Performance Analysis on Enhancing Security Through Object Detection using YOLO G

Traditional security measures often struggle with the timely detection of weapons, making integrating technologies like YOLOv5 (You Only Look Once version 5) vital. This model processes video feeds quickly, allowing security personnel to react promptly to potential threats, thereby potentially saving lives. The focus on integrating such advanced algorithms into surveillance systems can lead to more effective monitoring of public spaces, addressing the rising concerns regarding gun violence and security threats. The application of YOLOv5 in weapon detection significantly enhances public safety by utilizing its advanced deep-learning capabilities for real-time surveillance. YOLOv5 is highly regarded for its ability to balance speed and accuracy, critical for immediate threat identification in security scenarios. This research work explores an innovative method for weapon detection utilizing the YOLO framework, significantly enhancing security in public spaces. As concerns over gun violence grow, the ability to rapidly and accurately identify weapons in real time becomes essential for prevention. The YOLOv5 framework, recognized for its efficiency in object detection, was trained on a custom dataset that included various types of weapons, such as firearms and knives, in diverse settings. Data augmentation techniques were employed to improve the model’s robustness.