Cargando…

Multiple Aerial Targets Re-Identification by 2D- and 3D- Kinematics-Based Matching

This paper presents two techniques in the matching and re-identification of multiple aerial target detections from multiple electro-optical devices: 2-dimensional and 3-dimensional kinematics-based matching. The main advantage of these methods over traditional image-based methods is that no prior im...

Descripción completa

Detalles Bibliográficos
Autores principales: Seah, Shao Xuan, Lau, Yan Han, Srigrarom, Sutthiphong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8880728/
https://www.ncbi.nlm.nih.gov/pubmed/35200728
http://dx.doi.org/10.3390/jimaging8020026
_version_ 1784659291488124928
author Seah, Shao Xuan
Lau, Yan Han
Srigrarom, Sutthiphong
author_facet Seah, Shao Xuan
Lau, Yan Han
Srigrarom, Sutthiphong
author_sort Seah, Shao Xuan
collection PubMed
description This paper presents two techniques in the matching and re-identification of multiple aerial target detections from multiple electro-optical devices: 2-dimensional and 3-dimensional kinematics-based matching. The main advantage of these methods over traditional image-based methods is that no prior image-based training is required; instead, relatively simpler graph matching algorithms are used. The first 2-dimensional method relies solely on the kinematic and geometric projections of the detected targets onto the images captured by the various cameras. Matching and re-identification across frames were performed using a series of correlation-based methods. This method is suitable for all targets with distinct motion observed by the camera. The second 3-dimensional method relies on the change in the size of detected targets to estimate motion in the focal axis by constructing an instantaneous direction vector in 3D space that is independent of camera pose. Matching and re-identification were achieved by directly comparing these vectors across frames under a global coordinate system. Such a method is suitable for targets in near to medium range where changes in detection sizes may be observed. While no overlapping field of view requirements were explicitly imposed, it is necessary for the aerial target to be detected in both cameras before matching can be carried out. Preliminary flight tests were conducted using 2–3 drones at varying ranges, and the effectiveness of these techniques was tested and compared. Using these proposed techniques, an MOTA score of more than 80% was achieved.
format Online
Article
Text
id pubmed-8880728
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88807282022-02-26 Multiple Aerial Targets Re-Identification by 2D- and 3D- Kinematics-Based Matching Seah, Shao Xuan Lau, Yan Han Srigrarom, Sutthiphong J Imaging Article This paper presents two techniques in the matching and re-identification of multiple aerial target detections from multiple electro-optical devices: 2-dimensional and 3-dimensional kinematics-based matching. The main advantage of these methods over traditional image-based methods is that no prior image-based training is required; instead, relatively simpler graph matching algorithms are used. The first 2-dimensional method relies solely on the kinematic and geometric projections of the detected targets onto the images captured by the various cameras. Matching and re-identification across frames were performed using a series of correlation-based methods. This method is suitable for all targets with distinct motion observed by the camera. The second 3-dimensional method relies on the change in the size of detected targets to estimate motion in the focal axis by constructing an instantaneous direction vector in 3D space that is independent of camera pose. Matching and re-identification were achieved by directly comparing these vectors across frames under a global coordinate system. Such a method is suitable for targets in near to medium range where changes in detection sizes may be observed. While no overlapping field of view requirements were explicitly imposed, it is necessary for the aerial target to be detected in both cameras before matching can be carried out. Preliminary flight tests were conducted using 2–3 drones at varying ranges, and the effectiveness of these techniques was tested and compared. Using these proposed techniques, an MOTA score of more than 80% was achieved. MDPI 2022-01-28 /pmc/articles/PMC8880728/ /pubmed/35200728 http://dx.doi.org/10.3390/jimaging8020026 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
Seah, Shao Xuan
Lau, Yan Han
Srigrarom, Sutthiphong
Multiple Aerial Targets Re-Identification by 2D- and 3D- Kinematics-Based Matching
title Multiple Aerial Targets Re-Identification by 2D- and 3D- Kinematics-Based Matching
title_full Multiple Aerial Targets Re-Identification by 2D- and 3D- Kinematics-Based Matching
title_fullStr Multiple Aerial Targets Re-Identification by 2D- and 3D- Kinematics-Based Matching
title_full_unstemmed Multiple Aerial Targets Re-Identification by 2D- and 3D- Kinematics-Based Matching
title_short Multiple Aerial Targets Re-Identification by 2D- and 3D- Kinematics-Based Matching
title_sort multiple aerial targets re-identification by 2d- and 3d- kinematics-based matching
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8880728/
https://www.ncbi.nlm.nih.gov/pubmed/35200728
http://dx.doi.org/10.3390/jimaging8020026
work_keys_str_mv AT seahshaoxuan multipleaerialtargetsreidentificationby2dand3dkinematicsbasedmatching
AT lauyanhan multipleaerialtargetsreidentificationby2dand3dkinematicsbasedmatching
AT srigraromsutthiphong multipleaerialtargetsreidentificationby2dand3dkinematicsbasedmatching