Automated Shoreline Segmentation in Satellite Imagery Using USV Measurements

Generating aerial shoreline segmentation masks can be a daunting task, often requiring manual labeling or correction. This is further problematic because neural segmentation models require decent and abundant data for training, requiring even more manpower to automate the process. In this paper, we...

Full description

Saved in:
Bibliographic Details
Main Authors: Antoni Jaszcz, Marta Włodarczyk-Sielicka, Andrzej Stateczny, Dawid Połap, Ilona Garczyńska
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/23/4457
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260157665116160
author Antoni Jaszcz
Marta Włodarczyk-Sielicka
Andrzej Stateczny
Dawid Połap
Ilona Garczyńska
author_facet Antoni Jaszcz
Marta Włodarczyk-Sielicka
Andrzej Stateczny
Dawid Połap
Ilona Garczyńska
author_sort Antoni Jaszcz
collection DOAJ
description Generating aerial shoreline segmentation masks can be a daunting task, often requiring manual labeling or correction. This is further problematic because neural segmentation models require decent and abundant data for training, requiring even more manpower to automate the process. In this paper, we propose utilizing Unmanned Surface Vehicles (USVs) in an automated shoreline segmentation system on satellite imagery. The remotely controlled vessel first collects above- and underwater shoreline information using light detection and ranging (LiDAR) and multibeam echosounder (MBES) measuring instruments, resulting in a geo-referenced 3D point cloud. After cleaning and processing these data, the system integrates the projected map with an aerial image of the region. Based on the height values of the mapped points, the image is segmented. Finally, post-processing methods and the k-NN algorithm are introduced, resulting in a complete binary shoreline segmentation mask. The obtained data were used for training U-Net-type segmentation models with pre-trained backbones. The InceptionV3-based model achieved an accuracy of 96% and a dice coefficient score of 93%, demonstrating the effectiveness of the proposed system as a source of data acquisition for training deep neural networks.
format Article
id doaj-art-6f60523b522440bf908ca91c7febc8bc
institution OA Journals
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-6f60523b522440bf908ca91c7febc8bc2025-08-20T01:55:41ZengMDPI AGRemote Sensing2072-42922024-11-011623445710.3390/rs16234457Automated Shoreline Segmentation in Satellite Imagery Using USV MeasurementsAntoni Jaszcz0Marta Włodarczyk-Sielicka1Andrzej Stateczny2Dawid Połap3Ilona Garczyńska4Faculty of Applied Mathematics, Silesian University of Technology, Kaszubska 23, 44-100 Gliwice, PolandDepartment of Geoinformatic and Hydrographic, Maritime University of Szczecin, Wały Chrobrego 1-2, 70-500 Szczecin, PolandFaculty of Navigation, Gdynia Maritime University, 81-87 Morska St., 81-225 Gdynia, PolandFaculty of Applied Mathematics, Silesian University of Technology, Kaszubska 23, 44-100 Gliwice, PolandMarine Technology Ltd., Roszczynialskiego 4/6, 81-521 Gdynia, PolandGenerating aerial shoreline segmentation masks can be a daunting task, often requiring manual labeling or correction. This is further problematic because neural segmentation models require decent and abundant data for training, requiring even more manpower to automate the process. In this paper, we propose utilizing Unmanned Surface Vehicles (USVs) in an automated shoreline segmentation system on satellite imagery. The remotely controlled vessel first collects above- and underwater shoreline information using light detection and ranging (LiDAR) and multibeam echosounder (MBES) measuring instruments, resulting in a geo-referenced 3D point cloud. After cleaning and processing these data, the system integrates the projected map with an aerial image of the region. Based on the height values of the mapped points, the image is segmented. Finally, post-processing methods and the k-NN algorithm are introduced, resulting in a complete binary shoreline segmentation mask. The obtained data were used for training U-Net-type segmentation models with pre-trained backbones. The InceptionV3-based model achieved an accuracy of 96% and a dice coefficient score of 93%, demonstrating the effectiveness of the proposed system as a source of data acquisition for training deep neural networks.https://www.mdpi.com/2072-4292/16/23/4457USVLiDARmultibeam echosounderimagefusionmasks
spellingShingle Antoni Jaszcz
Marta Włodarczyk-Sielicka
Andrzej Stateczny
Dawid Połap
Ilona Garczyńska
Automated Shoreline Segmentation in Satellite Imagery Using USV Measurements
Remote Sensing
USV
LiDAR
multibeam echosounder
image
fusion
masks
title Automated Shoreline Segmentation in Satellite Imagery Using USV Measurements
title_full Automated Shoreline Segmentation in Satellite Imagery Using USV Measurements
title_fullStr Automated Shoreline Segmentation in Satellite Imagery Using USV Measurements
title_full_unstemmed Automated Shoreline Segmentation in Satellite Imagery Using USV Measurements
title_short Automated Shoreline Segmentation in Satellite Imagery Using USV Measurements
title_sort automated shoreline segmentation in satellite imagery using usv measurements
topic USV
LiDAR
multibeam echosounder
image
fusion
masks
url https://www.mdpi.com/2072-4292/16/23/4457
work_keys_str_mv AT antonijaszcz automatedshorelinesegmentationinsatelliteimageryusingusvmeasurements
AT martawłodarczyksielicka automatedshorelinesegmentationinsatelliteimageryusingusvmeasurements
AT andrzejstateczny automatedshorelinesegmentationinsatelliteimageryusingusvmeasurements
AT dawidpołap automatedshorelinesegmentationinsatelliteimageryusingusvmeasurements
AT ilonagarczynska automatedshorelinesegmentationinsatelliteimageryusingusvmeasurements