|
| |
|
|
Analysis of the celestial maps
Považan, Juraj ; Bayer, Tomáš (advisor) ; Čábelka, Miroslav (referee)
Analysis of the spheric map Abstract The master thesis deals with cartometric analysis of maps of the celestial sphere using image correlation. The main goal of this work was to design an algorithm for the identification of stars on old maps of the starry sky using a normalized cross-correlation and the application of a median and Gaussian filter. The analysis itself takes place on small scale maps or. the whole visible sky divided into two hemispheres, shown in a stereographic projection and also takes into account the influence of the cartographic map display on the position of objects, which it tries to eliminate by Helmert transformation, and also the influence of precession, which affects the position of astronomical objects over time. The accuracy of the drawing of the positions of the objects is evaluated by means of isolines drawn on the basis of positional coordinates. The algorithm was implemented in the Matlab programming environment and old maps from the Mapová sbírka PřF and the 5th edition of Bright Star Cataloque were used as test data, which contains the positions of stars with precisely determined coordinates. The achieved results are presented in the form of images of captured objects and created isolines over old maps as well as tables of the three nearest neighbors of the most important...
|
|
|
Automatic detection of zebra crossings from aerial images
Tomíček, Jiří ; Potůčková, Markéta (advisor) ; Fiala, Radek (referee)
There are a number of studies that deal with detection of road network from image Remote Sensing data. However, little work has been done on algorithms for horizontal road signs detection from Remote Sensing data. On the other hand there are many papers that deal with horizontal road signs detection in the field of Computer vision. Theoretical part of master thesis sumarizes the methods that are used to detect objects from both, Remote Sensing and Computer vision data. In the practical part an algorithm of automatic Zebra-crossing detection based on Aerial Images and vector road layer is designed. Zebra-crossings are detected using matching of image with set of predefined patterns. Obtained set of potential objects is then filtred using geometric and relational criteria. At the end of this thesis, the proposed algorithm is validated and the results are discussed with literature. Key words: Zebra-crossing, Horizontal road signs, Image matching, Aerial images
|
|
| |
guest ::
