A Framework for Detection and Recognition of Armed Persons Using Convolutional Neural Networks
DOI:
https://doi.org/10.67378/6ntqfx78Keywords:
Framework, Detection, Recognition, Armed person, Neural network.Abstract
Security threats posed by concealed weapons have necessitated the development of advanced detection techniques. In this study, a model for the detection and recognition of armed persons using Convolutional Neural Networks (CNNs) was investigated. The model utilizes thermal imaging data, preprocessing techniques, and supervised learning to detect and classify hidden weapons. Key performance metrics, including accuracy, precision, recall, and F1-score, are employed to evaluate the model’s effectiveness. The investigated approach demonstrates improved detection rates compared to conventional methods, offering a robust solution for security applications. The study also explores various deep learning techniques, dataset preparation strategies, and potential real-world applications.
References
A. Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet classification with deep convolutional neural networks," in Proc.
NIPS, 2012.
J. Redmon et al., "You Only Look Once: Unified, Real-Time Object Detection," in Proc. CVPR, 2016.
Y. Zhang et al., "Millimeter-wave imaging for concealed weapon detection using deep learning," IEEE Trans. Image
Process., vol. 29, pp. 1241-1254, 2020.
X. Li et al., "Thermal imaging-based deep learning for security applications," IEEE Access, vol. 8, pp. 4321-4334, 2021. [5] S. Ren et al., "Faster R-CNN: Towards real-time object detection with region proposal networks," IEEE Trans. PAMI,
2017.
K. He et al., "Mask R-CNN," in Proc. ICCV, 2017.
R. Singh et al., "Deep learning-based weapon detection in surveillance videos," IEEE Access, vol. 9, pp. 76375-76385,
2021.
Y. Zhou et al., "Fusion of thermal and visible images for enhanced object detection using CNNs," IEEE Sensors J., vol. 20,
no. 15, pp. 8474-8485, 2020.
H. Wang et al., "Hybrid deep learning models for concealed weapon detection," Pattern Recognit. Lett., vol. 138, pp. 17-
25, 2020.
A. Dosovitskiy et al., "An image is worth 16x16 words: Transformers for image recognition at scale," ICLR, 2021.
Liu et al., "Concealed object detection using hyperspectral imaging and deep learning," Pattern Recognition Letters,
2021.
Zhao et al., "Security surveillance with infrared object detection," IEEE Sensors Journal, 2019.
Xie et al., "Automatic gun detection in video surveillance systems using CNNs," IEEE Access, 2020.
Choi et al., "Real-time detection of dangerous objects in public spaces with AI-based models," Computers & Security,
2021.
Huang et al., "Hybrid deep learning models for intelligent surveillance," Expert Systems with Applications, 2022.
Patel et al., "Comparison of deep learning architectures for security threat detection," Neural Computing &
Applications, 2020.
Banerjee et al., "Thermal and optical fusion techniques for concealed weapon detection," SPIE Proceedings on
Imaging Techniques, 2019.
Jha et al., "Advancements in CNNs for real-time security monitoring," IEEE Transactions on Image Processing, 2021.
Kim et al., "Surveillance system improvements with deep feature extraction," IEEE Transactions on Neural Networks,
2022.
Das et al., "Real-time CNN-based detection of weapons in low-light conditions," Applied Intelligence, 2023.
Downloads
Published
License
Copyright (c) 2025 Agozie Eneh, Deborah Ebem, Richard Ochogwu (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
