Implementasi Sistem Identifikasi Senjata Real Time Menggunakan YOLOv7 dan Notifikasi Chat Telegram

This research produces an application that can send automatic notifications in the form of a chat on the Telegram platform when a weapon object is detected on CCTV. This application was created utilizing computer vision technology and artificial intelligence, in particular YOLOv7. As demonstrated by the mAP@0.5 value of 0.837 after 50 epochs of training, this application can detect weapon objects such as people, pistols, and knives with a reasonable degree of accuracy. This application is also linked to the telepot library, which enables it to send chats on the Telegram platform. These applications can aid in enhancing security and safety in a variety of environments and have numerous practical applications in fields such as public safety, law enforcement, and others. However, there are still deficiencies in this study that can be addressed in future research, such as the small number of training epochs and the size of the dataset.