Cargando…

Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion

Vehicle detection using data fusion techniques from overhead platforms (RGB/MSI imagery and LiDAR point clouds) with vector and shape data can be a powerful tool in a variety of fields, including, but not limited to, national security, disaster relief efforts, and traffic monitoring. Knowing the loc...

Descripción completa

Detalles Bibliográficos
Autores principales: Bowman, Lindsey A., Narayanan, Ram M., Kane, Timothy J., Bradley, Eliza S., Baran, Matthew S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10648684/
https://www.ncbi.nlm.nih.gov/pubmed/37960511
http://dx.doi.org/10.3390/s23218811
_version_ 1785135396022124544
author Bowman, Lindsey A.
Narayanan, Ram M.
Kane, Timothy J.
Bradley, Eliza S.
Baran, Matthew S.
author_facet Bowman, Lindsey A.
Narayanan, Ram M.
Kane, Timothy J.
Bradley, Eliza S.
Baran, Matthew S.
author_sort Bowman, Lindsey A.
collection PubMed
description Vehicle detection using data fusion techniques from overhead platforms (RGB/MSI imagery and LiDAR point clouds) with vector and shape data can be a powerful tool in a variety of fields, including, but not limited to, national security, disaster relief efforts, and traffic monitoring. Knowing the location and number of vehicles in a given area can provide insight into the surrounding activities and patterns of life, as well as support decision-making processes. While researchers have developed many approaches to tackling this problem, few have exploited the multi-data approach with a classical technique. In this paper, a primarily LiDAR-based method supported by RGB/MSI imagery and road network shapefiles has been developed to detect stationary vehicles. The addition of imagery and road networks, when available, offers an improved classification of points from LiDAR data and helps to reduce false positives. Furthermore, detected vehicles can be assigned various 3D, relational, and spectral attributes, as well as height profiles. This method was evaluated on the Houston, TX dataset provided by the IEEE 2018 GRSS Data Fusion Contest, which includes 1476 ground truth vehicles from LiDAR data. On this dataset, the algorithm achieved a 92% precision and 92% recall. It was also evaluated on the Vaihingen, Germany dataset provided by ISPRS, as well as data simulated using an image generation model called DIRSIG. Some known limitations of the algorithm include false positives caused by low vegetation and the inability to detect vehicles (1) in extremely close proximity with high precision and (2) from low-density point clouds.
format Online
Article
Text
id pubmed-10648684
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106486842023-10-30 Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion Bowman, Lindsey A. Narayanan, Ram M. Kane, Timothy J. Bradley, Eliza S. Baran, Matthew S. Sensors (Basel) Article Vehicle detection using data fusion techniques from overhead platforms (RGB/MSI imagery and LiDAR point clouds) with vector and shape data can be a powerful tool in a variety of fields, including, but not limited to, national security, disaster relief efforts, and traffic monitoring. Knowing the location and number of vehicles in a given area can provide insight into the surrounding activities and patterns of life, as well as support decision-making processes. While researchers have developed many approaches to tackling this problem, few have exploited the multi-data approach with a classical technique. In this paper, a primarily LiDAR-based method supported by RGB/MSI imagery and road network shapefiles has been developed to detect stationary vehicles. The addition of imagery and road networks, when available, offers an improved classification of points from LiDAR data and helps to reduce false positives. Furthermore, detected vehicles can be assigned various 3D, relational, and spectral attributes, as well as height profiles. This method was evaluated on the Houston, TX dataset provided by the IEEE 2018 GRSS Data Fusion Contest, which includes 1476 ground truth vehicles from LiDAR data. On this dataset, the algorithm achieved a 92% precision and 92% recall. It was also evaluated on the Vaihingen, Germany dataset provided by ISPRS, as well as data simulated using an image generation model called DIRSIG. Some known limitations of the algorithm include false positives caused by low vegetation and the inability to detect vehicles (1) in extremely close proximity with high precision and (2) from low-density point clouds. MDPI 2023-10-30 /pmc/articles/PMC10648684/ /pubmed/37960511 http://dx.doi.org/10.3390/s23218811 Text en © 2023 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
Bowman, Lindsey A.
Narayanan, Ram M.
Kane, Timothy J.
Bradley, Eliza S.
Baran, Matthew S.
Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion
title Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion
title_full Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion
title_fullStr Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion
title_full_unstemmed Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion
title_short Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion
title_sort vehicle detection and attribution from a multi-sensor dataset using a rule-based approach combined with data fusion
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10648684/
https://www.ncbi.nlm.nih.gov/pubmed/37960511
http://dx.doi.org/10.3390/s23218811
work_keys_str_mv AT bowmanlindseya vehicledetectionandattributionfromamultisensordatasetusingarulebasedapproachcombinedwithdatafusion
AT narayananramm vehicledetectionandattributionfromamultisensordatasetusingarulebasedapproachcombinedwithdatafusion
AT kanetimothyj vehicledetectionandattributionfromamultisensordatasetusingarulebasedapproachcombinedwithdatafusion
AT bradleyelizas vehicledetectionandattributionfromamultisensordatasetusingarulebasedapproachcombinedwithdatafusion
AT baranmatthews vehicledetectionandattributionfromamultisensordatasetusingarulebasedapproachcombinedwithdatafusion