OBJECT DETECTION USING YOLOv4

ABSTRACT

This project is an attempt at developing an object detection system using Artificial Intelligence, with the YOLO framework- a deep learning algorithm for real-time object tracking and detecting, and delivers on exactly that. Object detection is a Computer Vision technique that involves the detection and tracking of various objects in digital images or videos. These objects include real-world object instances such as car, bike, TV, humans and so on. The technology behind this deep learning algorithm and the results of this project are expressed in this report, and includes the various applications of computer vision techniques in tracking objects in a 2-dimensional scene. This report is designed in two parts - the theoretical and practical part. In the theoretical part, we review the relevant literature and study how Convolutional object detection methods have improved in the past few years. And in the practical part, we study how easily a Convolutional object detection system can be implemented in practice, and test how well it generalizes (this project uses a small training data size).