Use of Deep Learning for Firearms Detection in Images

• Guilherme Vinicius Simões Cardoso Universidade Federal do Espírito Santo
• Patrick Marques Ciarelli Universidade Federal do Espírito Santo
• Raquel Frizera Vassallo Universidade Federal do Espírito Santo

DOI: https://doi.org/10.5753/wvc.2019.7637

Resumo

Demand for weapons has grown along with crime rates, a contemporary problem haunting countries. This has motivated scientists to devise solutions that can aid in public safety in general. This paper proposes the detection of firearms in images through convolutional neural networks, using the YOLO (You Only Look Once) object detector. To improve learning, YOLO was used to generate annotations in an unmarked database, integrating a new database. This proposal was evaluated in a database containing 608 images, in which 304 images had weapons. Experiments carried out indicated an accuracy of 89.15% and a sensitivity of 100.00%, surpassing results presented in the current literature. These results show that the proposed methodology can be applied for the detection of firearms in images.

Palavras-chave: YOLO, CNN, Images, Firearms

Referências

D. R. d. C. Cerqueira, Causas e consequencias do crime no Brasil. Banco Nacional de Desenvolvimento Econômico e Social, 2014.

-- Lei n° 826, de 22 de dezembro de 2003, Dispõe sobre registro, posse e comercialização de armas de fogo e munição, sobre o sistema nacional de armas - sinarm, define crimes e dá outras providencias. ed., Brasil. Presidência da República. Casa Civil, Brasília, 2003.

D. R. d. C. Cerqueira and J. M. P. d. Mello, Menos armas, menos crimes, 2012.

-- Atlas da violência: Taxa de homicídios, http://www.ipea.gov.br/atlasviolência/dados-series/20, Brasil. Instituto de Pesquisa Economica Aplicada - IPEA, 2019, acesso: 22 - 01 - 2019.

-- Atlas da violência: Taxa de homicídios por armas de fogo, http://www.ipea.gov.br/atlasviolência/dados-series/35, Brasil. Instituto de Pesquisa Economica Aplicada - IPEA, 2019, acesso: 22 - 01 - 2019.

-- A. da violência, Ipea e fbsp, Rio de Janeiro.

-- Decreto nº847, de 25 de junho de 2019, Regulamenta a lei nº 10.826, de 22 de dezembro de 2003, para dispor sobre a aquisição, o cadastro, o registro, a posse, o porte e a comercialização de armas de fogo e de munição e sobre o sistema nacional de armas e o sistema de gerenciamento militar de armas. ed., http://www.planalto.gov.br/ccivil 03/ ato2019- 2022/2019/decreto/D9785.htm, Brasil. Presidencia da República. Casa Civil, Brasília, 2019.

K. He, G. Gkioxari, P. Dollár, and R. Girshick, Mask r-cnn, in Computer Vision (ICCV), 2017 IEEE International Conference on. IEEE, 2017, pp. 2980 - DOI: 10.1109/iccv.2017.322

J. Redmon and A. Farhadi, Yolo9000: better, faster, stronger, pp. 7263 - 7271, DOI: 10.1109/cvpr.2017.690

R. Olmos, S. Tabik, and F. Herrera, Automatic handgun detection alarm in videos using deep learning, Neurocomputing, vol. 275, pp. 66 - 72, DOI: 10.1016/j.neucom.2017.05.012

R. Gesick, C. Saritac, and C.-C. Hung, Automatic image analysis process for the detection of concealed weapons, in Proceedings of the 5th Annual Workshop on Cyber Security and Information Intelligence Research: Cyber Security and Information Intelligence Challenges and Strategies. ACM, 2009, p.

I. Daubechies, Ten lectures on wavelets. Siam, 1992, vol. DOI: 10.1137/1.9781611970104

D. G. Lowe, Distinctive image features from scale-invariant keypoints, International journal of computer vision, vol. 60, no. 2, pp. 91 - 110, DOI: 10.1023/b:visi.0000029664.99615.94

Z. Xiao, X. Lu, J. Yan, L. Wu, and L. Ren, Automatic detection of concealed pistols using passive millimeter wave imaging, in 2015 IEEE International Conference on Imaging Systems and Techniques (IST). IEEE, 2015, pp. 1 -

R. K. Tiwari and G. K. Verma, A computer vision based framework for visual gun detection using harris interest point detector, Procedia Computer Science, vol. 54, pp. 703 - 712, DOI: 10.1016/j.procs.2015.06.083

--, A computer vision based framework for visual gun detection using surf, in 2015 International Conference on Electrical, Electronics, Signals, Communication and Optimization (EESCO), 2015, pp. 1 -

N. B. Halima and O. Hosam, Bag of words based surveillance system using support vector machines, International Journal of Security and Its Applications, vol. 10, no. 4, pp. 331 - 346, DOI: 10.14257/ijsia.2016.10.4.30

Y. Elmir, S. A. Laouar, and L. Hamdaoui, Deep learning for automatic detection of handguns in video sequences, in 3rd edition of the National Study Day on Research on Computer Sciences (JERI 2019), Saida, Algeria, April 27, , ser. CEUR Workshop Proceedings, A. Amine, R. M. Hamou, M. Yahlali, and M. A. Boudia, Eds., vol. 2351. CEUR-WS.org, 2019. [Online]. Available: http://ceur-ws. org/ Vol- 2351 /paper 69.pdf

J. Redmon, Darknet: Open source neural networks in c, http://pjreddie.com/darknet/, 2013-2016.

T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, Microsoft coco: Common objects in context, in European conference on computer vision. Springer, 2014, pp. 740 - 755. DOI: 10.1007/978-3-319-10602-1_48

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, You only look once: Unified, real-time object detection, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779 - 788. DOI: 10.1109/cvpr.2016.91

R. Prati, G. Batista, and M. Monard, Curvas roc para avaliação de classificadores, Revista IEEE América Latina, vol. 6, no. 2, pp. 215 - 222, 2008.