Sistem Deteksi Senjata Otomatis Menggunakan Deep Learning Berbasis CCTV Cerdas
Nowadays, security and safety are big concerns in this modern and cyberwar era. Many countries invest some safety infrastructure to ensure their inhabitants for keeping their lives safely. Indonesia is the country with many problems because of urbanization and other challenges. This problem should be solved with smart city solution and it must be able to face the challenge of ensuring the safety and improving the quality of life regarding network centric warfare era. This problem also should be tackled with CCTV analytics with the ability to implement an automatic weapon detection system. It also can provide the early detection of potentially violent situations that is of paramount importance for citizens security. This paper is using deep Learning techniques based on Convolutional Neural Networks (CNN) can be trained to detect this type of object with YOLOv4 model and it proposes to implement CCTV analytics as a platform to process real-time data for monitoring weapon detection into knowledge displayed in a dashboard with accuracy 0.89, precision 0.82, recall 0.96 dan F1 Score 0.90 result on weapon detection with a real time speed of processing with NVIDIA 2080 Ti around of 35 FPS. It will send an early warning notification if the system detects the weapon detection such as a knife, gun etc.
R. Indonesia, “UU Nomor 3 Tahun 2003,” no. September, pp. 1–2, 2009, [Online]. Available: http://www2.pom.go.id/public/hukum_perundangan/pdf/.
I. A. Dahlan, F. Hamami, S. H. Supangkat, and F. Hidayat, “Big Data Implementation of Smart Rapid Transit using CCTV Surveillance,” Proceeding - 2019 Int. Conf. ICT Smart Soc. Innov. Transform. Towar. Smart Reg. ICISS 2019, pp. 1–5, 2019, doi: 10.1109/ICISS48059.2019.8969830.
B. D. Riyanto, “Cloud Service Design for Computer Vision , Image / Video Processing & Analytics,” no. June, 2021.
J. Redmon and A. Farhadi, “YOLO v.3,” Tech Rep., pp. 1–6, 2018, [Online]. Available: https://pjreddie.com/media/files/papers/YOLOv3.pdf.
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “Scaled-YOLOv4: Scaling Cross Stage Partial Network,” 2020, [Online]. Available: http://arxiv.org/abs/2011.08036.
A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv, 2020.
P. Mehta, A. Kumar, and S. Bhattacharjee, “Fire and Gun Violence based Anomaly Detection System Using Deep Neural Networks,” Proc. Int. Conf. Electron. Sustain. Commun. Syst. ICESC 2020, no. Icesc, pp. 199–204, 2020, doi: 10.1109/ICESC48915.2020.9155625.
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.
F. Hidayat, F. Hamami, I. A. Dahlan, S. H. Supangkat, A. Fadillah, and A. Hidayatuloh, “Real Time Video Analytics Based on Deep Learning and Big Data for Smart Station,” J. Phys. Conf. Ser., vol. 1577, no. 1, 2020, doi: 10.1088/1742-6596/1577/1/012019.