|
|
Application for Insertion of Virtual Objects to Camera Shots
Popelka, Karel ; Milet, Tomáš (referee) ; Herout, Adam (advisor)
The aim of this project is to design an application for mobile platform which can insert virtual objects to camera shots without disturbing the scene. The application is implemented on Windows 8.1 and Windows Phone 8.1 platforms. The scene rendering is done in DirectX with C++ programming language and the user interface is created in XAML. This text describes the relevant fundamentals of augmented reality and the selected platform and it describes advanced programming techniques such as asynchronous resources loading or advanced post processing rendering techniques. The result of this project is a mobile application for inserting a virtual object with its shadow to camera shot. It is possible to set some aspects of the light and take a picture with the virtual object in high resolution.
|
|
|
System for Administration and Monitoring of Fishing Activities
Sedláčková, Lucie ; Herout, Adam (referee) ; Beran, Vítězslav (advisor)
The task of this thesis was to do researches based on information by potential users connected to fishing activities in Czech Republic. After researches finished design and implement system for administration of fishing activities. During the work on system was performed multiple iterations of user testing and in reaction to the tests was made some changes in the system. The system is developped using Nette Framework combine with Bootstrap library as responsive web application.
|
|
|
Fooling of Algorithms of Computer Vision
Hrabal, Matěj ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The goal of this work was to research existing methods of computer vision and computer recognition fooling. My focus was on group of methods called pixel attacks. Another part of my thesis talks about methods of detecting and fighting against computer vision fooling. Implementation of various pixel attack methods and methods of defending against these kinds of attacks was done using the python programming language and python library Keras. Solution that I have created works as standalone application allowing user to perform various pixel attack methods on chosen image. This tool also allows collection of statistics from performed pixel attacks and is able to detect possible attacks in these images.
|
|
|
Detection of Person in Image
Bednář, Luboš ; Mlích, Jozef (referee) ; Herout, Adam (advisor)
This work deals with detection of person in image. At the beginning, there are described some methods to be used for this type of detection. Of these we chose a method histograms of oriented gradients. For classification we use SVM. Part of this work is the design and implementation of a simple detector.
|
|
|
Analysis of Motion of People by a Stationary Camera
Smatana, Stanislav ; Juránková, Markéta (referee) ; Herout, Adam (advisor)
Hlavním cílem této práce bylo navrhnout a vytvořit systém sledování osob s aplikací v oboru bezpečnosti nebo pro analýzu chování zákazníka v obchodě. Systém byl úspěšně implementován pomocí metod KLT trekování, AdaBoost klasifikátoru a datové asociace pomocí Markovských řetězců a metody Monte Carlo. Implementace umožňuje analýzu pohybu lidí ve vnitřních i vnějších prostorech.
|
|
|
Mobile App for Logging of Automobile Costs
Mokrý, Martin ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
The goal of this thesis is to design and implement a mobile application for the recording of a car's consumption. The application is made for the Android operating system. It lets the user easily and effectively input new refuel data. Based on this data the application can show the user an overall view of their car's costs. This thesis focuses on the creation of this application, individual stages of design, implementation details and the testing of the application. It also states and analyzes similar existing applications.
|
|
|
Secure data transmition using bar codes
Kratochvíl, Martin ; Herout, Adam (referee) ; Beran, Vítězslav (advisor)
The goal of this thesis was to create a system for visual data transmition using bar codes. It focuses mainly on the protection of the system against abuse. A mechanism was designed for the data transmition itself and the various security concepts. The most appropriate bar code for data transmition was selected on the basis of the analysis.
|
|
|
Visualization Tool for Drone Pilot in Microsoft HoloLens 2
Kyjac, Martin ; Herout, Adam (referee) ; Bambušek, Daniel (advisor)
When piloting a drone, the pilot must monitor both the drone itself and various flight data. This activity requires constant concentration and even less inattention can lead to an accident. Especially when flying at greater distances, the pilot can very easily lose track of where the drone is located, which side it is heading to, or how high it is. To verify this information, it is necessary in common applications to tilt the head and thus lose sight of the drone because this data is located on the controller, which the pilot holds in his hands. This context switching is very impractical. The goal of this application is to visualize this data using augmented reality displayed through Microsoft Hololens 2. All necessary flight data is displayed using holograms at the exact same position where the drone itself is in the sky, so the pilot does not have to switch between contexts. It is also much easier to display various elements of the mission in this way. Normally in such cases, the pilot has to somehow interpret the data from the 2D map into reality, which can be challenging. However, with augmented reality, this data can be displayed directly into the real world.
|
|
|
Controlling Computer Using Gestures
Lacko, Peter ; Herout, Adam (referee) ; Juránek, Roman (advisor)
This work deals with creation of system for controlling computer through webcam with gestures. Gesture in this work can be viewed as hand motion forming some pattern. In the beginning are described methods for hand detection, hand tracking and pattern recognition. Afterwards comes description of system and it's implementation with tests evaluation. Outcome of this work is program for simple control of document viewer and multimedia player.
|
|
|
Facial image restoration
Bako, Matúš ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
In this thesis, I tackle the problem of facial image super-resolution using convolutional neural networks with focus on preserving identity. I propose a method consisting of DPNet architecture and training algorithm based on state-of-the-art super-resolution solutions. The model of DPNet architecture is trained on Flickr-Faces-HQ dataset, where I achieve SSIM value 0.856 while expanding the image to four times the size. Residual channel attention network, which is one of the best and latest architectures, achieves SSIM value 0.858. While training models using adversarial loss, I encountered problems with artifacts. I experiment with various methods trying to remove appearing artefacts, which weren't successful so far. To compare quality assessment with human perception, I acquired image sequences sorted by percieved quality. Results show, that quality of proposed neural network trained using absolute loss approaches state-of-the-art methods.
|
guest ::
