Klasifikasi Tingkat Ancaman Kriminalitas Bersenjata Menggunakan Metode You Only Look Once (YOLO)

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.

Keywords

• YOLO object detection
• threat level classification
• monitoring