Paper Title
Object Detection and Tracking Using YOLOv8

Abstract
Object Detection and Tracking is a important capability of computer system in vision sector. In the research paper, it suggests a technique for object detection and tracking in real time, by utilizing cutting-edge computer vision algorithms. The main goal of object detection and tracking is to detect all objects from given scene and maintain the identity information of each target. Many tracking-by-detection algorithms use two deep neural networks for object tracking and information extraction separately. YOLO (You Only Look Once), is a technique with high performance CNN (Convolutional Neural Network) for object detection and tracking, and Deep Sort, is algorithm for splitting up objects and its matching objects detected across multiple frames which are on basis of motion and, these are assembled for creation of object detection and tracking pipeline. Using this approach one can achieve better tracking results. Deep learning has revolutionized object detection, with YOLO leading in real-time accuracy. This study’s findings show that how well YOLOv8’s quick object recognition and Deep SORT algorithm’s dependable object tracking, they work together to give precise and immediate object detection. This model of the YOLOv8 object detection method, it has a large amount of use cases in the areas like traffic control, video surveillance, and object detection, which can also improve conditional awareness and automation. However, detecting moving objects in visual streams will present some challenges. In this research paper it proposes a refined YOLOv8 object detection and tracking model, which emphasizes motion-specific detections in varied visual contexts. Keywords - Object Detection, YOLO, Deep SORT, YOLOv8, Tracking.