Project

Overview

I designed and implemented a web-based platform leveraging the YOLOv5 deep learning model for real-time object detection on video streams. By integrating the PyTorch framework, the system enables users to upload video content and receive instantaneous, frame-by-frame annotations highlighting recognized objects. Built on Flask's lightweight backend, the platform efficiently manages user requests and seamlessly streams processed videos. Paired with OpenCV, it ensures precise video frame extraction and dynamic content rendering. The responsive front-end interface ensures optimal user experience across various devices, making it a perfect amalgamation of modern web development with cutting-edge artificial intelligence capabilities.