|
|
Comparation of the Methods Generation of Tie Points in Aerotriangulation
Hromková, Zuzana ; Kalvoda, Petr (referee) ; Hanzl, Vlastimil (advisor)
The subjekt of this bachelor´s thesis is to compare the methods of generation of tie points in aerotriangulation using the program Photomod 4.3 made by Russian company Racurs. Part of this thesis is a detailed of description of the project initialization, subsequent implementation of aerotriangulation and bundle block adjustment in Photomod on those images. The result is a comparison of elements of exterior orientation. and coordinate determined points processed in tables and graphs.
|
|
|
Texture-Based Object Recognition
Hutárek, Jiří ; Šilhavá, Jana (referee) ; Španěl, Michal (advisor)
This thesis focuses on texture detection through the use of Local binary patterns (LBP). The LBP histogram extracted from the image is used as the texture feature and the image is classified by an artificial neural network. By using these methods, an universal texture detector is implemented, which is then specialized for the aerial image object recognition.
|
|
| |
|
|
Students' skills to use aerial and satellite images
Naiman, Petr ; Havelková, Lenka (advisor) ; Hanus, Martin (referee)
The thesis focuses on skills to use aerial and satellite images of students in lower-secondary schools and the corresponding years of grammar schools. The aim of the thesis is to compile an achievement test that will test all levels of skills for work with aerial and satellite images. In the first half of the thesis, readers are theoretically introduced to aerial and satellite images and skills for working with them. The literature review, which describes previous research in the field of skills for working with images, is followed by chapters dealing with the compilation of the achievement test and the subsequent pilot survey, which was conducted on 49 lower- scondary school students. Based on the analysis of the pilot survey, the properties of individual tasks were determined and the test was adjusted to the final form. Keywords: satellite images, aerial images, skills, achievement test, elementary school
|
|
|
Hodnocení změn krajiny v oblasti Jeseníků na základě historických a současných leteckých snímků
Bernadyová, Magdalena
The thesis focuses on the development of the foothills of the Hrubý Jeseník Mountains in the Bělá pod Pradědem municipality. It compares the situation in 1953 (1955) with that of 2018, based on aerial photographs. Manual vectorization created maps of land use, supplemented by the occurrence of line and solitary vegetation. Subsequent comparison evaluated that the forest and the built up area were expanded and the arable land was converted into grassland, which was connected with the reduction in the intensity of farming. The landscape has retained its foothill character with typical line and solitary vegetation. Subsequently, the automatic image classification (unsupervised and supervised) was used to create a land use map, its accuracy was evaluated and both methods were compared.
|
|
|
Texture-Based Object Recognition
Hutárek, Jiří ; Šilhavá, Jana (referee) ; Španěl, Michal (advisor)
This thesis focuses on texture detection through the use of Local binary patterns (LBP). The LBP histogram extracted from the image is used as the texture feature and the image is classified by an artificial neural network. By using these methods, an universal texture detector is implemented, which is then specialized for the aerial image object recognition.
|
|
|
Texture-Based Object Recognition
Hutárek, Jiří ; Švub, Miroslav (referee) ; Španěl, Michal (advisor)
Main subjects of this thesis are texture classification and texture-based object recognition. Various texture features are being explored, including several variants of local binary patterns (LBP). A novel modification of LBP (weighted spatial LBP) is proposed, with intention to improve on the spatial coverage of the traditional LBP. Rarely used color texture features are being discussed as well. Artificial neural networks and support vector machines are used to classify all the aforementioned features. Using these methods, framework for the texture classification and image segmentation is implemented. Comprehensive texture database is employed to test its performance under different conditions. In the end, the system is applied to solve a real-world problem - the segmentation of aerial photos.
|
|
|
Comparation of the Methods Generation of Tie Points in Aerotriangulation
Hromková, Zuzana ; Kalvoda, Petr (referee) ; Hanzl, Vlastimil (advisor)
The subjekt of this bachelor´s thesis is to compare the methods of generation of tie points in aerotriangulation using the program Photomod 4.3 made by Russian company Racurs. Part of this thesis is a detailed of description of the project initialization, subsequent implementation of aerotriangulation and bundle block adjustment in Photomod on those images. The result is a comparison of elements of exterior orientation. and coordinate determined points processed in tables and graphs.
|
|
|
Evaluation of tree crown detection with various spatial resolutions of aerial images
Miklas, Vojtěch
This work reviewed various tree detection and delineation algorithms and developed another one for ESRI ArcGIS Desktop software. This algorithm which employs the principles of local maxima filtering and region growing technique was enhanced by successfully applying NDVI index. Consequently, this algorithm was tested on 11 sample plots. These plots were located in the forest stand 187 C 10a (according to Forest Management Plan 2013 - 2022) in the forest section Proklest which belongs to the forest district Habrůvka in The Training Forest Enterprise Masaryk Forest Křtiny. The results were consequently, evaluated using these 6 different spatial resolutions: 10 cm, 20 cm, 40 cm, 60 cm, 80 cm and 100 cm. This evaluation was based on the comparison with manually vectorised 1,560 tree crowns. Spatial resolution of 40 cm provided the most accurate results for tree counting. At a standard deviation of 7.8 %, the accuracy reached 98 % of the reference layer. In the case of tree crown delineation, the most accurate results were provided for the spatial resolution of 80 cm. The accuracy reached 103 % with standard deviation of 9.6 %.
|
|
| |
guest ::
