Advanced Self-Driving Vehicle Model for Complex Road Navigation Using Integrated Image Processing and Sensor Fusion

This paper presents a sophisticated self-driving vehicle (SDV) model that addresses the challenges of navigating complex road networks characterized by high traffic and unpredictable environments. The model integrates state-of-the-art image processing techniques with advanced sensor fusion, utilizin...

Full description

Saved in:
Bibliographic Details
Main Authors: Kalapraveen Bagadi, Naveen Kumar Vaegae, Visalakshi Annepu, Khaled Rabie, Shafiq Ahmad, Thokozani Shongwe
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10737305/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311803370110976
author Kalapraveen Bagadi
Naveen Kumar Vaegae
Visalakshi Annepu
Khaled Rabie
Shafiq Ahmad
Thokozani Shongwe
author_facet Kalapraveen Bagadi
Naveen Kumar Vaegae
Visalakshi Annepu
Khaled Rabie
Shafiq Ahmad
Thokozani Shongwe
author_sort Kalapraveen Bagadi
collection DOAJ
description This paper presents a sophisticated self-driving vehicle (SDV) model that addresses the challenges of navigating complex road networks characterized by high traffic and unpredictable environments. The model integrates state-of-the-art image processing techniques with advanced sensor fusion, utilizing EfficientDet D0 and Haar Cascade object detection models to identify obstacles, road signs, and traffic signals accurately. The integration of data from cameras and ultrasonic sensors enables the creation of a precise 2D map of the vehicle’s surroundings, which, combined with a robust decision-making algorithm, allows for optimal performance in challenging traffic scenarios. The SDV prototype was tested extensively in a custom-built artificial environment, where it demonstrated its ability to handle various real-world scenarios, including lane detection, obstacle avoidance, and decision-making in the presence of stationary obstacles and heavy traffic. The experimental results confirm the model’s effectiveness in enhancing SDV capabilities, paving the way for safer and more efficient autonomous transportation systems. It is found from our experiments that the average precision for obstacle detection models is 0.729, the average recall is 0.758, and the prototype’s ability to process at 24 frames per second highlights the efficiency and accuracy of our proposed model.
format Article
id doaj-art-c3f53302eb5a4beb98bc52bc6899262c
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c3f53302eb5a4beb98bc52bc6899262c2025-08-20T03:53:17ZengIEEEIEEE Access2169-35362024-01-011218714118715910.1109/ACCESS.2024.348786810737305Advanced Self-Driving Vehicle Model for Complex Road Navigation Using Integrated Image Processing and Sensor FusionKalapraveen Bagadi0https://orcid.org/0000-0003-1082-1972Naveen Kumar Vaegae1https://orcid.org/0000-0002-0292-697XVisalakshi Annepu2https://orcid.org/0000-0002-7199-1898Khaled Rabie3https://orcid.org/0000-0003-0043-2025Shafiq Ahmad4https://orcid.org/0000-0003-0712-9133Thokozani Shongwe5https://orcid.org/0000-0002-3011-7600School of Electronics Engineering, VIT-AP University, Amaravati, IndiaSchool of Electronics Engineering, Vellore Institute of Technology, Vellore, IndiaSchool of Computer Science and Engineering, VIT-AP University, Amaravati, IndiaDepartment of Computer Engineering and Center for Communication Systems and Sensing, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaIndustrial Engineering Department, College of Engineering, King Saud University, Riyadh, Saudi ArabiaElectrical and Electronic Engineering Technology, University of Johannesburg, Johannesburg, South AfricaThis paper presents a sophisticated self-driving vehicle (SDV) model that addresses the challenges of navigating complex road networks characterized by high traffic and unpredictable environments. The model integrates state-of-the-art image processing techniques with advanced sensor fusion, utilizing EfficientDet D0 and Haar Cascade object detection models to identify obstacles, road signs, and traffic signals accurately. The integration of data from cameras and ultrasonic sensors enables the creation of a precise 2D map of the vehicle’s surroundings, which, combined with a robust decision-making algorithm, allows for optimal performance in challenging traffic scenarios. The SDV prototype was tested extensively in a custom-built artificial environment, where it demonstrated its ability to handle various real-world scenarios, including lane detection, obstacle avoidance, and decision-making in the presence of stationary obstacles and heavy traffic. The experimental results confirm the model’s effectiveness in enhancing SDV capabilities, paving the way for safer and more efficient autonomous transportation systems. It is found from our experiments that the average precision for obstacle detection models is 0.729, the average recall is 0.758, and the prototype’s ability to process at 24 frames per second highlights the efficiency and accuracy of our proposed model.https://ieeexplore.ieee.org/document/10737305/ArduinoEfficientDetimage processingobject detectionraspberry Piself-driving vehicles
spellingShingle Kalapraveen Bagadi
Naveen Kumar Vaegae
Visalakshi Annepu
Khaled Rabie
Shafiq Ahmad
Thokozani Shongwe
Advanced Self-Driving Vehicle Model for Complex Road Navigation Using Integrated Image Processing and Sensor Fusion
IEEE Access
Arduino
EfficientDet
image processing
object detection
raspberry Pi
self-driving vehicles
title Advanced Self-Driving Vehicle Model for Complex Road Navigation Using Integrated Image Processing and Sensor Fusion
title_full Advanced Self-Driving Vehicle Model for Complex Road Navigation Using Integrated Image Processing and Sensor Fusion
title_fullStr Advanced Self-Driving Vehicle Model for Complex Road Navigation Using Integrated Image Processing and Sensor Fusion
title_full_unstemmed Advanced Self-Driving Vehicle Model for Complex Road Navigation Using Integrated Image Processing and Sensor Fusion
title_short Advanced Self-Driving Vehicle Model for Complex Road Navigation Using Integrated Image Processing and Sensor Fusion
title_sort advanced self driving vehicle model for complex road navigation using integrated image processing and sensor fusion
topic Arduino
EfficientDet
image processing
object detection
raspberry Pi
self-driving vehicles
url https://ieeexplore.ieee.org/document/10737305/
work_keys_str_mv AT kalapraveenbagadi advancedselfdrivingvehiclemodelforcomplexroadnavigationusingintegratedimageprocessingandsensorfusion
AT naveenkumarvaegae advancedselfdrivingvehiclemodelforcomplexroadnavigationusingintegratedimageprocessingandsensorfusion
AT visalakshiannepu advancedselfdrivingvehiclemodelforcomplexroadnavigationusingintegratedimageprocessingandsensorfusion
AT khaledrabie advancedselfdrivingvehiclemodelforcomplexroadnavigationusingintegratedimageprocessingandsensorfusion
AT shafiqahmad advancedselfdrivingvehiclemodelforcomplexroadnavigationusingintegratedimageprocessingandsensorfusion
AT thokozanishongwe advancedselfdrivingvehiclemodelforcomplexroadnavigationusingintegratedimageprocessingandsensorfusion