Motion Constrained Point Cloud Matching for Maritime Tracking

Extended Object Tracking (EOT) plays a critical role in accurately estimating the state of nearby vessels in confined regions, such as urban waterways. By estimating a vessel’s extent, it is possible to improve velocity estimation and motion prediction. Traditional EOT methods in the mari...

Full description

Saved in:
Bibliographic Details
Main Authors: Nicholas Dalhaug, Martin Baerveldt, Angelica I. Aviles-Rivero, Carola-Bibiane Schonlieb, Annette Stahl, Rudolf Mester, Edmund Forland Brekke
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11048472/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428077544734720
author Nicholas Dalhaug
Martin Baerveldt
Angelica I. Aviles-Rivero
Carola-Bibiane Schonlieb
Annette Stahl
Rudolf Mester
Edmund Forland Brekke
author_facet Nicholas Dalhaug
Martin Baerveldt
Angelica I. Aviles-Rivero
Carola-Bibiane Schonlieb
Annette Stahl
Rudolf Mester
Edmund Forland Brekke
author_sort Nicholas Dalhaug
collection DOAJ
description Extended Object Tracking (EOT) plays a critical role in accurately estimating the state of nearby vessels in confined regions, such as urban waterways. By estimating a vessel’s extent, it is possible to improve velocity estimation and motion prediction. Traditional EOT methods in the maritime domain that use point clouds from Light Detection And Ranging (LiDAR) commonly parameterize target extents. However, these approaches often struggle with data association and clutter removal, particularly when using 2D parameterizations. To address these limitations, we propose a 3D EOT framework leveraging motion-constrained Iterative Closest Point (ICP) displacements integrated into an Error State Kalman Filter (ESKF). Our approach incorporates maritime-specific motion constraints, enabling robust target tracking even with sparse measurements. Evaluation on real-world maritime data demonstrates that the proposed 3D tracker significantly outperforms a 2D Gaussian Process Extended Object Tracking (GP-EOT) tracker, offering enhanced resilience against wake-induced noise and delivering superior state and extent estimation accuracy.
format Article
id doaj-art-78eee73fb01e40358cd1bbff411b5fbb
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-78eee73fb01e40358cd1bbff411b5fbb2025-08-20T03:28:48ZengIEEEIEEE Access2169-35362025-01-011311135411137110.1109/ACCESS.2025.358232711048472Motion Constrained Point Cloud Matching for Maritime TrackingNicholas Dalhaug0https://orcid.org/0009-0007-7824-5904Martin Baerveldt1https://orcid.org/0009-0008-6485-487XAngelica I. Aviles-Rivero2https://orcid.org/0000-0002-8878-0325Carola-Bibiane Schonlieb3https://orcid.org/0000-0003-0099-6306Annette Stahl4Rudolf Mester5Edmund Forland Brekke6https://orcid.org/0000-0001-8735-1687Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, NorwayDepartment of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, NorwayYau Mathematical Sciences Center, Tsinghua University, Beijing, ChinaDepartment of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, U.K.Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, NorwayDepartment of Computer Science, Norwegian University of Science and Technology (NTNU), Trondheim, NorwayDepartment of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, NorwayExtended Object Tracking (EOT) plays a critical role in accurately estimating the state of nearby vessels in confined regions, such as urban waterways. By estimating a vessel’s extent, it is possible to improve velocity estimation and motion prediction. Traditional EOT methods in the maritime domain that use point clouds from Light Detection And Ranging (LiDAR) commonly parameterize target extents. However, these approaches often struggle with data association and clutter removal, particularly when using 2D parameterizations. To address these limitations, we propose a 3D EOT framework leveraging motion-constrained Iterative Closest Point (ICP) displacements integrated into an Error State Kalman Filter (ESKF). Our approach incorporates maritime-specific motion constraints, enabling robust target tracking even with sparse measurements. Evaluation on real-world maritime data demonstrates that the proposed 3D tracker significantly outperforms a 2D Gaussian Process Extended Object Tracking (GP-EOT) tracker, offering enhanced resilience against wake-induced noise and delivering superior state and extent estimation accuracy.https://ieeexplore.ieee.org/document/11048472/EOTICPLiDARmaritimetarget tracking
spellingShingle Nicholas Dalhaug
Martin Baerveldt
Angelica I. Aviles-Rivero
Carola-Bibiane Schonlieb
Annette Stahl
Rudolf Mester
Edmund Forland Brekke
Motion Constrained Point Cloud Matching for Maritime Tracking
IEEE Access
EOT
ICP
LiDAR
maritime
target tracking
title Motion Constrained Point Cloud Matching for Maritime Tracking
title_full Motion Constrained Point Cloud Matching for Maritime Tracking
title_fullStr Motion Constrained Point Cloud Matching for Maritime Tracking
title_full_unstemmed Motion Constrained Point Cloud Matching for Maritime Tracking
title_short Motion Constrained Point Cloud Matching for Maritime Tracking
title_sort motion constrained point cloud matching for maritime tracking
topic EOT
ICP
LiDAR
maritime
target tracking
url https://ieeexplore.ieee.org/document/11048472/
work_keys_str_mv AT nicholasdalhaug motionconstrainedpointcloudmatchingformaritimetracking
AT martinbaerveldt motionconstrainedpointcloudmatchingformaritimetracking
AT angelicaiavilesrivero motionconstrainedpointcloudmatchingformaritimetracking
AT carolabibianeschonlieb motionconstrainedpointcloudmatchingformaritimetracking
AT annettestahl motionconstrainedpointcloudmatchingformaritimetracking
AT rudolfmester motionconstrainedpointcloudmatchingformaritimetracking
AT edmundforlandbrekke motionconstrainedpointcloudmatchingformaritimetracking