A Deep Learning-Based Efficient Firearms Monitoring Technique for Building Secure Smart Cities

Aim:

           The aim of this study is to detect weapon by employing YOLO v8, focusing on better accuracy.

 Abstract:

          This research introduces an advanced approach utilizing YOLO v8 for more accurate and efficient firearm and weapon detection in the context of developing secure smart cities. While the existing method, Faster RCNN, effectively detected human faces and guns, this study proposes an upgrade to YOLO v8 for detecting both knives and guns with higher accuracy scores. The proposed method aims to address the limitations of the current techniques to bolster security measures in urban areas.

Proposed Method:

        The proposed approach utilizes YOLO v8, a state-of-the-art object detection system known for its accuracy and speed. YOLO v8 is implemented to identify both knives and guns with higher precision than the existing Faster RCNN model.

Advantages:

• Enhanced Accuracy: YOLO v8 demonstrates improved accuracy in detecting both guns and knives.
• Increased Speed: YOLO v8 is known for its faster processing, enabling real-time detection in smart city environments.
• Expanded Weapon Detection: Unlike the previous model, YOLO v8 has the capability to detect multiple types of weapons, not just firearms.
• Potential for Real-Time Security Response: The quicker and more accurate identification of weapons can aid law enforcement and security measures promptly.