Deep neural networks (DNNs) have emerged as a powerful tool for object detection tasks in computer vision. Object detection focuses on locating the presence of objects with a bounding box and detecting the class of located objects in these boxes. This project explores the application of deep learning techniques particularly convolution neural networks (CNNs), for the task of object detection. By using state-of-the-art architecture such as YOLO (You Only Look Once), we focus on implementing YOLO model for object detection tasks. Our project evaluates its effectiveness and accuracy in identifying and localizing objects in real-time scenarios. We explore techniques for model optimization and deployment. Additionally, we extend on seamless integration of YOLO model with webcam for live video streaming, providing a straightforward solution for real-time object detection directly from live video feeds. Our project aims to provide a practical framework for deploying object detection models in real-world applications.