Loading...
Object Detection and Classification for Autonomous Vehicles Using Deep Learning Techniques
Neupane, Kiran
Neupane, Kiran
Citations
Altmetric:
Abstract
This study presents the development and evaluation of an object detection and classification system for autonomous vehicles using machine learning techniques. The primary objective is to enhance the ability of autonomous vehicles to accurately identify and classify surrounding objects, including vehicles, pedestrians, and traffic signs, under diverse real-world conditions. A Convolutional Neural Network (CNN) based on the ResNet-50 architecture was implemented using a transfer learning approach to improve classification performance.
The results demonstrate that the model achieves an accuracy of approximately 71.9% on training data and 71.8% on test data, indicating reliable predictive capability. However, lower precision and F1-score values highlight the need for further optimization. The study confirms the effectiveness of CNN-based approaches for object detection in autonomous vehicle applications and emphasizes the importance of data quality, model tuning, and computational resources. Future work will focus on improving model performance through advanced architectures, hyperparameter tuning, and enhanced datasets.
Description
Date
2024-05-10
Journal Title
Journal ISSN
Volume Title
Publisher
University of Wyoming Libraries
Files
Research Projects
Organizational Units
Journal Issue
Keywords
Object Detection,Autonomous Vehicles,Deep Learning,Convolutional Neural Networks,ResNet 50,Image Classification,Computer Vision,Traffic Object Recognition,Machine Learning,Intelligent Transportation Systems
Citation
License
Attribution 4.0 International