org/10.21015/vtcs.v12i2.1911.
H. V Lokhande, “A review on weapon detection and alert system using deep neural networks,” irjmets, vol. 4, no. 06, pp. 1–4, 2022.
S. Ahmed, M. T. Bhatti, M. G. Khan, B. Lövström, and M. Shahid, “Development and Optimization of Deep Learning Models for Weapon Detection in Surveillance Videos,” Appl. Sci., vol. 12, no. 12, p. 5772, 2022, doi: 10.3390/app12125772.
S. Gawade, R. Vidhya, and R. Radhika, “Automatic Weapon Detection for Surveillance Applications,” SSRN Electron. J., 2022, doi: 10.2139/ssrn.4143822.
S. Narejo, B. Pandey, D. Esenarro Vargas, C. Rodriguez, and M. R. Anjum, “Weapon Detection Using YOLO V3 for Smart Surveillance System,” Math. Probl. Eng., vol. 2021, 2021, doi: 10.1155/2021/9975700.
N. Hnoohom, P. Chotivatunyu, N. Maitrichit, V. Sornlertlamvanich, S. Mekruksavanich, and A. Jitpattanakul, “Weapon Detection Using Faster R-CNN Inception-V2 for a CCTV Surveillance System,” ICSEC 2021 - 25th Int. Comput. Sci. Eng. Conf., pp. 400–405, 2021, doi: 10.1109/ICSEC53205.2021.9684649.
U. V. Navalgund and P. K. Priyadharshini, “Crime Intention Detection System Using Deep Learning,” 2018 Int. Conf. Circuits Syst. Digit. Enterp. Technol. ICCSDET 2018, 2018, doi: 10.1109/ICCSDET.2018.8821168.
M. T. Bhatti, M. G. Khan, M. Aslam, and M. J. Fiaz, “Weapon Detection in Real-Time CCTV Videos Using Deep Learning,” IEEE Access, vol. 9, pp. 34366–34382, 2021, doi: 10.1109/ACCESS.2021.3059170.
T. Tahir, “Performance Evaluation and Comparison of YOLOv4 and Multiple Layers of CNN for Weapon Detection,” Feb. 2023, doi: https://doi.org/10.36227/techrxiv.22060520.v1.
J. Elsner, T. Fritz, L. Henke, O. Jarrousse, S. Taing, and M. Uhlenbrock, “Automatic Weapon Detection in Social Media Image Data using a Two-Pass Convolutional Neural Network,” Eur. Law Enforc. Res. Bull., no. 4, p. tbc-tbc, 2018.
J. Ruiz-Santaquiteria, A. Velasco-Mata, N. Vallez, G. Bueno, J. A. Alvarez-Garcia, and O. Deniz, “Handgun Detection Using Combined Human Pose and Weapon Appearance,” IEEE Access, vol. 9, pp. 123815–123826, 2021, doi: 10.1109/ACCESS.2021.3110335.
J. Salido, V. Lomas, J. Ruiz-Santaquiteria, and O. Deniz, “Automatic handgun detection with deep learning in video surveillance images,” Appl. Sci., vol. 11, no. 13, 2021, doi: 10.3390/app11136085.
S. Nikkath Bushra, G. Shobana, K. Uma Maheswari, and N. Subramanian, “Smart Video Surveillance Based Weapon Identification Using Yolov5,” 2022 Int. Conf. Electron. Syst. Intell. Comput., vol. 1, no. 1, pp. 1–7, 2022, doi: 10.1109/ICESIC53714.2022.9783499.
F. Gelana and A. Yadav, Firearm Detection from Surveillance Cameras Using Image Processing and Machine Learning Techniques, vol. 851, no. January. Springer Singapore, 2020.
T. S. S. Hashmi, N. U. Haq, M. M. Fraz, and M. Shahzad, “Application of Deep Learning for Weapons Detection in Surveillance Videos,” 2021 Int. Conf. Digit. Futur. Transform. Technol. ICoDT2 2021, 2021, doi: 10.1109/ICoDT252288.2021.9441523.
A. Singh, T. Anand, S. Sharma, and P. Singh, “IoT Based Weapons Detection System for Surveillance and Security Using YOLOV4,” Proc. 6th Int. Conf. Commun. Electron. Syst. ICCES 2021, pp. 488–493, 2021, doi: 10.1109/ICCES51350.2021.9489224.
N. U. Haq, M. M. Fraz, T. S. S. Hashmi, and M. Shahzad, “Orientation Aware Weapons Detection In Visual Data: A Benchmark Dataset,” Comput., 2022, doi: 10.1007/s00607-022-01095-0.
M. Brahmaiah, S. R. Madala, and C. M. Chowdary, “Artificial Intelligence and Deep Learning for Weapon Identification in Security Systems,” J. Phys. Conf. Ser., vol. 2089, no. 1, 2021, doi: 10.1088/1742-6596/2089/1/012079.
Y. Ma, H. Chen, and J. Huo, “Assault Rifle Detection and Identification Based on Convolutional Neural Network YOLOv3,” 2021 3rd World Symp. Artif. Intell. WSAI 2021, pp. 1–4, 2021, doi: 10.1109/WSAI51899.2021.9486333.
A. O. Ramon and L. Barba Guaman, “Detection of weapons using Efficient Net and Yolo v3,” 2021 IEEE Lat. Am. Conf. Comput. Intell. LA-CCI 2021, pp. 0–5, 2021, doi: 10.1109/LA-CCI48322.2021.9769779.
R. Garg and S. Singh, “Intelligent Video Surveillance Based on YOLO: A Comparative Study,” 2021 7th IEEE Int. Conf. Adv. Comput. Commun. Control. ICAC3 2021, pp. 0–5, 2021, doi: 10.1109/ICAC353642.2021.9697321.
A. H. Ashraf et al., “Weapons detection for security and video surveillance using CNN and YOLO-V5s,” Comput. Mater. Contin., vol. 70, no. 2, pp. 2761–2775, 2022, doi: 10.32604/cmc.2022.018785.
A. Belurkar, A. Waghmare, S. Mallick, N. Waghamode, and P. R. Totare, “Weapon Detection using Yolov4, CNN,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 10, no. 4, pp. 2058–2062, 2022, doi: 10.22214/ijraset.2022.41702.
S. A. Ali Shah, M. Ahmad Al-Khasawneh, and M. I. Uddin, “Review of weapon detection techniques within the scope of street-crimes,” 2021 2nd Int. Conf. Smart Comput. Electron. Enterp. Ubiquitous, Adapt. Sustain. Comput. Solut. New Norm. ICSCEE 2021, pp. 26–37, 2021, doi: 10.1109/ICSCEE50312.2021.9498007.
M. V Girish, H. K. G. B. H, B. Prakash, and P. K. N, “Crime Detection In Videos And Alerting System Using Artificial Intelligence,” Turkish J. Comput. Math. Educ., vol. 12, no. 12, pp. 738–743, 2021.
S. Mahmud, S. Hossain, Y. Arafat, J. Rawnak Jahan, and R. Zannat, “Weapons Detection of Criminal Activities Based on Computer Vision,” Advances in Image and Video Processing, vol. 2, no. 4, p. 64, 2021, doi: 10.11648/j.advances.20210204.11.
V. Kaya, S. Tuncer, and A. Baran, “Detection and classification of different weapon types using deep learning,” Appl. Sci., vol. 11, no. 16, 2021, doi: 10.3390/app11167535.
V. Arulalan, T. Javali, S. Jha and P. Garg, “Object Detection Using YOLOv4 and PSO CNN,” Innovations and Advances in Cognitive Systems, ICIACS Conference, Springer, 2024.
K. Lu, F. Zhao, X. Xu and Y. Zhang, “An object detection algorithm combining self attention and YOLOv4 in traffic scenes,” in PLOS One, vol. 18, no. 05, 2023, doi: 10.1371/journal.pone.0285654.
M. Ali Shah and T. Tahir, “A Novel Model for Pneumonia Detection Using Hybrid CNN Architecture,” IPSI Transactions on Internet Research, Jan. 2025, doi: https://doi.org/10.58245/ipsi.tir.2501.04.
M. I.-U. Haque, M. Fatima, F. Waqas, S. Fatima, M. Bukhari, and M. Ahmed, “A Next Generation Real Time Framework for Drone Video Decoding Leveraging IoT-Enabled Communication Network,” VAWKUM Transactions on Computer Sciences, vol. 13, no. 2, pp. 205–219, Dec. 2025, doi: https://doi.org/10.21015/vtcs.v13i2.2266.
Downloads
Published
How to Cite
Issue
Section
License
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 (CC-By) 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 acknowledgement 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 (See The Effect of Open Access).
This work is licensed under a Creative Commons Attribution License CC BY
