Cargando…

A Real-Time Method for Time-to-Collision Estimation from Aerial Images

Large vessels such as container ships rely on experienced pilots with extensive knowledge of the local streams and tides responsible for maneuvering the vessel to its desired location. This work proposes estimating time-to-collision (TTC) between moving objects (i.e., vessels) using real-time video...

Descripción completa

Detalles Bibliográficos
Autores principales: Tøttrup, Daniel, Skovgaard, Stinus Lykke, Sejersen, Jonas le Fevre, Pimentel de Figueiredo, Rui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8948977/
https://www.ncbi.nlm.nih.gov/pubmed/35324617
http://dx.doi.org/10.3390/jimaging8030062
_version_ 1784674783583010816
author Tøttrup, Daniel
Skovgaard, Stinus Lykke
Sejersen, Jonas le Fevre
Pimentel de Figueiredo, Rui
author_facet Tøttrup, Daniel
Skovgaard, Stinus Lykke
Sejersen, Jonas le Fevre
Pimentel de Figueiredo, Rui
author_sort Tøttrup, Daniel
collection PubMed
description Large vessels such as container ships rely on experienced pilots with extensive knowledge of the local streams and tides responsible for maneuvering the vessel to its desired location. This work proposes estimating time-to-collision (TTC) between moving objects (i.e., vessels) using real-time video data captured from aerial drones in dynamic maritime environments. Our deep-learning-based methods utilize features optimized with realistic virtually generated data for reliable and robust object detection, segmentation, and tracking. Furthermore, we use rotated bounding box representations, obtained from fine semantic segmentation of objects, for enhanced TTC estimation accuracy. We intuitively present collision estimates as collision arrows that gradually change color to red to indicate an imminent collision. Experiments conducted in a realistic dockyard virtual environment show that our approaches precisely, robustly, and efficiently predict TTC between dynamic objects seen from a top-view, with a mean error and a standard deviation of 0.358 and 0.114 s, respectively, in a worst-case scenario.
format Online
Article
Text
id pubmed-8948977
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89489772022-03-26 A Real-Time Method for Time-to-Collision Estimation from Aerial Images Tøttrup, Daniel Skovgaard, Stinus Lykke Sejersen, Jonas le Fevre Pimentel de Figueiredo, Rui J Imaging Article Large vessels such as container ships rely on experienced pilots with extensive knowledge of the local streams and tides responsible for maneuvering the vessel to its desired location. This work proposes estimating time-to-collision (TTC) between moving objects (i.e., vessels) using real-time video data captured from aerial drones in dynamic maritime environments. Our deep-learning-based methods utilize features optimized with realistic virtually generated data for reliable and robust object detection, segmentation, and tracking. Furthermore, we use rotated bounding box representations, obtained from fine semantic segmentation of objects, for enhanced TTC estimation accuracy. We intuitively present collision estimates as collision arrows that gradually change color to red to indicate an imminent collision. Experiments conducted in a realistic dockyard virtual environment show that our approaches precisely, robustly, and efficiently predict TTC between dynamic objects seen from a top-view, with a mean error and a standard deviation of 0.358 and 0.114 s, respectively, in a worst-case scenario. MDPI 2022-03-03 /pmc/articles/PMC8948977/ /pubmed/35324617 http://dx.doi.org/10.3390/jimaging8030062 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
Tøttrup, Daniel
Skovgaard, Stinus Lykke
Sejersen, Jonas le Fevre
Pimentel de Figueiredo, Rui
A Real-Time Method for Time-to-Collision Estimation from Aerial Images
title A Real-Time Method for Time-to-Collision Estimation from Aerial Images
title_full A Real-Time Method for Time-to-Collision Estimation from Aerial Images
title_fullStr A Real-Time Method for Time-to-Collision Estimation from Aerial Images
title_full_unstemmed A Real-Time Method for Time-to-Collision Estimation from Aerial Images
title_short A Real-Time Method for Time-to-Collision Estimation from Aerial Images
title_sort real-time method for time-to-collision estimation from aerial images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8948977/
https://www.ncbi.nlm.nih.gov/pubmed/35324617
http://dx.doi.org/10.3390/jimaging8030062
work_keys_str_mv AT tøttrupdaniel arealtimemethodfortimetocollisionestimationfromaerialimages
AT skovgaardstinuslykke arealtimemethodfortimetocollisionestimationfromaerialimages
AT sejersenjonaslefevre arealtimemethodfortimetocollisionestimationfromaerialimages
AT pimenteldefigueiredorui arealtimemethodfortimetocollisionestimationfromaerialimages
AT tøttrupdaniel realtimemethodfortimetocollisionestimationfromaerialimages
AT skovgaardstinuslykke realtimemethodfortimetocollisionestimationfromaerialimages
AT sejersenjonaslefevre realtimemethodfortimetocollisionestimationfromaerialimages
AT pimenteldefigueiredorui realtimemethodfortimetocollisionestimationfromaerialimages