|
|
Retargeting of the assembler language compiler
Navrátil, Jan ; Macho, Tomáš (referee) ; Petyovský, Petr (advisor)
This bachelor thesis describes a design and implementation of modification of retargetable compiler Flat Assembler G that provides a translation of assembly language for HCS08 microprocessor family. It describes current solutions in the design of assembly language compilers, existing retargetable compilers and their differences from Flat Assembler G. Furthermore, it shows process that can generate binary output in selected format with the compiler. Last part of this thesis is dedicated to testing of the correctness of the implementation and demonstration of the correctness on a real hardware.
|
|
|
Objects Classification in Images
Gabriel, Petr ; Petyovský, Petr (referee) ; Janáková, Ilona (advisor)
This master's thesis deal with problems of classification objects on the basis of atributes get from images. This thesis pertain to a branch of computer vision. Describe possible instruments of classification (e.g. neural networks, decision tree, etc.). Essential part is description objects by means of atributes. They are imputs to classifier. Practical part of this thesis deal with classification of object collection, which can be usually found at home (e.g. scissors, compact disc, sticky, etc.). Analyzed image is preprocessed , segmented by thresholding in HSV color map. Then defects caused by a segmentation are reconstructed by morfological operations. After are determined atribute values, which are imputs to classifier. Classifier has form of decision tree.
|
|
|
Image processing library wrapper for Lua
Prymus, Jiří ; Dusíková, Hana (referee) ; Petyovský, Petr (advisor)
The thesis deals with OpenCV library and its implementation into scripting language Lua. The first part of the thesis concentrates on description of the course Computer vision MPOV and description of mathematical basics needed for further understandings. The second part describes OpenCV library and its potential usage in the MPOV. Next chapter examines the programming scripting language Lua. The description of the implementation of binding the OpenCV library to Lua language along with its overall functionality is included in the practical part of the thesis. The use of LuaCV is more comfortable thanks to Open Source projects for cross-platform compilation and distribution. Part of the thesis is also generator of Latex documentation for LuaCV binding. The last chapter deals with testing LuaCV in course MPOV and analysis of criticism from students.
|
|
|
Automated optical measurement of drops contact angle
Dugáček, Ján ; Richter, Miloslav (referee) ; Petyovský, Petr (advisor)
Measurement of surface tension of solids usually requires manual processing of photographs of droplets of liquids with known properties on the measured material's surface, during which the contact angle is manually determined. The objective of this work is to implement an algorithm that can determine these contact angles from photographs and does not require the photographs to be made under specific light conditions. The implementation cannot depend on paid libraries and must be simple to incorporate into existing software.
|
|
|
Optimal Deployment of Multiple Hypotheses Generators for Detecting Traffic Lights in Camera Images
Bajus, Tomáš ; Richter, Miloslav (referee) ; Petyovský, Petr (advisor)
Táto práca sa zaoberá detekciou semafórov na snímkoch z kamery. Cieľom je nájsť vhodné nastavenie a kombináciu dostupných detektorov. V prvej časti práce je vysvetlený princíp funkcie použitých detektorov. Nasleduje zhodnotenie vlastností jednotlivých detektorov pred ich optimalizáciou. V ďalšej časti práce je popísaný proces testovania a evaluácie detektorov a predstavený nový systém pre zefektívnenie hľadania optimálneho nastavenia detektorov. V rámci optimizácie je popísaný effekt jednotlivých parametrov na chovanie systému a sú navrhnuté rozpätia vhodných hodnôt pre každý parameter. Taktiež je predstavené nové zapojenie detektorov sú nájdené optimálne pracovné body systému. Posledná časť sa zaoberá použitím vhodných metód na filtorvanie a zhlukovanie hypotéz. Nakoniec je prezentovaná celková funkčnosť systému pred a po optimizácii a výsledky sú zhodnotené.
|
|
|
Enhanced mathematical library for C++
Temel, Aleš ; Macho, Tomáš (referee) ; Petyovský, Petr (advisor)
I create a library for storing matrices and working with matrices in this bachelor’s thesis. In this case, the issues concern mainly so-called sparse matrices. C++ do not provide among the standard libraries tools for easy working with sparse matrices. The most frequent alternative is the application of two-dimensional array (2D array). 2D array may be realized as a double pointer representing the rows and the columns of the matrix. The basic problem is that behavior of 2D array is identical both to the sparse, and to the full non-zero matrix. 2D array ignores the possibility to store matrices more favorable. The library for storing matrices designed by me takes into account the storing of sparse matrices by several different ways. It offers the sparse format CSR (Compressed sparse rows), as well as alternatives to save the specially structured matrices. In the course of creating library the main emphasis first of all I put on the amount of memory that is necessary for storing matrices. Because it is a mathematical library, it contains different functions suitable for working with matrices, such as determinant calculation, inverse matrix calculation and so. When calculate these functions it is necessary to take into account used memory size as well. Intermediate results are stored also in sparse format, and removed as soon as possible after their use. I created also the second library that deals with the floating point numbers stored with greater precision than standard data types like float and double. The size of occupied memory increases according to precision of floating point number.
|
|
|
Mobile robot in smart house
Kuparowitz, Tomáš ; Burian, František (referee) ; Petyovský, Petr (advisor)
Aim of this thesis is to search the market for suitable autonomous robot to be used by smart house. The research in this work is partly done on the range of abilities of smart houses in matter of sensor systems, ability of data processing and their use by mobile robots. The output of this thesis is robotics application written using Microsoft Robotics Developer Studio (C#) and simulated using Visual Simulation Environment. Main feature of this robotic application is the interface between robot and smart house, and robot and user. This interface enables employer to directly control robot's movement or to use automated pathfinding. The robot is able to navigate in dynamic environment and to register, interact and eventually forget temporary obstacles.
|
|
|
3D model
Sládeček, Martin ; Petyovský, Petr (referee) ; Richter, Miloslav (advisor)
This paper concerns the task three-dimensional scene using image sequence obtained with an ordinry camera. First portion of this thesis outlines the principles used in solving of the task, the second chapter describes a reconstucion algorithm and it's implementation in the Python programming language. The output of this program is demonstrated on several selected scenes. Final remarks discuss the quality of resulting models, shortcomings of the program and possible improvements.
|
|
|
Universal measurement interface for digital audio signal
Gál, Marek ; Macho, Tomáš (referee) ; Petyovský, Petr (advisor)
This master’s thesis deals with a modification of existing project which is used as a helpful tool for tracking and measuring digital audio interface I2S. The original design was created by Ing. Martin Stejskal, Polymorphic USB – I2S Interface. Modifications are based on practical one year experience when the device was tested and deals with new requirements for extension. This work describes and justify individual changes of hardware and software part of project.
|
|
|
Unary Classification of Image Data
Beneš, Jiří ; Petyovský, Petr (referee) ; Horák, Karel (advisor)
The work deals with an introduction to classification algorithms. It then divides classifiers into unary, binary and multi-class and describes the different types of classifiers. The work compares individual classifiers and their areas of use. For unary classifiers, practical examples and a list of used architectures are given in the work. The work contains a chapter focused on the comparison of the effects of hyperparameters on the quality of unary classification for individual architectures. Part of the submission is a practical example of implementation of the unary classifier.
|
guest ::
