|
|
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.
|
|
|
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.
|
|
|
Displaying Virtual Graphics and Animations for Sports Analysis
Očenáš, Daniel Miloslav ; Zemčík, Pavel (referee) ; Beran, Vítězslav (advisor)
The aim of this bachelor thesis is to create graphic tools used for the analysis of video recordings of sports events, especially football matches. The user can use the tools to highlight selected football players, which are further tracked and highlighted with three-dimensional objects rendered into video scene. Secondly, user can manually create pointed arrows representing player or football movement. Three-dimensional objects are created by perspective distortion corresponding with the scene taken by camera. The theoretical part focuses on the proper rendering of graphical objects into calibrated scene. The practical part focuses on implementation and visualization of mentioned tools by using OpenGL library.
|
|
|
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.
|
|
| |
|
|
Workstation with termo camera
Zeman, Martin ; Horák, Karel (referee) ; Richter, Miloslav (advisor)
This thesis contains an overview of physical principles concerning thermography and infra-red sensing, and a specification of a measuring instrument in a measurement system. Next, there are some particular examples of IR sensing applications. In the second part there is a thermal camera market research including individual manufacturers and models with their attributes and prices. There is a closer view of the thermal camera used for this thesis (Guide EasIR-4). In the end of the thesis there are some drafts of computer vision subject tasks (or practices), including workplace designs and solutions, and three task suggestions for bachelor or diploma theses including solution verifications.
|
|
|
Scene Analysis Based on the 2D Images
Hejtmánek, Martin ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This thesis deals with an object surface analysis in a simple scene represented by two-dimensional raster image. It summarizes the most common methods used within this branch of information technology and explains both their advantages and drawbacks. It introduces the design of an surface profile analysis algorithm based on the lighting analysis using knowledge and experiences from previous work. It contains a detailed description of the implemented algorithm and discusses the experimental results. It also brings up options for the possible enhancement of the projected algorithm.
|
|
|
System for Recognition of 3D Hand Geometry
Svoboda, Jan ; Mráček, Štěpán (referee) ; Drahanský, Martin (advisor)
V posledním desetiletí došlo ke zvýšení zájmu o užití 3D dat k biometrické identifikaci osob. Možná vůbec největší výzkum proběhl v oblasti 3D rozpoznávání podle obličeje, přičemž je v současné době dostupných vícero komerčních zařízení. V oblastni rozpoznávání podle 3D geometrie ruky byl v minulých letech proveden určitý výzkum jehož výsledkem však nebylo žádné komerční zařízení. Nezávisle na tomto výzkumu se v posledních letech velmi rozšířil trh s cenově dostupnými 3D sensory, což potenciálně umožňuje jejich nasazení v mnoha typech biometrických systémů. Hlavním cílem této práce je vytvořit funkční vzorek bezdotykového systému pro rozpoznávání osob podle 3D geometrie ruky, který bude používat novou levnou kameru RealSense 3D vyvíjenou v současné době firmou Intel. Jedním z problémů při použití RealSense kamery je její velmi malý form factor, který je příčinou nižší kvality výsledných snímků v porovnání s velmi drahými alternativami, které byly použity v již dříve zmíněném výzkumu 3D biometrických systémů. Práce se snaží analyzovat robustnost různých 2D a 3D příznaků a vyzkoušet několik různých přístupů k jejich fúzi. Rovněž je vyhodnocena výkonnost výsledného systému, kde je ukázáno, že navržené řešení dosahuje výsledků porovnatelných se state-of-the-art.
|
|
|
Hough's transform for circle detection
Kazík, Martin ; Burget, Radim (referee) ; Říha, Kamil (advisor)
The thesis is focused on the implementation of Hough transform algorithm for circle recognition. Algorithm is implemented in C++ language using open source library OpenCv. As a development environment was chosen Microsoft Visual Studio 2008. At first there is general description of classical Hough transform for line and circle recognition. Then thesis contains description of particular steps of Hough transform algorithm and description of OpenCv functions witch are used in these steps. There is a detail description of functions for converting image to grayscale, smoothing image by Gaussian filter and Canny edge detector for edge detecting in smoothed image. Efficiency and speed of algorithm is increased by using function for finding possible centers. This function using the fact that line perpendicular to the chord of circle and going thought its middle point at the same time have to cross the center of the circle. Results of particular stages of algorithm (converting to grayscale, smoothing by Gaussian filter, edge detection, creating of possible centers accumulator and drawing circles) are presented on ultrasonic image of collagen arterial substitute. In the second part of the thesis the algorithm is used for detection of artery in frames of video captured by ultrasound. There is a description of automatic method for evaluating of success of artery detection. Success of detection is analyzed by changing values of important algorithm parameters. From series of tests there are defined ideal parameters of algorithm for artery detection in the video.
|
|
|
Longtime Video
Kubiš, Matěj ; Beran, Vítězslav (referee) ; Herout, Adam (advisor)
This thesis includes the creation of a graphic user interface for the management of a set of photographies, its navigation, playback and subsequent export into videoformat. It studies the problems of timelapse video and deals with the implementation of algorithms concerning the removal of undesirable effects rising during the process of its creation. To be specific, it processes the interpolation of fluctuating levels of brightness in the sequence and the stabilization of image sequences acquired without a tripod.
|
guest ::
