Open Access Open Access  Restricted Access Subscription Access

A Survey on Enhanced Weapon Detection System using Deep Learning

Neethu George, Shakeeb Rahman, Mohammed Haiz, Rahuldev T S, Serin Simon

Abstract


Considering the increasing prevalence of criminal activities, this study introduces a novel deep learning model designed for accurate weapon detection. The model, based on the VGGNet architecture and implemented on TensorFlow, classifies seven weapon types: assault rifles, bazookas, grenades, hunting rifles, knives, pistols, and revolvers. Trained on a custom dataset, the model achieves an impressive 98.40% accuracy, surpassing VGG-16, ResNet-50, and ResNet-101. The proposed system addresses challenges like self-occlusion and complex backgrounds, offering practical applications for enhancing security.


Full Text:

PDF

References


Raturi, G., Rani, P., Madan, S., & Dosanjh, S. (2019, November). ADoCW: An automated technique for identifying hidden weapons. In 2019 Fifth International Conference on Image Information Processing (ICIIP) (pp. 181-186). IEEE.

Bhagyalakshmi, P., Indhumathi, P., &Bhavadharini, L. R. (2019). Live video monitoring for automated identification of fire arms. International Journal of Trend in Scientific Research and Development (IJTSRD).

Lim, J., Al Jobayer, M. I., Baskaran, V. M., Lim, J. M., Wong, K., & See, J. (2019, November). Utilizing deep neural networks to detect firearms in surveillance videos. In 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (pp. 1998-2002). IEEE.

Yuan, J., & Guo, C. (2018, June). An advanced neural network approach for identifying hazardous machinery. In 2018 Eighth International Conference on Information Science and Technology (ICIST) (pp. 159-164). IEEE.

Ilgin, F. Y. (2020). Utilizing copulas for cognitive radios, we implement energy-based spectrum sensing. Bulletin of the Polish Academy of Sciences. Technical Sciences, 68(4), 829-834.

Navalgund, U. V., & Priyadharshini, K. (2018, December). Deep learning-based approach for detecting criminal intentions. In 2018 International Conference on Circuits and Systems in Digital Enterprise Technology (ICCSDET) (pp. 1-6). IEEE.

Chandan, G., Jain, A., & Jain, H. (2018, July). Utilizing Deep Learning and OpenCV, this system enables real-time detection and tracking of objects. In 2018 International Conference on inventive research in computing applications (ICIRCA) (pp. 1305-1308). IEEE.

Deng, L., & Yu, D. (2014). Exploration of deep learning techniques and their practical uses. Foundations and trends® in signal processing, 7(3–4), 197-387.

Bengio, Y. (2009). Studying complex structures for artificial intelligence. Foundations and trends® in Machine Learning, 2(1), 1-127.

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444.


Refbacks

  • There are currently no refbacks.