|
|
Visual Camera Orientation Estimation using Machine Learning
Kubička, Martin ; Polášek, Tomáš (referee) ; Čadík, Martin (advisor)
Účel tejto práce je vytvoriť model pomocou sférických konvolučných neuronových sietí, ktorý vie odhadnúť orientáciu kamery z dvoch vstupov, kde prvým vstupom je panoráma a druhým vstupom je fotka, ktorá zachytáva určitú časť panorámy. Inými slovami, úlohou je nájsť kde v panoráme, ktorá tvorí prvý vstup, sa nachádza fotka, ktorá tvorí druhý vstup. Mimo troch vytvorených modelov, ktoré riešia daný problém, vzniklo aj 6 nových datasetov, ktoré rozširujú momentálne dostupný počet datasetov, ktorých fotky sú v equirectangulárnom alebo stereografickom formáte
|
|
|
Bayesian approaches to adaptive system identification
Skalský, Ondřej ; ,, Straka Ondřej (referee) ; Dokoupil, Jakub (advisor)
The paper deals with Bayesian identification of time variant normal regression models and provides four key algorithms. The first two algorithms are designed for the online regularized identification of a single regression model. Absence of the time evolution model is solved in both algorithmizations by a data-informed forgetting technique. The choice of the forgetting factor in the first algorithm is performed using Variational Bayesian approximation. The second algorithm determines the value of the forgetting factor by statistical decision making. The second pair of algorithms treats the problem of time evolution of parameters as a sequence of switching normal regression models. In both of these offline algorithms which are based on the Variational Bayesian approximation, both the inference of the bank of model parameters and the activities of these models over the time of the experiment are iteratively performed. The actual number of models forming this bank is determined automatically. The difference between these algorithms lies mainly in the noise properties of the switched models. All four algorithms are tested on a real system and in simulations. The paper is complemented by a short introduction to the Bayesian world, which presents the essential statistical techniques that are used. For completeness and continuity with the aforementioned algorithms, the offline and online identification of a time invariant normal regression model is also described.
|
|
|
Probabilistic Localization of Mobile Robot
Kopečný, Tomáš ; Luža, Radim (referee) ; Rozman, Jaroslav (advisor)
Motion control, navigation and sense of orientation of a mobile robot are tied to development of every mobile robot. This work concerns mainly about robot localization in the sense of orientation in space. Nevertheless, nor other aspects of mobile robotics are being omitted. Therefore, the goal of this work is to get familiar with Monte Carlo localization algorithm and apply this algorithm on a real robot.
|
|
|
Effective random number generator for limited devices
Michálek, Tomáš ; Mlýnek, Petr (referee) ; Fujdiak, Radek (advisor)
This thesis solves the problem of generating random numbers on low-power devices. Author describes possible ways of generating and implements selected generators of (pseudo)random numbers on MSP430F5438A. 4 generators were added by the enhancement of one of them and a new generator was created, using the phenomenon of temperature change in the surroundings. For each generator, test sequences were generated and these sequences were tested by the Dieharder, STS-NIST, and Visual Test. The output of the thesis is the functional implementation of the generators, their testing by statistical methods and their comparison between each other.
|
|
|
Risk Management inside Construction Company
Fujaszová, Petra ; Vašíček, Petr (referee) ; Nováková, Jana (advisor)
The thesis aims to describe risk management in the construction company focusing primarily on project risks. The first half of the work deals with the theoretical description and explanation of the terms associated with the project, risk and risk management in construction companies. After the theoretical introduction follows a demonstration on the practical example, namely JAMU - musical drama laboratory, Brno realized by Unistav Construction Inc.
|
|
| |
|
|
Detection of Vehicles in Image
Špaňhel, Jakub ; Juránek, Roman (referee) ; Herout, Adam (advisor)
This thesis aims to implement the vehicle detection and tracking method based on the motion model suitable for real-time processing. The first part includes analysis of the commonly used methods. The second part introduces principles of implemented method. This method consists of low-level features extraction, the spatiotemporal profiling of extracted features and image intensities, and classification of obtained traces based on HMM. Subsequently experiments using this trustworthy method are conducted to locate areas of potential method improvements.
|
|
|
The Betting Agent
Bělohlávek, Jiří ; Rozman, Jaroslav (referee) ; Grulich, Lukáš (advisor)
This master thesis deals with design and implementation of betting agent. It covers issues such as theoretical background of an online betting, probability and statistics. In its first part it is focused on data mining and explains the principle of knowledge mining form data warehouses and certain methods suitable for different types of tasks. Second, it is concerned with neural networks and algorithm of back-propagation. All the findings are demonstrated on and supported by graphs and histograms of data analysis, made via SAS Enterprise Miner program. In conclusion, the thesis summarizes all the results and offers specific methods of extension of the agent.
|
|
|
Creating a knowledge base for the diagnosing of diseases
Macháček, Daniel ; Steinerová, Kateřina (referee) ; Jirsík, Václav (advisor)
This bachelor thesis is focused on problematic of creation knowledge base. It is describing basics of expert systems, their function and possible usage in modern world. In result of this thesis is knowlenge base in web aplication NPS able to diagnose diseases of hematology-oncology and that is proving possibility for use in real life. Knowledge base was created in cooperation with experts in the medical field and contains real data.
|
|
|
Risk Management inside Construction Company
Resl, Jan ; Chval, Petr (referee) ; Nováková, Jana (advisor)
The aim of the thesis is to analyse issues of risk management in a construction company, especially in the context of construction contracts implementation. The first part is devoted to applied terminology and interpretation of relevant terms, followed by a classification of risks from different perspectives, including the risks’ possible further sub classification. Furthermore, significant risk resources and construction participants who might be affected by the risks are presented. The third chapter deals with risk management; individual phases of this complex process are described herein, including their correct sequences, as well as a selection of methods and techniques that are standardly used in risk management. The last, fourth chapter summarises the problems of risk management on a practical example, where a construction company implements a construction contract by applying selected risk management methodologies.
|
guest ::
