SHALLOW WATER BATHYMETRY MAPPING FROM UAV IMAGERY BASED ON MACHINE LEARNING

The determination of accurate bathymetric information is a key element for near offshore activities, hydrological studies such as coastal engineering applications, sedimentary processes, hydrographic surveying as well as archaeological mapping and biological research. UAV imagery processed with Stru...

Full description

Bibliographic Details
Main Authors: P. Agrafiotis, D. Skarlatos, A. Georgopoulos, K. Karantzalos
Format: Article
Language:English
Published: Copernicus Publications 2019-04-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W10/9/2019/isprs-archives-XLII-2-W10-9-2019.pdf
_version_ 1818525202662817792
author P. Agrafiotis
P. Agrafiotis
D. Skarlatos
A. Georgopoulos
K. Karantzalos
author_facet P. Agrafiotis
P. Agrafiotis
D. Skarlatos
A. Georgopoulos
K. Karantzalos
author_sort P. Agrafiotis
collection DOAJ
description The determination of accurate bathymetric information is a key element for near offshore activities, hydrological studies such as coastal engineering applications, sedimentary processes, hydrographic surveying as well as archaeological mapping and biological research. UAV imagery processed with Structure from Motion (SfM) and Multi View Stereo (MVS) techniques can provide a low-cost alternative to established shallow seabed mapping techniques offering as well the important visual information. Nevertheless, water refraction poses significant challenges on depth determination. Till now, this problem has been addressed through customized image-based refraction correction algorithms or by modifying the collinearity equation. In this paper, in order to overcome the water refraction errors, we employ machine learning tools that are able to learn the systematic underestimation of the estimated depths. In the proposed approach, based on known depth observations from bathymetric LiDAR surveys, an SVR model was developed able to estimate more accurately the real depths of point clouds derived from SfM-MVS procedures. Experimental results over two test sites along with the performed quantitative validation indicated the high potential of the developed approach.
first_indexed 2024-12-11T06:06:27Z
format Article
id doaj.art-c683a343c0f14076b3692052cd3130bb
institution Directory Open Access Journal
issn 1682-1750
2194-9034
language English
last_indexed 2024-12-11T06:06:27Z
publishDate 2019-04-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj.art-c683a343c0f14076b3692052cd3130bb2022-12-22T01:18:17ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342019-04-01XLII-2-W1091610.5194/isprs-archives-XLII-2-W10-9-2019SHALLOW WATER BATHYMETRY MAPPING FROM UAV IMAGERY BASED ON MACHINE LEARNINGP. Agrafiotis0P. Agrafiotis1D. Skarlatos2A. Georgopoulos3K. Karantzalos4National Technical University of Athens, School of Rural and Surveying Engineering, Department of Topography, Zografou Campus, 9 Heroon Polytechniou str., 15780, Athens, GreeceCyprus University of Technology, Civil Engineering and Geomatics Dept., Lab of Photogrammetric Vision, 2-8 Saripolou str., 3036, Limassol, CyprusCyprus University of Technology, Civil Engineering and Geomatics Dept., Lab of Photogrammetric Vision, 2-8 Saripolou str., 3036, Limassol, CyprusNational Technical University of Athens, School of Rural and Surveying Engineering, Department of Topography, Zografou Campus, 9 Heroon Polytechniou str., 15780, Athens, GreeceNational Technical University of Athens, School of Rural and Surveying Engineering, Department of Topography, Zografou Campus, 9 Heroon Polytechniou str., 15780, Athens, GreeceThe determination of accurate bathymetric information is a key element for near offshore activities, hydrological studies such as coastal engineering applications, sedimentary processes, hydrographic surveying as well as archaeological mapping and biological research. UAV imagery processed with Structure from Motion (SfM) and Multi View Stereo (MVS) techniques can provide a low-cost alternative to established shallow seabed mapping techniques offering as well the important visual information. Nevertheless, water refraction poses significant challenges on depth determination. Till now, this problem has been addressed through customized image-based refraction correction algorithms or by modifying the collinearity equation. In this paper, in order to overcome the water refraction errors, we employ machine learning tools that are able to learn the systematic underestimation of the estimated depths. In the proposed approach, based on known depth observations from bathymetric LiDAR surveys, an SVR model was developed able to estimate more accurately the real depths of point clouds derived from SfM-MVS procedures. Experimental results over two test sites along with the performed quantitative validation indicated the high potential of the developed approach.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W10/9/2019/isprs-archives-XLII-2-W10-9-2019.pdf
spellingShingle P. Agrafiotis
P. Agrafiotis
D. Skarlatos
A. Georgopoulos
K. Karantzalos
SHALLOW WATER BATHYMETRY MAPPING FROM UAV IMAGERY BASED ON MACHINE LEARNING
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title SHALLOW WATER BATHYMETRY MAPPING FROM UAV IMAGERY BASED ON MACHINE LEARNING
title_full SHALLOW WATER BATHYMETRY MAPPING FROM UAV IMAGERY BASED ON MACHINE LEARNING
title_fullStr SHALLOW WATER BATHYMETRY MAPPING FROM UAV IMAGERY BASED ON MACHINE LEARNING
title_full_unstemmed SHALLOW WATER BATHYMETRY MAPPING FROM UAV IMAGERY BASED ON MACHINE LEARNING
title_short SHALLOW WATER BATHYMETRY MAPPING FROM UAV IMAGERY BASED ON MACHINE LEARNING
title_sort shallow water bathymetry mapping from uav imagery based on machine learning
url https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W10/9/2019/isprs-archives-XLII-2-W10-9-2019.pdf
work_keys_str_mv AT pagrafiotis shallowwaterbathymetrymappingfromuavimagerybasedonmachinelearning
AT pagrafiotis shallowwaterbathymetrymappingfromuavimagerybasedonmachinelearning
AT dskarlatos shallowwaterbathymetrymappingfromuavimagerybasedonmachinelearning
AT ageorgopoulos shallowwaterbathymetrymappingfromuavimagerybasedonmachinelearning
AT kkarantzalos shallowwaterbathymetrymappingfromuavimagerybasedonmachinelearning