Paper Key : IRJ************188
Author: Vivek Vijay Karnakar
Date Published: 06 Nov 2023
Abstract
In the rapidly evolving landscape of autonomous vehicles, accurate object detection stands as a cornerstone for ensuring safe and reliable navigation. This research paper delves into the realm of object detection in autonomous vehicles, focusing on the implementation of the You Only Look Once version 5 (YOLOv5) model. The study investigates the effectiveness of YOLOv5 by subjecting it to rigorous testing using a meticulously curated dataset, aiming to assess its performance, accuracy, and real-time processing capabilities.The core objective of this research was to evaluate YOLOv5's ability to accurately detect and classify diverse objects crucial for autonomous driving, including pedestrians, vehicles, cyclists, and road signs. To accomplish this, a comprehensive dataset encompassing a wide array of driving scenarios, lighting conditions, and environmental challenges was used.Furthermore, the results of the research paper illustrate YOLOv5's superiority in terms of both accuracy and speed, reaffirming its potential as a leading choice for object detection in autonomous vehicles. These findings have significant implications for the development and deployment of autonomous vehicles, as accurate object detection is fundamental to ensuring the safety of passengers and pedestrians alike.In conclusion, this research paper validates the effectiveness of YOLOv5 in object detection for autonomous vehicles. The robustness, accuracy, and real-time processing capabilities exhibited by YOLOv5 underscore its pivotal role in shaping the future of autonomous transportation. As the demand for safer and more efficient autonomous vehicles continues to rise, the findings presented in this paper provide a strong foundation for further research and development in the pursuit of fully autonomous and secure transportation systems.
DOI LINK : 10.56726/IRJMETS45668 https://www.doi.org/10.56726/IRJMETS45668