Klasifikasi Tingkat Ancaman Kriminalitas Bersenjata Menggunakan Metode You Only Look Once (YOLO)
Article Sidebar
Main Article Content
Abstract
The research aim to recognize potential weapon threats through object detection on camera. This research utilize YOLO (You Only Look Once) method in object detection which implemented on Raspberry Pi 4. The process was by detecting object from the camera and classify the object class in 2 available classes : Gun and Knife. Meanwhile, in the classifying process, it also count the object in every classes. When the system detect object in the process, it will send notification in terms of threat level through android application so that the user or operator can mitigate the threat immediately. From the research, we achieve the mAP of 85.12% in which YOLOv4 tiny is used and the testing is done inside a room environment. In its application in detecting weapon in Raspberry Pi 4, the result is around 1.53 fps (frame per second), in which is accommodate to be implemented on, but with a very limited fps.
Article Details
References
[2] Jung, Yeondae, Andrew P. Wheeler. 2019. The effect of public surveillance cameras on crime clearance rates. University of Texas, Dallas. DOI: 10.31219/osf.io/eh5bg.
[3] Cohen, N., Gattuso, J., MacLennan-Brown, K., Branch, G.B.H.O.S.D. 2009. CCTV Operational Requirements Manual. Criminal Justice System Race Unit. The Home Office: London.UK.
[4] Oyedeji, A.. Salami, A., Folorunsho, O., & Abolade, O. 2020. March 30. Analysis and Prediction of Student Academic Performance Using Machine Learning. JITCE (Journal of Information Technology and Computer Engineering).4(01),10-15.https://doi.org/https://doi.org/10.25077/jitce.4.01 .10-15.2020.
[5] Grega, M., & Andrzej Metiolanski, P. G. 2016. Automated Detection of Firearms and Knives in a CCTV Image. Sensors (Basel). 2016 Jan 1;16(1):47. DOI: 10.3390/s16010047.
[6] S. S. Kunapuli, P. C. B.H. and U. Singh, "Designing and Implementing a Real Time Weapons Detection System on ODROID-XU4," 2018 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE), Chonburi, Thailand, 2018, pp. 137-140, DOI: 10.1109/WIECON-ECE.2018.8783187.
[7] Olmos, Roberto, Siham Tabik, Francisco Herrera. 2017. Automatic Handgun Detection Alarm in VideosUsing Deep Learning. NEUCOM (NeuroComputing) 18416, Vol 275, 66-72. DOI : https://arxiv.org/abs /1702.05147.
[8] Nofriani, N. (2020, September 30). Machine Learning Application for Classification Prediction of Household’s Welfare Status. JITCE (Journal of Information Technology and Computer Engineering), 4(02), 72-82. https://doi.org/https://doi.org/10.25077/jitce.4.02.72-82.202.
[9] Redmon, Joseph. Divvala Santosh, Ross Girshick, Ali Farhadi. 2016. You Only Look Once : Unified Real-Time Object Detection. arXiv. DOI : arXiv:1506.02640.
[10] Shung, Koo Ping. 2018. Accuracy, Precision, Recall or F1 ? . Diakses pada tanggal 18 Desember 2020 : https://towardsdatascience.com/accuracy-precision-recall-or-f1-331fb37c5cb9.
[11] Solawetz, Jacob. 2020. What is Mean Average Precision (mAP) in Object Detection. Roboflow. Diakses pada tanggal 18 Desember 2020 : https://blog.roboflow.com/mean-average-precision/.
[12] Yohanandan, Shivy. 2020. mAP (mean Average Precision) might confuse you! . Toward Data Science. Diakses pada tanggal 18 Desember 2020 : https://towardsdatascience.com/map-mean-average-precision-might-confuse-you-5956f1bfa9e2.
[13] Raspberry Pi Foundation. n.d. Raspberry Pi 4 Tech Specs. Diakses pada tanggal 6 September 2020 : https://www.raspberrypi. org/products/raspberry-pi-4-modelb/specificati ons/?resellerType =home.