Object Detection

Abstract

Object detection is a foundational task in the field of computer vision that focuses on identifying and localizing objects within digital images or videos. This mini project presents a real-time object detection system built using YOLOv4 (You Only Look Once Version 4), a state-of-the-art deep learning model known for its high detection accuracy and fast processing speed. The main objective of this project is to develop a lightweight, efficient, and adaptable object detection model suitable for real-time applications across diverse domains. The system has been implemented using Python and deep learning libraries such as TensorFlow and OpenCV, with Streamlit providing a user-friendly web interface. The model is trained on custom datasets to detect specific object classes, and it supports both image and video input. Through the interface, users can upload media or use a webcam to perform object detection and view results instantly with bounding boxes and labels drawn around identified objects.