Tytuł: The Reduction Method of Bathymetric Datasets that Preserves True Geodata

Autor/Autorzy: Marta Włodarczyk-Sielicka, Andrzej Stateczny, Jacek Łubczonek

Miejsce
publikacji: Remote Sensing

Rok: 2019

Słowa
kluczowe: big data applications, data processing, data visualization, neural networks, reduction, coastal waters

Abstrakt:Water areas occupy over 70 percent of the Earth’s surface and are constantly subject to research and analysis. Often, hydrographic remote sensors are used for such research, which allow for the collection of information on the shape of the water area bottom and the objects located on it. Information about the quality and reliability of the depth data is important, especially during coastal modelling. In-shore areas are liable to continuous transformations and they must be monitored and analyzed. Presently, bathymetric geodata are usually collected via modern hydrographic systems and comprise very large data point sequences that must then be connected using long and laborious processing sequences including reduction. As existing bathymetric data reduction methods utilize interpolated values, there is a clear requirement to search for new solutions. Considering the accuracy of bathymetric maps, a new method is presented here that allows real geodata to be maintained, specifically position and depth. This study presents a description of a developed method for reducing geodata while maintaining true survey values.

Adres strony internetowej (link) do pełnego tekstu
publikacji: https://www.mdpi.com/2072-4292/11/13/1610

DOI: 10.3390/rs11131610

Tytuł: Analysis of the accuracy of shoreline mapping in inland navigational charts (Inland ENC) using photogrammetric and sonar images

Autor/Autorzy: Jacek Łubczonek, Małgorzata Łącka, Grzegorz Zaniewicz

Miejsce
publikacji: Scientific Journals of the Maritime University of Szczecin-Zeszyty Naukowe Akademii Morskiej w Szczecinie

Rok: 2019

Słowa
kluczowe: photogrammetry, navigation chart, hydrography

Abstrakt:Shoreline mapping is one of the key stages in navigational charting. In terms of navigation, the shoreline marks the boundary of a river, which is often equivalent to the navigable water area. In cartographic terms, it is an important topological element between different objects that are adjacent to it. Currently, topographic objects are often mapped using photogrammetric materials obtained from various altitudes – satellite, airborne or low, which is associated with the use of an airborne UAV. Depending on the type of materials, the shoreline can be obtained in vector form with differing situational accuracy and differing degree of detail. In addition to the standard methods of processing vector data, the research in this paper also included the use of sonar images, enabling the detection of the shoreline with the use of a surveying hydrographic unit. On the basis of the collected photogrammetric and sonar images of different spatial resolution, an analysis of the accuracy of shoreline mapping was performed in terms of the situational accuracy and the level of detail in its representation. The results of the research provided the basis for the determination of dedicated remote sensing materials enabling the development of maps for inland navigation.

Adres strony internetowej (link) do pełnego tekstu
publikacji:http://repository.scientific-journals.eu/handle/123456789/2534

DOI: 10.17402/335

Tytuł: The Use of an Artificial Neural Network to Process Hydrographic Big Data during Surface Modeling

Autor/Autorzy: Marta Włodarczyk-Sielicka, Jacek Łubczonek

Miejsce
publikacji: Computers

Rok: 2019

Słowa
kluczowe: neural networks, bathymetric data, interpolation, reduction, DTM, big data

Abstrakt:At the present time, spatial data are often acquired using varied remote sensing sensors and systems, which produce big data sets. One significant product from these data is a digital model of geographical surfaces, including the surface of the sea floor. To improve data processing, presentation, and management, it is often indispensable to reduce the number of data points. This paper presents research regarding the application of artificial neural networks to bathymetric data reductions. This research considers results from radial networks and self-organizing Kohonen networks. During reconstructions of the seabed model, the results show that neural networks with fewer hidden neurons than the number of data points can replicate the original data set, while the Kohonen network can be used for clustering during big geodata reduction. Practical implementations of neural networks capable of creating surface models and reducing bathymetric data are presented.

Adres strony internetowej (link) do pełnego tekstu
publikacji: https://www.mdpi.com/2073-431X/8/1/26

DOI: 10.3390/computers8010026

Tytuł: The use of terrestrial laser scanning for mapping bridges on electronic navigational charts

Autor/Autorzy: Jacek Łubczonek

Miejsce
publikacji: Roczniki Geomatyki [Annals of Geomatics]

Rok: 2017

Słowa
kluczowe: electronic navigational charts, terrestrial laser scanning, map creation

Abstrakt: Bridges are one of the most important objects of electronic navigation maps. Presently, multiple sources to create maps, such as basic maps, orthoimages or technical drawings, can be used. Unfortunately, these materials are not always suitable for collecting bridge data. Basic maps do not always present correct shapes of the supports, on orthoimages all land cover elements are subject to radial shifts, relative to the projection centre, and drawings do not have reference points to allow for data registration to the coordinate system. The paper presents the use of terrestrial laser scanning for mapping bridges, from data collection to acquisition of vector data. The study analyzes the range of scanning performed in day and night conditions, discusses the problems associated with point clouds combination, discusses the process of the project point cloud registration to the coordinate system and the data vectorisation process. Finally, the accuracy of vector data was analysed on the basis of independent measurement control points. The resulting differences between the checkpoints and the vector data with the average value of 4 cm and the maximum value of 8 cm, indicate that the use of this technique for mapping bridges on electronic navigation charts is justified. In the final stage, all the activities related to the acquisition of mapping data and vector data are presented in the form of the workflow diagram.

Adres strony internetowej (link) do pełnego tekstu
publikacji: http://rg.ptip.org.pl/index.php/rg/issue/view/265

DOI:

Tytuł: Geoprocessing of High Resolution Imageries for Shoreline Extraction in the Process of the Production of Inland Electronic Navigational Charts.

Autor/Autorzy: Jacek Łubczonek

Miejsce
publikacji: Photogrammetrie Fernerkundung Geoinformation

Rok: 2016

Słowa
kluczowe: ELECTRONIC NAVIGATIONAL CHARTS, IMAGE PROCESSING, MATHEMATICAL MORPHOLOGY, SHORELINE EXTRACTION

Abstrakt: At present, for map elaboration, remote sensing images are used very frequently. By using different methods of image processing, the process of developing the map can be automated, mainly due to the reduced time required to obtain geographical objects in vector form. The paper presents a method for the extraction of shorelines by using high resolution images. The extraction process by using geoprocessing tools of the ArcGIS software is exemplarily illustrated. Because GIS or remote sensing software can have several geo-processing tools, it is important to investigate the set of tools proposed by the software developer that can be used for image processing. Based on this study, an image geoprocessing routine is proposed, which uses methods such as classification, thresholding, mathematical morphology, and vectorisation. The target use of the extraction method is dedicated to the production of Inland Electronic Navigational Charts.

Adres strony internetowej (link) do pełnego tekstu
publikacji: https://www.researchgate.net/publication/311089078_Geoprocessing_of_High_Resolution_Imageries_for_Shoreline_Extraction_in_the_Process_of_the_Production_of_Inland_Electronic_Navigational_Charts

DOI: 10.1127/pfg/2016/0297

Tytuł: The Use of an Artificial Neural Network for a Sea Bottom Modelling

Autor/Autorzy: Jacek Łubczonek, Marta Włodarczyk-Sielicka

Miejsce
publikacji: Rozdział w książce

Rok: 2018

Słowa
kluczowe: Bathymetric data, Neural networks, Interpolation, Reduction, DTM, Big data

Abstrakt: Currently data are often acquired by using various remote sensing sensors and systems, which produce big data sets. One of important product are digital models of geographical surfaces that include the sea bottom surface. To improve their processing, visualization and management is often necessary reduction of data points. Paper presents research regarding the application of neural networks for bathymetric geodata reductions. Research take into consideration radial networks, single layer perceptron and self-organizing Kohonen network. During reconstructions of sea bottom model, results shows that neural network with less number of hidden neurons can replace original data set. While the Kohonen network can be used for clustering during reduction of big geodata. Practical implementation of neural network with creation of surface models and reduction of bathymetric data is presented.

Adres strony internetowej (link) do pełnego tekstu
publikacji: https://link.springer.com/content/pdf/10.1007%2F978-3-319-99972-2.pdf

DOI: 10.1007/978-3-319-99972-2_29

Tytuł: Application of Sentinel-1 imageries for shoreline extraction

Autor/Autorzy: Jacek Łubczonek

Miejsce
publikacji: Rozdział w książce

Rok: 2017

Słowa

kluczowe: radar, image, shoreline, extraction

Abstrakt: The shoreline is an important part of many cartographic materials. Given the geometric complexity and its length, it is important to use the methods of the automatic extraction. This can be done by using satellite radar imageries. The paper presents an analysis of the automatic shoreline extraction by using selected image processing methods. Extracted shoreline was also assessed in the aspect of the production process of the electronic navigational charts.

Adres strony internetowej (link) do pełnego tekstu
publikacji: http://ieeexplore.ieee.org/abstract/document/8008161/

DOI: 10.23919/IRS.2017.8008161

Tytuł: Location determination of radar sensors by using LIDAR data

Autor/Autorzy: Jacek Łubczonek

Miejsce
publikacji: Tekst popularnonaukowy, IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA

Rok: 2016

Słowa
kluczowe: GIS, Radar sensor, sensor network design, visibility analisis

Abstrakt: Radar sensor location planning is the first stage of sensor network designing. Observational sensors, i.e. radars, often need to perform spatial analyses to determine an effective surveillance of an area. Currently remote sensing sensors, like airborne LIDAR, are able to collect high density data of the Earth surface. In this paper is analysed application of LIDAR data for determination of radar sensor location.

Adres strony internetowej (link) do pełnego tekstu
publikacji: http://ieeexplore.ieee.org/document/7497289/

DOI: 10.1109/IRS

Tytuł: A New Approach to Geodata Storage and Processing Based on Neural Model of the Bathymetric Surface

Autor/Autorzy: Jacek Łubczonek, Mariusz Borawski

Miejsce
publikacji: Tekst popularnonaukowy, IEEE Computer Society Conference Publishing Services

Rok: 2016

Słowa
kluczowe: Marine navigation, Function approximation, Radial basis function networks, Sea floor

Abstrakt: Presently, bathymetric data in the navigational electronic charts are presented in the simplified form as points, lines and polygons. Such presentation of the data causes that the navigational chart contains blank spaces where is lack of bathymetric information. This work presents a new approach to the processing and storing of bathymetric data. It is based on the use of artificial neural networks, which allow for computation of bathymetric data in the entire domain of modelled bathymetric surface.

Adres strony internetowej (link) do pełnego tekstu
publikacji: http://ieeexplore.ieee.org/document/7547996/

DOI: 10.1109/BGC

Tytuł: Comparison of selected clustering algorithms of raw data obtained by interferometric methods using artificial neural networks

Autor/Autorzy: Marta Włodarczyk-Sielicka, Jacek Łubczonek, Andrzej Stateczny

Miejsce
publikacji: Tekst popularnonaukowy, IEEE Computer Society Conference Publishing Services

Rok: 2016

Słowa
kluczowe: bathymetry, interferometric system, artificial neural network, clustering algorithm

Abstrakt: The article presents a particular comparison of selected clustering algorithms of data obtained by interferometrie methods using artificial neural networks. For the purposes of the experiment original data from Szczecin Port have been tested. For collecting data authors used the interferometric sonar system GeoSwath Plus 250 kHz. GeoSwath Plus offers very efficient simultaneous swath bathymetry and side scan seabed mapping. During the use of Kohonen’s algorithm, the network, during learning, use the Winner Take All rule and Winner Take Most rule. The parameters of the tested algorithms were maintained at the level of default. During the research several populations were generated with number of clusters equal 9 for data gathered from the area of 100m2. In the subsequent step statistics were calculated and outcomes were shown as spatial visualization and in tabular form.

Adres strony internetowej (link) do pełnego tekstu
publikacji: http://ieeexplore.ieee.org/document/7497290/

DOI: 10.1109/IRS