|
|
Detection of Weapons in 2D Image
Demčák, Ján ; Spurný, Martin (referee) ; Drahanský, Martin (advisor)
This bachelor thesis deals with detection of weapons in 2D image. In the theoretical part of the thesis the term weapon was defined and the possibilities of detection of weapons in image with using classic methods and deep neural networks were mentioned there. The key steps of image processing, objects classification and detection were described. The overview of frameworks, libraries was presented. To implement the pratical part of the thesis, 3 models were chosen. The first classic model with using HOG transformation. The second CNN model with priority target detection accuracy and with two different neural network architectures as classifiers. The third model with YOLO network architecture had as priority target real-time detection. The essential part of each model was choice, or more precisely creating suitable dataset. What followed was the construction and implementation of models and the evaluation of obtained data.
|
|
|
Traffic Light Detection in Image
Boček, Václav ; Jirsík, Václav (referee) ; Horák, Karel (advisor)
This bachelor thesis deals with the traffic lights detection and recognition of the displayed colour using methods of machine learning. In the theoretical section, different methods to solve this problem are described. The practical part describes the proposed system which was realized using convolutional neural networks. Furthermore, results of performed tests are shown.
|
|
|
Image similarity measuring using deep learning
Štarha, Dominik ; Šeda, Pavel (referee) ; Rajnoha, Martin (advisor)
This master´s thesis deals with the reseach of technologies using deep learning method, being able to use when processing image data. Specific focus of the work is to evaluate the suitability and effectiveness of deep learning when comparing two image input data. The first – theoretical – part consists of the introduction to neural networks and deep learning. Also, it contains a description of available methods, their benefits and principles, used for processing image data. The second - practical - part of the thesis contains a proposal a appropriate model of Siamese networks to solve the problem of comparing two input image data and evaluating their similarity. The output of this work is an evaluation of several possible model configurations and highlighting the best-performing model parameters.
|
|
|
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.
|
|
|
Creation of a publication plan in the field of science and research
Smetana, Tomáš ; Chlapek, Dušan (advisor) ; Kučera, Jan (referee)
This thesis focuses on the topic of open data, especially in the field of science and research. The work is defined by six sub-targets and characterize the area of science and research in the Czech Republic and abroad, to characterize the issue of open data in the Czech Republic and in the world, describe the method of publication of data on the promotion of science and research in the Czech Republic and in the world, how to propose a procedure and create publications plan for TA CR, prepare a sample dataset, and then evaluate the procedure used. The work is divided into thematic blocks, which are based on these goals. It consists of an introduction, theoretical part, practical part and conclusion. The introductory section defines the objectives of work and research resources devoted to similar topics. The theoretical part describes the problems of science and the problem of open data in the Czech Republic and other countries, and also the process of creating publication plan according to the chosen methodology. The practical part contains according to the targets two parts, one is the analysis of open data of science and research and other preparation publication plan TA CR. The practical part ends with evaluation of procedure used with proposals for improvement. The conclusion contains a summary of the work and evaluate the goals achieved.
|
|
|
Data journalism aimed by Datablog IHNED.cz
Hrbková, Nikola ; Láb, Filip (advisor) ; Kasík, Pavel (referee)
Now when information is abundant, practice of Data Journalism is quickly becoming a core technique of the 21st century newsrooms. The diploma thesis "Data Journalism aimed by Datablog IHNED.cz" is focused on introducing Data Journalism as a genre responding to the changes in the society and the technology development. The theoretical part concerns with the history of the subject, the workflow of Data Journalism in the newsrooms and the limitations; such as inappropriate business models, difficult process of collecting data or the lack of training. The main goal of the research is to map the work of the Czech data team in the IHNED.cz and compare the results with the work of teams in Australia. The research methods are combination of quantitative and qualitative analyses. The main source of information are interviews conducted with data journalists from the Czech Republic and Australia. On top of that the research gives deeper understanding of how the integration of data journalists in the newsrooms affect the way journalism can support the existence of media organizations and contribute to the public good. The last part offers predictions of the future of Data Journalism.
|
|
|
Evaluating of data sources and land use changes in Prague and surroundings
Šmausová, Barbora ; Štych, Přemysl (advisor) ; Janoušek, Zbyněk (referee)
The aim of this study was to compare the data sets used in land use / land cover in terms of their content and analyze their classification systems. The work is focused on the capital city of Prague and its surroundings. The data used are described and characterized. Review was made for available data sets on a general level, especially focusing on their classification systems. For further work was chosen model area containing four cadastral (Čestlice, Křeslice, Průhonice, Újezd u Průhonic). In the model area was made analysis of data, which focused on a comparison of classification systems using spatial overlays, status and map of changes. The resulting synthesis was carried out on the basis of a general review and analysis carried out for the model area. The results of the work answer to the fundamental objectives of the work and try to describe the basic knowledge of the different and identical parameters of studied data sets. Powered by TCPDF (www.tcpdf.org)
|
|
|
Web Search Engine
Tamáš, Miroslav ; Galamboš, Leo (advisor) ; Skopal, Tomáš (referee)
Academic fulltext search engine Egothor has recently became starting point of several thesis aimed on searching. Until now, there was no solution available to provide robust set of web content processing tools. This master thesis is aiming on design and implementation of distributed search system working primary with internet sources. We analyze first generation components for processing of web content and summarize their primary features. We use those features to propose architecture of distributed web search engine. We aim mainly to phases of data fetching, processing and indexing. We also describe final implementation of such system and propose few ideas for future extensions.
|
|
|
Computer Application Control by Natural Head Movement
Vojvoda, Jakub ; Materna, Zdeněk (referee) ; Beran, Vítězslav (advisor)
The aim of this work is to design and implement a system that tracks user's head in the input video frames and on the basis of its position achieves interaction with computer applications. Four methods for head detection have been proposed based on computer vision techniques as face detection by Haar-like features, background detection, Camshift or Lucas-Kanade to calculate an optical flow. The individual methods have been tested on recorded and in this field used data sets, and evaluated. The implementation of the system was then used to build the demo applications.
|
|
|
Software Support for Projects Management
Janda, Petr ; Kreslíková, Jitka (referee) ; Květoňová, Šárka (advisor)
This project describes design and implementation of project management information system support, mainly for IT organizations. It includes informations about basic facts in project management and mainly about Rational Unified Process, the modern metodology which is well usefull in today changeable environment. System is implemented in Microsoft Visual Studio 2005 with support of Microsoft SQL Server 2005 and consists of ASP.NET presentation and of DLL library written in C# language. Information system provides support for project planing and management. System work in standard internet browsers and is very usefull for geografically devided teams.
|
guest ::
