Missile Detection

This project presents an intelligent missile detection system leveraging cutting-edge deep learning models—YOLOv9, YOLOv10, and YOLOv11—for real-time object detection. The primary objective is to accurately identify and localize missiles within uploaded images using a robust and lightweight framework. The dataset for training and evaluation is sourced from Roboflow’s open-source Missile Detection dataset. The backend is implemented in Python, integrating pretrained and fine-tuned YOLO models for high-precision object recognition. A user-friendly frontend is developed using Streamlit, offering functionality such as secure user login, image upload, and visualized detection results. This solution is designed for defense surveillance, threat monitoring, and autonomous system integration. It ensures fast inference, high accuracy, and an intuitive interface for non-technical users. Future enhancements may include real-time video stream detection and model optimization for edge deployment on embedded devices.

Keywords:

Missile detection, YOLOv9, YOLOv10, YOLOv11, Streamlit, object detection, Roboflow dataset, Python, deep learning, image analysis, defense AI, computer vision, threat monitoring.