|
|
Approximation surfaces for 3D data
Valachová, Alžbeta ; Novák, Jiří (referee) ; Procházková, Jana (advisor)
This bachelor thesis is dealing with approximation surfaces for 3D data using methods such as RANSAC, least square method and B-spline surface. Its goal is to study and program these methods. First, the methods are described and then the actual programs are analysed. In the end of the thesis, we compare all three methods using data from 3D scanning. Through this effort we can assess their positives and negatives.
|
|
|
3D data presentation
Matyskiewicz, Jiří ; Petyovský, Petr (referee) ; Richter, Miloslav (advisor)
Thesis deals with manipulation, archiving and viewing of 3D data. Theoretic part contains basic introduction to the field. Practical part of the thesis is design and implementation of the library for viewing 3D data and viewer / editor using this library. Library is written in c++ computer language and it’s intended to be used as a dynamic linked library, which functionality can be easily enhanced with additional plug-in modules without need to modify the source code of the library. Actual viewing is not tied to any specific type of graphical API, library can be extended with plug-in for rendering using any software or hardware. Part of the implementation is plug-in for rendering 3D data using OpenGL interface.
|
|
|
3D data
Klusáček, Jan ; Janáková, Ilona (referee) ; Richter, Miloslav (advisor)
The goal of this thesis is to design methods for acquisition of three dimensional model of object using illumination by laser streak which is read by camera. The first part describes theoretical principle and points out some problems which are linked to this method. Followed by description of interfaces which can be used for acquisition of image from camera. Next part is focused on more detailed description of DirectShow interface which is used in this thesis. Description of concrete methods designated for processing acquired image, calibration and composition of three dimensional model are also topics of this work. The Last part describes device which was created to verificate and automatize designed methods.
|
|
|
Artificial neural networks and their application for 3D-data processing
Pihera, Josef ; Mrázová, Iveta (advisor) ; Holan, Tomáš (referee)
Neural networks represent a powerful means capable of processing various multi-media data. Two applications of artificial neural networks to 3D surface models are examined in this thesis - detection of significant features in 3D data and model classification. The theoretical review of existing self-organizing neural networks is presented and followed by description of feed-forward neural networks and convolutional neural networks (CNN). A novel modification of existing model - N-dimensional convolutional neural networks (ND- CNN) - is introduced. The proposed ND-CNN model is enhanced by an existing technique for enforced knowledge representation. The developed theoretical methods are assessed on supporting experiments with scanned 3D face models. The first experiment focuses on automatic detection of significant facial features while the second experiment performs classification of the models by their gender using the CNN and ND-CNN.
|
|
|
Approximation surfaces for 3D data
Valachová, Alžbeta ; Novák, Jiří (referee) ; Procházková, Jana (advisor)
This bachelor thesis is dealing with approximation surfaces for 3D data using methods such as RANSAC, least square method and B-spline surface. Its goal is to study and program these methods. First, the methods are described and then the actual programs are analysed. In the end of the thesis, we compare all three methods using data from 3D scanning. Through this effort we can assess their positives and negatives.
|
|
|
Artificial neural networks and their application for 3D-data processing
Pihera, Josef ; Mrázová, Iveta (advisor) ; Holan, Tomáš (referee)
Neural networks represent a powerful means capable of processing various multi-media data. Two applications of artificial neural networks to 3D surface models are examined in this thesis - detection of significant features in 3D data and model classification. The theoretical review of existing self-organizing neural networks is presented and followed by description of feed-forward neural networks and convolutional neural networks (CNN). A novel modification of existing model - N-dimensional convolutional neural networks (ND- CNN) - is introduced. The proposed ND-CNN model is enhanced by an existing technique for enforced knowledge representation. The developed theoretical methods are assessed on supporting experiments with scanned 3D face models. The first experiment focuses on automatic detection of significant facial features while the second experiment performs classification of the models by their gender using the CNN and ND-CNN.
|
|
|
3D data
Klusáček, Jan ; Janáková, Ilona (referee) ; Richter, Miloslav (advisor)
The goal of this thesis is to design methods for acquisition of three dimensional model of object using illumination by laser streak which is read by camera. The first part describes theoretical principle and points out some problems which are linked to this method. Followed by description of interfaces which can be used for acquisition of image from camera. Next part is focused on more detailed description of DirectShow interface which is used in this thesis. Description of concrete methods designated for processing acquired image, calibration and composition of three dimensional model are also topics of this work. The Last part describes device which was created to verificate and automatize designed methods.
|
|
|
3D data presentation
Matyskiewicz, Jiří ; Petyovský, Petr (referee) ; Richter, Miloslav (advisor)
Thesis deals with manipulation, archiving and viewing of 3D data. Theoretic part contains basic introduction to the field. Practical part of the thesis is design and implementation of the library for viewing 3D data and viewer / editor using this library. Library is written in c++ computer language and it’s intended to be used as a dynamic linked library, which functionality can be easily enhanced with additional plug-in modules without need to modify the source code of the library. Actual viewing is not tied to any specific type of graphical API, library can be extended with plug-in for rendering using any software or hardware. Part of the implementation is plug-in for rendering 3D data using OpenGL interface.
|
guest ::
