|
|
Augmented Reality on iOS - Displaying of Map Features in Terrain
Bezák, Adam ; Brejcha, Jan (referee) ; Herout, Adam (advisor)
This thesis aims to improve the user's orientation in terrain using his smartphone and augmented reality. By combining these two elements and cost-free OpenStreetMap database of geographic data, is possible to show nearby map features from the maps or show additional information about nearby objects. The resulting technology is used in implemented iOS application called Water Radar. This application displays nearby water streams (or other water objects) relative to the GPS position of the user. The application also uses Google Elevation API, in order to enable displayed water streams to follow the landscape.
|
|
|
Augmented Reality for Commercials
Angelov, Michael ; Herout, Adam (referee) ; Beran, Vítězslav (advisor)
Master's thesis presents a possible application of augmented reality in domain of commerci- als. It presents designed architecture of a mobile application that is able to detect and track specific objects (e.g. printed commercials, logos) in mobile';s phone camera in real time and provide some extra information about the detected object towards the user. Thesis also provides a review of contemporary used techniques in object recognition, object tracking and image retrieval from image databases.
|
|
|
Detection of Traffic Signs and Lights
Chocholatý, Tomáš ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The thesis focuses on traffic sign detection and traffic lights detection in view with utilization convolution neural network. The goal is create suitable detector for detection and classification traffic sign in real traffic. For training of convolution neural network were created appropriate datasets, that contains synthetic and real dataset. For synthetic dataset was create generator, that can simulated different deformation of traffic signs. Evaluation is done by own program for quantitative evaluation. The detection rate successfully detected signs is 89\% over own test dataset. The results allow to find out importance of representation real or synthetic dataset in training dataset and influence individual deformations synthetic dataset for final detection quality.
|
|
|
Analysis of 3D CT image data aimed at segmentation of bone elements and other specific tissue types
Kodym, Oldřich ; Herout, Adam (referee) ; Jan, Jiří (advisor)
The goal of this thesis is to get acquainted with methods of determining bone mineral density from appropriate tissue types in diagnostic CT data and possibly modifying or extending them in order to make the bone quality diagnosis more reliable. The thesis begins by introducing the issue of determining bone quality. Next, a method that takes cortical bone deformations into account as well as bone mineral density is introduced. Accuracy assessment based on opinion of a medical expert suggests positive outcome of future objective accuracy assessment utilizing so far unavailable base of calibrated CT data, that is needed before deployment into clinical practice. If the accuracy of the suggested method is confirmed this way, this work provides a so far absent tool for fully automatic preventive diagnostics of osteoporosis.
|
|
|
Implementation of Simple Speech Recognizer in Android
Flajšingr, Petr ; Herout, Adam (referee) ; Szőke, Igor (advisor)
The subject of this thesis is an implementation and optimization of speech recognizer for operating system Android. This work covers implementation of recording of an audio signal and the subsequent feature extraction using Mel filter banks and neural network. It also contains information about implementation of dynamic decoder. The work focuses on implementation in low-level tools such as Android NDK and Renderscript and evaluates the success rate of the recognizer and its memory and time requirements.
|
|
|
Viewing Large Raster Geodata Online
Mikita, Martin ; Španěl, Michal (referee) ; Herout, Adam (advisor)
This thesis describes the design of a multi-platform client-server application to access large raster data, existing and proposed ways to optimize the running speed and processing raster. The advantage of the application is an updated version of GDAL for reading most known raster format, and implementing extension for reading GeoPDF with open-source PDF rendering library. Integrating created and optimized server component into the open-source project IIPImage improves it to support more raster formats.
|
|
|
Chatbot for Smart Cities
Jusko, Ján ; Herout, Adam (referee) ; Zemčík, Pavel (advisor)
The aim of this work is to simplify access to information for citizens of the city of Brno and at the same time to innovate the way of communication between the citizen and his city. The problem is solved by creating a conversational agent - chatbot Kroko. Using artificial intelligence and a Czech language analyzer, the agent is able to understand and respond to a certain set of textual, natural language queries. The agent is available on the Messenger platform and has a knowledge base that includes data provided by the city council. After conducting an extensive user testing on a total of 76 citizens of the city, it turned out that up to 97\% of respondents like the idea of a city-oriented chatbot and can imagine using it regularly. The main finding of this work is that the general public can easily adopt and effectively use a chatbot. The results of this work motivate further development of practical applications of conversational agents.
|
|
|
Distributed Ray Tracing
Slovák, Radek ; Jošth, Radovan (referee) ; Herout, Adam (advisor)
This project describes method for global display of distributed ray tracing. The method generates high quality and realistic two-dimensional images from mathematical specification of scene. The methods for solution of this issue are presented and analyzed. Integral part of this method - conventional ray tracing - is also presented.
|
|
|
Deep Learning for Virtual Patient-Specific Skull Modelling and Reconstruction
Kodym, Oldřich ; Kozubek, Michal (referee) ; Egger, Bernhard (referee) ; Herout, Adam (advisor)
Segmentace lebky ze 3D pacientských dat a virtuální rekonstrukce tvaru lebek s defekty jsou nejnáročnějšími kroky potřebnými pro tvorbu lebečních modelů na míru pacienta. Tyto modely jsou v kranioplastice využívány pro plánování operací, poučení pacienta a design implantátů na míru, avšak jejich využitelnost je v současnosti limitována množstvím manuální práce potřebné pro dosažení dostatečné kvality virtuálních modelů. Tato teze má za cíl zefektivnění tohoto virtuálního pracovního postupu s využitím metod hlubokého učení. Teze popisuje klinickou motivaci a současnou výzkumnou literaturu v oblasti automatizace virtuální kranioplastiky. Dále navrhuje nové řešení sestávajicí z metody automatické segmentace lebky založené na kombinaci konvoluční neuronové sítě a algoritmu graph-cut a metody automatické rekonstrukce lebky založené na kaskádě konvolučních sítí. Obě tyto komponenty demonstrují přesnost na úrovni vědeckého stavu poznání. Dále tato práce cílí na zvýšení reprodukovatelnosti výzkumu lebečních rekonstrukcí poskytnutím strukturovaného syntetického datasetu pro vývoj a srovnávání automatických metod. Hlavním cílem této práce je využitelnost v klinické praxi. Zatímco navržená metoda segmentace lebek je již v klinické praxi využívána, integrace automatické virtuální rekonstrukce lebky představuje několik dalších překážek, jako nízká tolerance k nepřesnostem ve tvaru okolo hranice defektu. Tato práce proto také navrhuje rozšíření metody rekonstrukce lebky, které umožňuje její adaptaci na cílovou populaci a typ kraniálních implantátů, který se může mezi jednotlivými klinickými pracovištěmi lišit. Výsledky vyhodnocení experta ukazují, že výstupy této metody dosahují dostatečné kvality pro implementaci do klinické praxe společně s metodou segmentace.
|
|
|
Multimedia Data Processing in Heterogeneous Distributed Environment
Kajan, Rudolf ; Ferko,, Andrej (referee) ; Míkovec, Zdeněk (referee) ; Herout, Adam (advisor)
Pervasive computing sa zameriava odstránenie zložitostí pri interakcii s výpočtovou technikou a zvýšenie efektivity pri jej každodennom používaní. Ale i po viac ako 15 rokoch od sformulovania hlavných cieľov Pervasive computingu existujú aspekty interakcie ktoré stále nie sú súčasťou užívateľskej skúsenosti s dnešnou technológiou. Bezproblémová integrácia s prostredím vedúca k technologickej neviditeľnosti, alebo interakcia naprieč rôznymi zariadeniami predstavujú stále veľkú výzvu. Hlavným cieľom tejto práce je prispieť k tomu, aby sa ciele Pervasive computingu priblížili k realizovaniu tým, že predstavíme spôsob intuitívneho zdieľania informácií medzi osobným a verejne umiestneným zariadením. Predstavili sme tri interakčné techniky, ktoré podporujú intuitívnu výmenu obsahu medzi osobným zariadením a zdieľaným displejom. Tieto techniky sú založené na prenose videa, rozšírenej realite a analýze pohľadových dát. Okrem interakčných techník sme tiež predstavili mechanizmus pre získavanie, prenos a rekonštrukciu aplikačného stavu na cieľovom zariadení.
|
guest ::
