Fractional B-Spline Wavelets and U-Net Architecture for Robust and Reliable Vehicle Detection in Snowy Conditions
This paper addresses the critical need for advanced real-time vehicle detection methodologies in Vehicle Intelligence Systems (VIS), especially in the context of using Unmanned Aerial Vehicles (UAVs) for data acquisition in severe weather conditions, such as heavy snowfall typical of the Nordic regi...
Published in: | Sensors |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2024
|
Subjects: | |
Online Access: | https://doi.org/10.3390/s24123938 https://doaj.org/article/896ef75ec0be4d3b8de1120c01e71744 |
id |
ftdoajarticles:oai:doaj.org/article:896ef75ec0be4d3b8de1120c01e71744 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:896ef75ec0be4d3b8de1120c01e71744 2024-09-15T18:26:11+00:00 Fractional B-Spline Wavelets and U-Net Architecture for Robust and Reliable Vehicle Detection in Snowy Conditions Hamam Mokayed Christián Ulehla Elda Shurdhaj Amirhossein Nayebiastaneh Lama Alkhaled Olle Hagner Yan Chai Hum 2024-06-01T00:00:00Z https://doi.org/10.3390/s24123938 https://doaj.org/article/896ef75ec0be4d3b8de1120c01e71744 EN eng MDPI AG https://www.mdpi.com/1424-8220/24/12/3938 https://doaj.org/toc/1424-8220 doi:10.3390/s24123938 1424-8220 https://doaj.org/article/896ef75ec0be4d3b8de1120c01e71744 Sensors, Vol 24, Iss 12, p 3938 (2024) vehicle detection fractional B-spline U-Net harsh weathers Chemical technology TP1-1185 article 2024 ftdoajarticles https://doi.org/10.3390/s24123938 2024-08-05T17:49:05Z This paper addresses the critical need for advanced real-time vehicle detection methodologies in Vehicle Intelligence Systems (VIS), especially in the context of using Unmanned Aerial Vehicles (UAVs) for data acquisition in severe weather conditions, such as heavy snowfall typical of the Nordic region. Traditional vehicle detection techniques, which often rely on custom-engineered features and deterministic algorithms, fall short in adapting to diverse environmental challenges, leading to a demand for more precise and sophisticated methods. The limitations of current architectures, particularly when deployed in real-time on edge devices with restricted computational capabilities, are highlighted as significant hurdles in the development of efficient vehicle detection systems. To bridge this gap, our research focuses on the formulation of an innovative approach that combines the fractional B-spline wavelet transform with a tailored U-Net architecture, operational on a Raspberry Pi 4. This method aims to enhance vehicle detection and localization by leveraging the unique attributes of the NVD dataset, which comprises drone-captured imagery under the harsh winter conditions of northern Sweden. The dataset, featuring 8450 annotated frames with 26,313 vehicles, serves as the foundation for evaluating the proposed technique. The comparative analysis of the proposed method against state-of-the-art detectors, such as YOLO and Faster RCNN, in both accuracy and efficiency on constrained devices, emphasizes the capability of our method to balance the trade-off between speed and accuracy, thereby broadening its utility across various domains. Article in Journal/Newspaper Northern Sweden Directory of Open Access Journals: DOAJ Articles Sensors 24 12 3938 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
vehicle detection fractional B-spline U-Net harsh weathers Chemical technology TP1-1185 |
spellingShingle |
vehicle detection fractional B-spline U-Net harsh weathers Chemical technology TP1-1185 Hamam Mokayed Christián Ulehla Elda Shurdhaj Amirhossein Nayebiastaneh Lama Alkhaled Olle Hagner Yan Chai Hum Fractional B-Spline Wavelets and U-Net Architecture for Robust and Reliable Vehicle Detection in Snowy Conditions |
topic_facet |
vehicle detection fractional B-spline U-Net harsh weathers Chemical technology TP1-1185 |
description |
This paper addresses the critical need for advanced real-time vehicle detection methodologies in Vehicle Intelligence Systems (VIS), especially in the context of using Unmanned Aerial Vehicles (UAVs) for data acquisition in severe weather conditions, such as heavy snowfall typical of the Nordic region. Traditional vehicle detection techniques, which often rely on custom-engineered features and deterministic algorithms, fall short in adapting to diverse environmental challenges, leading to a demand for more precise and sophisticated methods. The limitations of current architectures, particularly when deployed in real-time on edge devices with restricted computational capabilities, are highlighted as significant hurdles in the development of efficient vehicle detection systems. To bridge this gap, our research focuses on the formulation of an innovative approach that combines the fractional B-spline wavelet transform with a tailored U-Net architecture, operational on a Raspberry Pi 4. This method aims to enhance vehicle detection and localization by leveraging the unique attributes of the NVD dataset, which comprises drone-captured imagery under the harsh winter conditions of northern Sweden. The dataset, featuring 8450 annotated frames with 26,313 vehicles, serves as the foundation for evaluating the proposed technique. The comparative analysis of the proposed method against state-of-the-art detectors, such as YOLO and Faster RCNN, in both accuracy and efficiency on constrained devices, emphasizes the capability of our method to balance the trade-off between speed and accuracy, thereby broadening its utility across various domains. |
format |
Article in Journal/Newspaper |
author |
Hamam Mokayed Christián Ulehla Elda Shurdhaj Amirhossein Nayebiastaneh Lama Alkhaled Olle Hagner Yan Chai Hum |
author_facet |
Hamam Mokayed Christián Ulehla Elda Shurdhaj Amirhossein Nayebiastaneh Lama Alkhaled Olle Hagner Yan Chai Hum |
author_sort |
Hamam Mokayed |
title |
Fractional B-Spline Wavelets and U-Net Architecture for Robust and Reliable Vehicle Detection in Snowy Conditions |
title_short |
Fractional B-Spline Wavelets and U-Net Architecture for Robust and Reliable Vehicle Detection in Snowy Conditions |
title_full |
Fractional B-Spline Wavelets and U-Net Architecture for Robust and Reliable Vehicle Detection in Snowy Conditions |
title_fullStr |
Fractional B-Spline Wavelets and U-Net Architecture for Robust and Reliable Vehicle Detection in Snowy Conditions |
title_full_unstemmed |
Fractional B-Spline Wavelets and U-Net Architecture for Robust and Reliable Vehicle Detection in Snowy Conditions |
title_sort |
fractional b-spline wavelets and u-net architecture for robust and reliable vehicle detection in snowy conditions |
publisher |
MDPI AG |
publishDate |
2024 |
url |
https://doi.org/10.3390/s24123938 https://doaj.org/article/896ef75ec0be4d3b8de1120c01e71744 |
genre |
Northern Sweden |
genre_facet |
Northern Sweden |
op_source |
Sensors, Vol 24, Iss 12, p 3938 (2024) |
op_relation |
https://www.mdpi.com/1424-8220/24/12/3938 https://doaj.org/toc/1424-8220 doi:10.3390/s24123938 1424-8220 https://doaj.org/article/896ef75ec0be4d3b8de1120c01e71744 |
op_doi |
https://doi.org/10.3390/s24123938 |
container_title |
Sensors |
container_volume |
24 |
container_issue |
12 |
container_start_page |
3938 |
_version_ |
1810466637332086784 |