An Enhanced Weapon Detection System using D...

An Enhanced Weapon Detection System using Deep Learning

Author Name : Gaurav Mahavir Phade, Dr. Dinesh Bhagwan Hanchate, Dr. Sachin Sukhadeo Bere

ABSTRACT In an era marked by increasing security concerns, the rapid and accurate detection of weapons in public and restricted areas has become a critical priority. This project presents an enhanced weapon detection system utilizing deep learning techniques to identify and localize various types of weapons in real-time video feeds and images. Leveraging the power of convolutional neural networks (CNNs) and advanced object detection architectures such as YOLOv5 and Faster R-CNN, the system is trained on a diverse dataset comprising both real and synthetic images of firearms, knives, and other potential threats. The model achieves high accuracy while maintaining low inference time, making it suitable for deployment in surveillance systems, transportation hubs, and public venues. Additionally, the system incorporates post-processing techniques to minimize false positives and enhance detection confidence. This project demonstrates the potential of deep learning-based approaches in augmenting traditional surveillance systems, thereby contributing to improved public safety and proactive threat mitigation.