Cargando…

Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets

The work presented here develops a computer vision framework that is view angle independent for vehicle segmentation and classification from roadway traffic systems installed by the Virginia Department of Transportation (VDOT). An automated technique for extracting a region of interest is discussed...

Descripción completa

Detalles Bibliográficos
Autores principales: Yousef, Amr, Flora, Jeff, Iftekharuddin, Khan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9654483/
https://www.ncbi.nlm.nih.gov/pubmed/36365821
http://dx.doi.org/10.3390/s22218121
_version_ 1784828943098970112
author Yousef, Amr
Flora, Jeff
Iftekharuddin, Khan
author_facet Yousef, Amr
Flora, Jeff
Iftekharuddin, Khan
author_sort Yousef, Amr
collection PubMed
description The work presented here develops a computer vision framework that is view angle independent for vehicle segmentation and classification from roadway traffic systems installed by the Virginia Department of Transportation (VDOT). An automated technique for extracting a region of interest is discussed to speed up the processing. The VDOT traffic videos are analyzed for vehicle segmentation using an improved robust low-rank matrix decomposition technique. It presents a new and effective thresholding method that improves segmentation accuracy and simultaneously speeds up the segmentation processing. Size and shape physical descriptors from morphological properties and textural features from the Histogram of Oriented Gradients (HOG) are extracted from the segmented traffic. Furthermore, a multi-class support vector machine classifier is employed to categorize different traffic vehicle types, including passenger cars, passenger trucks, motorcycles, buses, and small and large utility trucks. It handles multiple vehicle detections through an iterative k-means clustering over-segmentation process. The proposed algorithm reduced the processed data by an average of 40%. Compared to recent techniques, it showed an average improvement of 15% in segmentation accuracy, and it is 55% faster than the compared segmentation techniques on average. Moreover, a comparative analysis of 23 different deep learning architectures is presented. The resulting algorithm outperformed the compared deep learning algorithms for the quality of vehicle classification accuracy. Furthermore, the timing analysis showed that it could operate in real-time scenarios.
format Online
Article
Text
id pubmed-9654483
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96544832022-11-15 Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets Yousef, Amr Flora, Jeff Iftekharuddin, Khan Sensors (Basel) Article The work presented here develops a computer vision framework that is view angle independent for vehicle segmentation and classification from roadway traffic systems installed by the Virginia Department of Transportation (VDOT). An automated technique for extracting a region of interest is discussed to speed up the processing. The VDOT traffic videos are analyzed for vehicle segmentation using an improved robust low-rank matrix decomposition technique. It presents a new and effective thresholding method that improves segmentation accuracy and simultaneously speeds up the segmentation processing. Size and shape physical descriptors from morphological properties and textural features from the Histogram of Oriented Gradients (HOG) are extracted from the segmented traffic. Furthermore, a multi-class support vector machine classifier is employed to categorize different traffic vehicle types, including passenger cars, passenger trucks, motorcycles, buses, and small and large utility trucks. It handles multiple vehicle detections through an iterative k-means clustering over-segmentation process. The proposed algorithm reduced the processed data by an average of 40%. Compared to recent techniques, it showed an average improvement of 15% in segmentation accuracy, and it is 55% faster than the compared segmentation techniques on average. Moreover, a comparative analysis of 23 different deep learning architectures is presented. The resulting algorithm outperformed the compared deep learning algorithms for the quality of vehicle classification accuracy. Furthermore, the timing analysis showed that it could operate in real-time scenarios. MDPI 2022-10-24 /pmc/articles/PMC9654483/ /pubmed/36365821 http://dx.doi.org/10.3390/s22218121 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yousef, Amr
Flora, Jeff
Iftekharuddin, Khan
Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets
title Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets
title_full Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets
title_fullStr Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets
title_full_unstemmed Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets
title_short Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets
title_sort monocular camera viewpoint-invariant vehicular traffic segmentation and classification utilizing small datasets
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9654483/
https://www.ncbi.nlm.nih.gov/pubmed/36365821
http://dx.doi.org/10.3390/s22218121
work_keys_str_mv AT yousefamr monocularcameraviewpointinvariantvehiculartrafficsegmentationandclassificationutilizingsmalldatasets
AT florajeff monocularcameraviewpointinvariantvehiculartrafficsegmentationandclassificationutilizingsmalldatasets
AT iftekharuddinkhan monocularcameraviewpointinvariantvehiculartrafficsegmentationandclassificationutilizingsmalldatasets