Real-Time Object Detection Using Deep Learning

Abstract

Real-time object detection is a crucial task in computer vision, enabling intelligent systems to identify and classify multiple objects from visual data streams such as images and videos. Traditional detection methods relied heavily on manual feature extraction and suffered from limited scalability in dynamic environments. This paper presents an intelligent system for Real-Time Object Detection Using Deep Learning, utilizing the YOLOv8 (You Only Look Once) architecture integrated with a Flask-based web interface. The proposed system detects and labels multiple objects in live webcam feeds, video inputs, or static images with high accuracy and low latency. It leverages convolutional neural networks (CNNs) for feature extraction and performs training on a custom dataset enhanced through extensive data augmentation. This research demonstrates the potential of integrating deep learning with web-based technologies for real-world applications such as surveillance, industrial monitoring, and autonomous systems.