|
|
Evaluation of the land cover in the military training area Libavá using Random Forest classifier
Žďánský, Vít ; Štych, Přemysl (advisor) ; Laštovička, Josef (referee)
Data land cover help us understand nature, how it develops, its uses and the influence that human actions have on it. Thanks to new methods in the remote sensing area, we can record these processes faster and at a larger scale than before. This thesis evaluates accuracy of the Random Forest (RF) and Maximum Likelihood (ML) classifiers using satellite data Sentinel-2 from the military training area Libavá. The military area went through a very specific development and the information regarding natural coverage in the region is missing. The classifier documentation contains 8 classes. The classification results from both algorithms are higher than 80 %. As expected, more accurate results were achieved using the Random Forest classifier. The most accurate classifications were of water surfaces and forests. The least accurate classifications were of agricultural land and sparse vegetation. Other classes varied in accuracy levels. This thesis' results are evaluated using error matrices, overall accuracy and the kappa coefficient. Keywords: classification, Random Forest, Maximum Likelihood, military training area, remote sensing, Sentinel 2, land cover, Libavá
|
|
| |
|
|
Evaluation of area and changes of the agricultural land in Czechia 2006 - 2012
Hofrajtr, Martin ; Štych, Přemysl (advisor) ; Laštovička, Josef (referee)
Evaluation of area and changes of the agricultural land in Czechia 2006 - 2012 Abstract This thesis deals with the evaluation of area and changes of the agricultural land in selected regions in Czechia on the basis of the data from the years of 2006 and 2012, using the available international and national databases of land cover and land use. In the practical part, firstly the compatibility of classification systems of the surveyed databases is compared, then the state and changes of individual classes of agricultural land are analysed on two levels - national and regional - using functions of ArcGIS software. The overall result confirmed the assumption that the proportion of permanent grass cover in respect to agricultural land is increasing at the expense of that of arable land. Certain discrepancies between the results, however, point out different purposes of the surveyed databases and thus differences in their parameters and classification systems. Remote sensing, which enables to determine the real state of agricultural land and its classes, seems to be auspicious. Key words: change detection, agricultural land, CORINE Land Cover, Urban Atlas, land register - LPIS
|
|
|
Evalution of Time Series of Satellite Images to Observe Disturbancec in the Low Tatras
Laštovička, Josef ; Štych, Přemysl (advisor) ; Hais, Martin (referee)
The work is aimed at finding appropriate methods for observing changes in the status of forest vegetation and its evaluation in the years 1992-2015. The satellite images of the Low Tatras are analyzed by using Time Series technology. Specifically, the images Landsat 4, 5, 7 and 8, for which it is necessary to perform a calibration and an adjustment of input data values to realize the individual vegetation indices, due to the fact that the images are captured by different sensors with different radiometric resolution. From this perspective, the work deals with the possibilities of normalized relative radiometric corrections and search for a particular type of appropriate compensation for Landsat CDR images. Calibrated data sets are evaluated by Time Series of different vegetation indices. The resulting values are evaluated in relation with the occurrence of forest disturbances, eg. wind storms, biological and other pests. The final part is discussion of the results, evaluating the test methods of calibration and suitability of vegetation indices for observing the state of calamity. The App is created for generating the Time Series of Landsat images CDR and for preparing RRN datasets. Key words: Time Series, radiometric correction, atmospheric correction, Landsat CDR, vegetation indices,...
|
|
|
Technology of GIS in mobile equipment
Laštovička, Josef ; Štych, Přemysl (advisor) ; Čábelka, Miroslav (referee)
The aim of this work is to provide an overview of modern geoinformation systems operating on mobile technology platform. Selected technologies were evaluated by the students of elementary and secondary schools developed using test materials. In the introductory part of the paper briefly describes the current available technology smart phones and tablets focusing comparison platform iOS and Android. The second part of presents an overview of available geo-information software with a focus on free downloadable programs. The third part presents a critical evaluation of the functional parameters of the software. The following are the positive and negative aspects of the applications evaluated and compared to the available free downloadable programs with paid programs. The last part focuses on the possibility of integrating geo-information systems on the platform of smartphones and tablets in teaching primary and secondary schools. Their use in teaching could change students' view of current spatial information systems and could increase their popularity and practical use. Key words: Mobile GIS, smartphone, tablet, GPS, mobile operating systems, iOS and Android.
|
|
| |
guest ::
RSS feed.