Real‐time object detection for unmanned vehicles in Bangladesh: Dataset, implementation and evaluation

Abstract Automated vehicle detection within the advanced application framework of autonomous vehicles significantly enhances road safety compared to human drivers on roads and highways. However, the intelligent identification of road vehicles in a densely populated country like Bangladesh is challen...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Liakat Ali, Topu Biswas, Shahin Akter, Mohammed Farhan Jawad, Hadaate Ullah
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:The Journal of Engineering
Subjects:
Online Access:https://doi.org/10.1049/tje2.70033
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846107153220239360
author Muhammad Liakat Ali
Topu Biswas
Shahin Akter
Mohammed Farhan Jawad
Hadaate Ullah
author_facet Muhammad Liakat Ali
Topu Biswas
Shahin Akter
Mohammed Farhan Jawad
Hadaate Ullah
author_sort Muhammad Liakat Ali
collection DOAJ
description Abstract Automated vehicle detection within the advanced application framework of autonomous vehicles significantly enhances road safety compared to human drivers on roads and highways. However, the intelligent identification of road vehicles in a densely populated country like Bangladesh is challenging due to irregular traffic patterns, highly diverse vehicle types, a cluttered environment, and a lack of high‐quality datasets. This study proposes a system that utilizes computer vision technology to identify road vehicles with greater speed and accuracy. First, the dataset was collected and organized in Roboflow to identify the 21 classes of Bangladeshi native vehicle images, along with two additional classes for people and animals. Subsequently, the You Only Look Once v5 (YOLOv5) model underwent training on the dataset. This process produced bounding boxes, which were then refined using the non‐maximum suppression technique. The loss function complete intersection over union is employed to obtain the accurate regression bounding box of the vehicles. The MS COCO (Microsoft Common Objects in Context) dataset weights are included in the YOLOv5 deep learning network for transfer learning. Finally, Python TensorBoard was used to evaluate and visualize the model's performance. The model was developed and validated on the Google Colab platform. A set of experimental evaluations demonstrate that the proposed method is effective and efficient in recognizing Bangladeshi vehicles. In all test road scenarios, the proposed computer vision system for road vehicle identification achieved 95.8% accuracy and 0.3 ms processing time for 200 epochs. This research could lead to intelligent transportation systems and driverless vehicles in Bangladesh.
format Article
id doaj-art-a75c1324c7a1485f91a4519688ce883a
institution Kabale University
issn 2051-3305
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series The Journal of Engineering
spelling doaj-art-a75c1324c7a1485f91a4519688ce883a2024-12-26T18:34:28ZengWileyThe Journal of Engineering2051-33052024-12-01202412n/an/a10.1049/tje2.70033Real‐time object detection for unmanned vehicles in Bangladesh: Dataset, implementation and evaluationMuhammad Liakat Ali0Topu Biswas1Shahin Akter2Mohammed Farhan Jawad3Hadaate Ullah4Department of Electrical and Electronic Engineering Southern University Bangladesh Chattogram BangladeshDepartment of Computer Science and Engineering University of Science and Technology Chittagong Chattogram BangladeshDepartment of Electrical and Electronic Engineering Chittagong University of Engineering and Technology Chattogram BangladeshDepartment of Electrical and Computer Engineering University of Delaware Newark Delaware USADepartment of Electrical and Electronic Engineering University of Science and Technology Chittagong Chattogram BangladeshAbstract Automated vehicle detection within the advanced application framework of autonomous vehicles significantly enhances road safety compared to human drivers on roads and highways. However, the intelligent identification of road vehicles in a densely populated country like Bangladesh is challenging due to irregular traffic patterns, highly diverse vehicle types, a cluttered environment, and a lack of high‐quality datasets. This study proposes a system that utilizes computer vision technology to identify road vehicles with greater speed and accuracy. First, the dataset was collected and organized in Roboflow to identify the 21 classes of Bangladeshi native vehicle images, along with two additional classes for people and animals. Subsequently, the You Only Look Once v5 (YOLOv5) model underwent training on the dataset. This process produced bounding boxes, which were then refined using the non‐maximum suppression technique. The loss function complete intersection over union is employed to obtain the accurate regression bounding box of the vehicles. The MS COCO (Microsoft Common Objects in Context) dataset weights are included in the YOLOv5 deep learning network for transfer learning. Finally, Python TensorBoard was used to evaluate and visualize the model's performance. The model was developed and validated on the Google Colab platform. A set of experimental evaluations demonstrate that the proposed method is effective and efficient in recognizing Bangladeshi vehicles. In all test road scenarios, the proposed computer vision system for road vehicle identification achieved 95.8% accuracy and 0.3 ms processing time for 200 epochs. This research could lead to intelligent transportation systems and driverless vehicles in Bangladesh.https://doi.org/10.1049/tje2.70033image processingimage processing and machine visionimage recognitionimage segmentationmachine learning
spellingShingle Muhammad Liakat Ali
Topu Biswas
Shahin Akter
Mohammed Farhan Jawad
Hadaate Ullah
Real‐time object detection for unmanned vehicles in Bangladesh: Dataset, implementation and evaluation
The Journal of Engineering
image processing
image processing and machine vision
image recognition
image segmentation
machine learning
title Real‐time object detection for unmanned vehicles in Bangladesh: Dataset, implementation and evaluation
title_full Real‐time object detection for unmanned vehicles in Bangladesh: Dataset, implementation and evaluation
title_fullStr Real‐time object detection for unmanned vehicles in Bangladesh: Dataset, implementation and evaluation
title_full_unstemmed Real‐time object detection for unmanned vehicles in Bangladesh: Dataset, implementation and evaluation
title_short Real‐time object detection for unmanned vehicles in Bangladesh: Dataset, implementation and evaluation
title_sort real time object detection for unmanned vehicles in bangladesh dataset implementation and evaluation
topic image processing
image processing and machine vision
image recognition
image segmentation
machine learning
url https://doi.org/10.1049/tje2.70033
work_keys_str_mv AT muhammadliakatali realtimeobjectdetectionforunmannedvehiclesinbangladeshdatasetimplementationandevaluation
AT topubiswas realtimeobjectdetectionforunmannedvehiclesinbangladeshdatasetimplementationandevaluation
AT shahinakter realtimeobjectdetectionforunmannedvehiclesinbangladeshdatasetimplementationandevaluation
AT mohammedfarhanjawad realtimeobjectdetectionforunmannedvehiclesinbangladeshdatasetimplementationandevaluation
AT hadaateullah realtimeobjectdetectionforunmannedvehiclesinbangladeshdatasetimplementationandevaluation