|
|
Image Completion Using Depth Maps
Valeš, Ondřej ; Brejcha, Jan (referee) ; Čadík, Martin (advisor)
The aim of this thesis is to design and implement aplication for dataset driven scene completion utilizing data from similar dataset images and test the posibility of generating data used in reconstruction directly from depth map. For scene matching in dataset novel modification of GIST descriptor including depth data is used. Furthermore, depth maps can be used to split reconstructed image into parts with similar depth, simplifying reconstruction process. Part of this thesis is also computing GIST descriptors for datset images and implementation of tools for searching datset for similar images using depth maps.
|
|
|
object matching
Mišta, Petr ; Petyovský, Petr (referee) ; Richter, Miloslav (advisor)
Detection of objects based on color is not commonly used method of computer vision. There are many methods thats deals with the detection of significant points, but the color information has been omitted. The goal of this thesis is to design method of the detection significant color image areas and these areas match up with areas detected in another image. I analyzed features of detectors required to identify the reciprocal correspondence of images, defined the color significance concept, described basic color models and their properties, and a design of statistically compiled data - based method was described. Algorithms for the detection of color use color models RGB and HSV. Correspondence of areas detected in different images is performedy Kohonen neural network. The first input vector can teach Kohonen neural network and the second vector is classified by this network. To remove erroneous classifications RANSAC method is used. As a result, the method can be used for basic and rapid determination of correspondence between images, or to speed up commonly used methods for detection of significant points. At the end of the thesis are presented programs, showing functionality and options of design methods. The designed algorithms have been developed in MATLAB.
|
|
|
Determination of an area and proportions of selected objects in a picture
Mittner, Ondřej ; Stančík,, Petr (referee) ; Říčný, Václav (advisor)
The master’s thesis describes hardware opto-electronic instruments for contactless measurement of surfaces. It concentrates on instruments used for opto-electrical transformation of a taking scene and software processing of digital pictures. It presents selected methods of pre-processing, segmenting and following final modifications of these pictures. Then it deals with measuring of areas of surfaces and sizes of selected objects in these pictures and conversion of results from pixels to SI system of units. Possible divergences of measuring are described as well. A flow chart of a program for automatic and manual measuring of surfaces and sizes of objects in a picture, which is commented in detail, is a part of the thesis. The main product of this thesis is application Merovo, which provides measuring of an area and proportions of included objects. This application is analysed and described in detail in this thesis.
|
|
|
Free algebraic structures and their application for segmentation of a digital image
Čambalová, Kateřina ; Solovjovs, Sergejs (referee) ; Pavlík, Jan (advisor)
The thesis covers methods for image segmentation. Fuzzy segmentation is based on the thresholding method. This is generalized to accept multiple criteria. The whole process is mathematically based on the free algebra theory. Free distributive lattice is created from poset of elements based on image properties and the lattice members are represented by terms used by the threshoding. Possible segmentation results compose the equivalence classes distribution. The thesis also contains description of resulting algorithms and methods for their optimization. Also the method of area subtracting is introduced.
|
|
|
Target tracking
Černín, Jan ; Horák, Karel (referee) ; Janáková, Ilona (advisor)
The subject of this bachelor thesis was to program an algorithm, which would be able to process image data from connected camera. Real-time application is working with data in basic of evaluated position of the object and control robotic head that turns and follows selected target. Whole algorithm implements two methods of tracking which are written in program language C/C++ using functions of OpenCV library.
|
|
|
Smoke and Fire Detection in Video Sequences
Tomek, Peter ; Štancl, Vít (referee) ; Švub, Miroslav (advisor)
This thesis aims to analyse a videosignal given in input and find segments that contains fire or smoke. The problem is divided into two cases-detection of fire and detection of smoke. The first and main step of analysation is detection of segments by Gaussian mixture model that is trained by Expectation-Maximization algorithm, or shortly EM algorithm. For smoke detection is than used method of optical flow. The final segments are than processed by some morphological methods and determination of their position is made. Finally, the output of algorithm is again a videosignal in which segments that probably contains fire or smoke are highlighted.
|
|
|
Non-Photorealistic Rendering
Žilák, Jaroslav ; Bartoň, Radek (referee) ; Žák, Pavel (advisor)
The main purpose of this thesis besides providing the reader with basics of non-photorealistic rendering, is concept and possible solution for system realization, which is capable of this rendering using image post-processing. This thesis describes solution that is sufficiently flexible to support use of integrated filters along with the creation of new ones that can be recursively used to create another filters for this type of rendering. Thus part of this thesis is some kind of manual which provide basic syntax description and possibilities of use.
|
|
|
The idnetification of the objects in the imege
Zavalina, Viktoriia ; Fliegel, Karel (referee) ; Boleček, Libor (advisor)
Master´s thesis deals with methods of objects detection in the image. It contains theoretical, practical and experimental parts. Theoretical part describes image representation, the preprocessing image methods, and methods of detection and identification of objects. The practical part contains a description of the created programs and algorithms which were used in the programs. Application was created in MATLAB. The application offers intuitive graphical user interface and three different methods for the detection and identification of objects in an image. The experimental part contains a test results for an implemented program.
|
|
| |
|
|
Image quality analysis using Fourier transform
Tkadlecová, Markéta ; Druckmüller, Miloslav (referee) ; Hoderová, Jana (advisor)
This thesis deals with two-dimensional Fourier transform and its use in digital image quality assessment. An algorithm based on amplitude spectra is introduced and tested on different sets of images. Its possible use and disadvantages are described. For understanding the basics of the algorithm the fundamental mathematical theory is included. Mainly the properties of amplitude spectra are explained. Next, the theory of digital images and their characteristics, which can affect their quality, is described. For testing the quality of the image the demonstrative program has been developed.
|
guest ::
