Object detection in inland vessels using combined trained and pretrained models of YOLO8

Abstract

Abstract—One of the main challenges in computer vision isobject detection, which entails both locating and identifyingspecific items on an image. With a fresh perspective, the YOLO(You Only Look Once) algorithm was developed in 2015 andperforms object detection in a single neural network. That causedthe field of object detection to explode and produce considerablymore amazing achievements than it had a decade before. So far,YOLO has been improved to eight versions and rated as oneof the top object identification algorithms. This is thanks to itscombination with many of the most cutting-edge concepts beingexplored in the computer vision research field. The most recentversion of YOLO, known as YOLOv8, performs better than theYOLOv7 and YOLO5 in terms of accuracy and speed, though.This paper examines the most recent developments in computervision that were incorporated into YOLOv5,YOLO7 and YOLO8and its predecessors.Index Terms—Object Detection, YOLO, Autonomous Vehicles,Inland Waterway Vessels, Bounded Boxes, Neural Network, CNN.Received: 14 June 2023 Accepted: 11 September 2023Published: 20 November 2023