|
|
Classification of Norway Spruce based on imaging and laboratory spectroscopy
Soudková, Kristýna ; Potůčková, Markéta (advisor) ; Kupková, Lucie (referee)
The master thesis deals with subpixel classification of hyperspectral data from senzor APEX. In the first part there is research from the literature describing algorithms of the subpixel classifications and spectral characteristics of the vegetation. In the practical part there is a work focusing on the classification of the areas with the cover of Norway Spruce trees at eight areas in the Krkonoše national park. Three methods of supervised classification were used - Linear Spectral Unmixing, Support Vector Machine and Spectral Angle Mapper. Field data, spectral curves for exact trees from the eight areas obtained by the contact probe ASD FieldSpec 4 Wide-Res, were used for the extraction of endmembers of the spruces. For each research area maps of land cover were produced by means of the classification methods described above and the accuracies of the classifications were evaluated. Powered by TCPDF (www.tcpdf.org)
|
|
|
Evaluation of Land Cover Changes Using the Object Detections
Skokanová, Eliška ; Štych, Přemysl (advisor) ; Kupková, Lucie (referee)
The aim of the project is to perform object based change detection of land cover in specific areas of Czech republic. Landsat 2000 and Spot 2006 satellite images are used as input data. The method used for evaluation of changes is Multivariate Alteration Detection unsupervised method which is based on statistical procedures and is available from e-Cognition software. The results of detection are compared with Corine Land Cover changes database to evaluate degree of parity on detected areas. Different mapping unit is used to be able to detect smaller changes than Corine database. First part of the work is review of literature sources aimed on processing of satellite images, description of the spectral behavior of landscape objects, origins of Corine Land Cover database and principle of change detection using MAD. Second part deals with data adjustment, change detection process and comparison of reached results with Corine. Keywords: object based change detection, satellite images, Corine Land Cover, mapping unit of changes, Multivariate Alteration Detection, e-Cognition
|
|
|
Classification of selected agricultural crops from time series of Sentinel-2 and PlanetScope imagery in Kutnohorsko model area
Kuthan, Tomáš ; Kupková, Lucie (advisor) ; Potůčková, Markéta (referee)
Classification of selected agricultural crops from time series of Sentinel-2 and PlanetScope imagery in Kutnohorsko model area Abstract The thesis is focused on the analysis of spectral characteristics of selected agricultural crops druring agriculutural season from time series of Sentinel -2 (A and B) and PlanetScope sensors in the model area situated around the settlements of Kolín and Kutná Hora. It is based on the assumption that the use of multiple dates of image data acquired crops in different phenological phases of the crops allows better identification of crop species (Lu et al., 2004). The aim of the thesis was to analyse the characteristics of the seasonal course of spectral features of selected agricultural crops (sugar beet, spring barley, winter barley, maize, spring wheat, winter wheat, winter rape) and to determine the period of the year suitable for the differentiation of individual crops. Another aim of the thesis was to classify these crops in the model area from time series of two above-mentioned sensors and to compare the accuracy of the pixel and object-oriented classification approach for multitemporal composites and the accuracy for monotemporal image from the term when the individual crops are clearly distinguishable. The training and validation datasets and the classification mask...
|
|
|
Evaluation of landscape changes in the Krkonoše Mountains national park using remote sensing and landscape metrics
Karvánek, Matouš ; Kupková, Lucie (advisor) ; Štych, Přemysl (referee)
The aim of this bachelor thesis was to analyse of land cover and landscape state in the Krkonoše Mountains National Park between 1999 and 2007, using supervised classification and landscape metrics calculation. After the classification (Maximum likelihood algorithm) based on legend with 8 categories (5 types of vegetation, arable land, water areas, other areas), overlay analysis was performed by change detection and map sof land cover state and changes were created. The changes of the landscape and landscape components state were evaluated using landscpae metrics in software Fragstats. The overall accuracy for the image from 1999 was 81,50% and for the image from 2007 83,25%. Based on results i tis possible to conclude, that the area of forests increased and as fr the species composition the share of deciduous forests increased during this time period. Shift to a less diverse landscape was recorded based on landscape metrics evaluation. Coniferous forests comprised the landscape matrix in 1999 and also in 2007. Key words: supervised classification, land cover, landscape metrics, SPOT, FRAGSTATS, The Krkonoše Mountains National Park
|
|
|
Mapping of terrain relics of the extinct village of Palohlavy (Ralsko) using early maps and airborne laserscanning data
Turek, Matěj ; Lysák, Jakub (advisor) ; Kupková, Lucie (referee)
Bachelor thesis deals with mapping of extinct villages using old maps, orthophotos and ALS. Specifically, it focuses on the village of Palohlavy in the former MTA Ralsko. At this location, the methodology of mapping extinct villages in this military area was tested. In the course of the work, the collection and evaluation of available data sources, field measurements, proposal and fulfillment of digidal spatial database and map creation, took place. The spatial database contains elements to determine their time existence.
|
|
|
Evaluation of suburbanization process in the hinterland of Prague in the period 1990-2020 using remote sensing data
Brabec, Michal ; Kupková, Lucie (advisor) ; Štych, Přemysl (referee)
Significant changes have taken place in the hinterland of Prague in recent years. The villages, where 200 people used to live, are now large residential areas with an old core and a much larger population. The high increase in population and the new built-up area will also be reflected in the surrounding landscape, either by deforestation of the remaining forest areas or by the degradation of the highest quality soils. The aim of this work was to describe the course of suburbanization of selected municipalities and the associated change in landscape cover using data from remote sensing (RS), statistical data and field survey in the issue. At the same time, identify tools that to some extent, guide or regulate these suburbanization processes. The first part of the work is an introduction to the issue, followed by a chapter on standard regulatory measures in Czech Republic. Furthermore, the data and methods of remote sensing are described, which were used to develop a map output of the areas and last but not least, the agricultural land fund (ZPF) was analyzed focusing on the quality of soils in the monitored area. The main goal of the work was to find out and show the development of a selected background of Prague in the years 1990 to 2020. The results can be used as a basis for an even more...
|
|
| |
|
|
Classification of UAV hyperspectral images using deep learning methods
Řádová, Martina ; Potůčková, Markéta (advisor) ; Kupková, Lucie (referee)
Diploma thesis "Classification of UAV hyperspectral images using deep learning methods" focuses on the classification methods, namely convolutional neural networks (CNN), of hyperspectral (HS) images. Based on a thorough literature review, a comprehensive overview on CNN utilisation in remote sensing is assembled as a basis for identifying suitable methods for the specific task of this thesis. Two methods with an open solution in programming language Python were selected - Capsule Network and U-Net. The main aim of this work is to verify the suitability of chosen methods for the classification of hyperspestral images. The images were acquired by sensors with high spatial resolution carried by a UAV over Krkonoše Mts. tundra. Important step was to prepare input HS data (54 bands, 9cm) to have suitable form for entering the network. Not all the required results were achieved due to the complexity of the Capsule Network architecture. The U-Net method was used in purpose of comparing and verifying the results. Accuracies retrieved from the U-Net overcome results achieved by traditionally used machine learning methods (SVM, ML, RF, etc). Overall accuracy for U-Net was higher than 90% where other mentioned methods did not get over 88%. Especially classes block fields and dwarf pine achieved higher...
|
|
|
Use of laboratory and image spectroscopy to evaluate drought resistance of Scots pine and to distinguish its ecotypes
Raasch, Filip ; Kupková, Lucie (advisor) ; Potůčková, Markéta (referee)
The aim of this study was to propose a non-destructive method for measuring Pinus sylvestris seedlings, to determine whether water stress would be evident in laboratory spectra of pines, to compare whether the response of pines would differ by ecotype, and to investigate whether two ecotypes of Pinus sylvestris could be distinguished using laboratory and image spectroscopy. For these purposes, hyperspectral images of seed orchards from August 2020 were processed and a three-month laboratory experiment was conducted, in which stress from water deficit was induced in two-year-old pine seedlings from the upland and hilly ecotypes. Spectral data were analysed using mixed statistical models, analysis of variance, principal component analysis, training of supervised pixel classifiers, vegetation indices, and linear regression. Based on the analyses, it was found that water stress can be detected in severely stressed Pinus sylvestris seedlings. The most sensitive spectral bands to water content were observed in the region between 1000-2500 nm. The initial response to water stress did not differ by ecotype, but a faster recovery was observed at the upland ecotype after the period of draught. The two Pinus sylvestris ecotypes were distinguished with high accuracy from both laboratory and image spectral...
|
|
|
LOST LANDSCAPES OF CENTRAL BOHEMIA: EVALUATION OF CHANGES IN LAND USE AND LANSCAPE STRUCTURE
Mór, Jiří ; Kupková, Lucie (advisor) ; Štych, Přemysl (referee)
This thesis deals with land use and land cover changes in two geographically close areas - - "Milovicko" and "Rožďalovicko". The thesis's main goal was to analyze land use / land cover changes between years 1836 and 2019 in the surroundings of Milovice town, where the military area called "Milovice - Mladá" was established in 1904 and dissolved in 1991, and in intensively-used agricultural area around small town Rožďalovice. The evaluation was mainly based on vectorized maps of so called Stable cadastre and on the data of current cadastre. Another goal was to analyze the development of landscape structure in surroundings of Rožďalovice, also between years 1836 and 2019. We aimed also to answer the question, if parcels of arable land in the stable cadastre could be considered as patches in the landscape mosaic. Based on three types of satellite data (PlanetScope, Sentinel-2 and Landsat 8) it was analyzed, how much landscape metrics and a description of landscape structure change in dependency on spatial resolution of remote sensing data. Satellite images from June 2019 were classified and then the landscape metrics, which characterized landscape structure, were calculated. Development of land use in Milovice surroundings differs from the trends of development of other (post)military areas as classes...
|
guest ::
RSS feed.