|
|
Remote sensing for classification of new wilderness vegetation in the hinterland of Kutná Hora
Dančejová, Daniela ; Kupková, Lucie (advisor) ; Červená, Lucie (referee)
Numerous areas in the Czech landscape have been abandoned by human activity, allowing natural processes to take over. Some of these areas have transformed into new wilderness characterized by diverse vegetation compositions, representing va- rious successional stages. The aim of this work is to conduct a comprehensive and accurate classification of vegetation in the new wilderness area utilizing remote sensing techniques. For this purpose, multispectral UAS data with a 5 cm spatial resolution, hyperspectral aerial data with a 60 cm spatial resolution, and botani- cal data collected at three different dates within the area of interest were used. Based on the collected data and the assessment of species separability, three clas- sification legends were proposed to classify the area of interest using Maximum Likelihood, Random Forest and object-based classifiers. The F1-score was used to assess the classification accuracy of vegetation classes. The results demonstrated the suitability of the object classifier for classifying a highly diverse vegetational area at a very high spatial resolution (achieving the highest overall accuracy of 84.06% across 22 classes). The Random Forest classifier yielded better results for vegetation classification on hyperspectral data with a lower spatial resolution...
|
|
|
CRISM sensor - available data and possible applications for mineral detection on Mars
Pavlová, Martina ; Červená, Lucie (advisor) ; Potůčková, Markéta (referee)
This bachelor's thesis focuses on data accumulated by the Compact Reconnaissance Imaging Spectrometer for Mars (CRISM) sensor and the possibilities of their subsequent processing. The first part of this paper focuses on the history of remote sensing of Mars since its beginning in the 1960s, with the most detailed description of the Mars Reconnaissance Orbiter (MRO) mission which carries the CRISM spectroradiometer. The nine different data products acquired by this instrument are described in detail together with the possibilities of their download and subsequent processing. Furthermore, the minerals found on the surface of Mars are mentioned and examples of their spectral curves are shown. In the practical part, the processing of CRISM data in JCAT is first presented, from the actual data download to the creation of spectral curves suitable for comparison with spectral libraries. Subsequently, an image containing low calcium pyroxene was selected. This image was preprocessed in CAT in ENVI and using three different methods which were Linear Spectral Unmixing (LSU), Spectral Angle Mapper (SAM) and spectral parameter calculation, the detection of the selected mineral was performed. The LSU and SAM methods gave similar results, but the calculation of spectral parameters differed more from them, which...
|
|
|
Remote Sensing of the Icy Moons of Jupiter - Galileo mission
Tomášková, Eliška ; Červená, Lucie (advisor) ; Potůčková, Markéta (referee)
The bachelor's thesis focuses on the processing and analysis of Galileo SSI and NIMS image data, which captures the Tyre region of Europa and the Kittu region of Ganymede. Initially, the problems of data retrieval from the PDS archive and its thorough radiometric and geometric corrections are addressed. Pre-processing, visualization, and subsequent data analysis were conducted using the POW tool, ISIS3, ENVI, and ArcGIS Pro software. Based on the principal component analysis of the NIMS data, the two most different end-members representing ice and "salt" were selected. These were then used in Linear Spectral Unmixing, which provided information on the spatial distribution and relative concentrations of the "salt" end-member in the study areas. The outputs from the hyperspectral data were projected over the higher spatial resolution data to examine relationships between surface morphology and composition. The resulting SSI, Voyager, and NIMS composites suggest a strong correlation between the salt component and areas with disrupted ice crust on Jupiter's icy moons. Furthermore, unsupervised classification of SSI images capturing the Tyre crater was performed and showed similar results to Linear Spectral Unmixing of the NIMS data. Additionally, significant differences in reflectance values between...
|
|
|
Use of UAV hyperspectral data for training of classifications of data with lower spectral and spatial resolution on the example of vegetation classifications in the Krkonoše tundra.
Šašková, Marie ; Červená, Lucie (advisor) ; Hrázský, Záboj (referee)
Use of UAV hyperspectral data for training of classifications of data with lower spectral and spatial resolution on the example of vegetation classifications in the Krkonoše tundra Abstract The thesis focuses on the problem of supervised classification of the Krkonoše tundra with a limited amount of training data. UAV hyperspectral data of 100×100 m2 area on Luční hora from 2020 and 2021 with spatial resolution of 9 cm and 54 spectral bands were classified using Maximum Likelihood, Support Vector Machine, Object Oriented Classification and Random Forest algorithms. The defined legend contained 9 classes: Avenella flexuosa, Avenella flexuosa with high cover of other species, Vaccinium myrtillus, Deschampsia cespitosa, Pinus mugo, Nardus stricta, blosckfields, Calluna vulgaris, mosaic of rocks, bare soil, mosses and vegetation. The results of these classifications were compared based on their overlaps. The overlays of the multitemporal composite classifications, which achieve higher overall accuracies, are used to find more training data. The wider area of Luční hora was classified based on CASI hyperspectral aerial data with a spatial resolution of 60 cm and 48 spectral bands. The original training dataset designed for the classification of the smaller area and new training datasets extended with additional...
|
|
|
Liability for defects of a share or shares of stock
Červená, Lucie ; Čech, Petr (advisor) ; Eichlerová, Kateřina (referee)
Liability for defects of a share or shares of stock ABSTRACT This diploma thesis deals with the analysis of legal and contractual liability for defects of a share or shares of stock and with the definition of its qualities focusing on the legislation of the purchase. Due to the fact, that the number of executed transactions concerning a share or shares of stock reaches several hundred per year in the Czech Republic and the Czech legal system deals with the legislation of the share purchase agreement marginally, the number of disputes arises regarding their defects and the transferor's liability for them in practice. Therefore, I consider the topic of liability for defects of a share or shares of stock as a topical issue and appropriate to more detailed elaboration. Several research questions were asked e.g.: if a share of shares of stock can have the usual qualities or the usual purpose of use; if the qualities of the enterprise can be also the qualities of a share or shares of stocks directly by law; or if a shareholder of the business corporation can be considered as a consumer. In some issues that are controversial in legal theory or are not solved, or only marginally in the Czech legal system, a comparison with foreign legal doctrine, especially German and Austrian, is used to find solutions. Following...
|
|
|
Analysis of important grass species distribution in the Krkonoše Mts. tundra using remote sensing
Ježek, Vít ; Kupková, Lucie (advisor) ; Červená, Lucie (referee)
Analysis of important grass species distribution in the Krkonoše Mts. tundra using remote sensing Abstract The aim of this thesis was to test the application of maximum likelihood classification, Random forest, Support vector machine and object-oriented classification with the Support vector machine classifier on selected areas in the Krkonoše Mts. relict arctic-alpine tundra for the purpose of mapping the distribution of vegetation with a focus on conservation-important grass species. The research used pre-processed multitemporal hyperspectral data and multispectral data from UAS with a spatial resolution of 0.03 m and 0.06 m and hyperspectral aerial data with a spatial resolution of 0.6 m together with training and validation data collected by botanists directly from the fields using GPS (all data are from 2019-2021). The classifications achieved excellent results. The best overall accuracies were achieved by the object-oriented classification, with accuracies ranging between 80-95 %. Similarly, good results were also achieved by pixel methods - Random forest and Support vector machine (highest overall accuracy 94 %). Of the important grass species, Calamagrostis villosa (producer's accuracy 99.73 %, user's accuracy 99.95 %) and Deschampsia cespitosa (producer's accuracy 99.98 %, user's accuracy 99.33 %)...
|
|
|
Subpixel approach for vegetation classification from hyperspectral and multispectral data in the Krkonoše Mts. tundra
Růžička, Josef ; Kupková, Lucie (advisor) ; Červená, Lucie (referee)
This diploma thesis focuses on the possibilities and potential of using subpixel-based classification methods for hyperspectral and multispectral data capturing selected localities of the tundra in the Krkonoše Mountains, specifically the Bílá louka meadow and Luční hora mountain areas. The thesis presents current methods for collecting and using endmembers as well as methods for the classification itself using the spectral unmixing approach, mainly in connection with the classification of heterogeneous vegetation communities. In the practical part of the thesis, various methods of collecting end members are used, especially the extraction of end member spectra directly from image data using manual, semi-automatic and automatic methods. Envi, EnMAP-Box 3 and MATLAB software are used for collection and subsequent classification. Endmembers collected in different ways are then combined with different classification methods in an attempt to achieve the most accurate result possible, which would be at the level of controlled pixel-based classification. The classification took place on two legend levels. Detailed, classifying individual plant species and less detailed, where species are aggregated into larger groups. The best results were achieved by the classification of the Bílá louka meadow...
|
|
|
Determination of chlorophyll content in selected grass communities of Krkonoše tundra based on field spectroscopy and aerial hyperspectral data
Pinlová, Gabriela ; Červená, Lucie (advisor) ; Lhotáková, Zuzana (referee)
The thesis focuses on the determination of chlorophyll content from hyperspectral data in grass communities in the arctic-alpine tundra in the Krkonoše Mountains, namely Nardus stricta, Molinia caerulea, Calamagrostis villosa, and Deschampsia cespitosa. Leaf chlorophyll content (LCC) was measured using two methods - spectrophotometric destructive determination in the laboratory, and the LCC assessed non-destructively by fluorescence portable chlorophyll meter CCM-300. Leaf area index (LAI) values for canopy chlorophyll content (CCC) retrieval were also acquired by destructive biomass sampling and indirectly using LAI-2200C. Relationships were established between the LCCs, LAI, CCCs, and vegetation indices (VI) calculated from respective spectra, i.e. leaf level spectra acquired with contact probe coupled with an ASD FieldSpec4 Wide-Res spectroradiometer, canopy level spectra measured by the spectroradiometer and extracted from hyperspectral images (HSI) acquired by Headwall Nano- Hyperspec® mounted on the DJI Matrice 600 Pro drone. Chlorophyll content maps were created based on the results of multiple stepwise linear regression applied to HSI. For the model, derived from the non-destructive data sampling and used for the LCC map, a RMSE of 66.55 mg/m2 was achieved. Keywords: leaf chlorophyll...
|
|
| |
|
|
Land cover changes in District Nachod using remote sensing data
Červená, Lucie ; Štych, Přemysl (advisor) ; Kupková, Lucie (referee)
Land cover changes in District Nachod using remote sensing data Abstract The purpose of this project was to create a classification of the land cover of Náchod district for years 1979, 1991 and 2001 based on multi-spectral images gained from publicly available archive images database provided by Landsat satellites. Data used in this paper are described in details. The created classification system is based on CORINE Land Cover and adjusted to a measured area and data available. The method used for images classification was method of supervised classification in PCI Geomatics program and classification algorithm of Maximum Likelihood Classification. The result was smoothed by majority filter and converted to the vector form. Accuracy of the classification was evaluated in details, based on the check points. Overall accuracy was quite low (2001 - 82 %, 1991 - 74 %, 1979 - 67 %), depending on the quality (mainly spectral and spatial resolution) of the images and also availability of other reference data. Land cover changes for the whole time period were therefore evaluated using just the balance method (i.e. overall classes distributions in district were compared between separate years). For years 1991 and 2001 it was also tried to overlap their final vector land cover layouts, however target Change areas in...
|
guest ::
RSS feed.