|
|
Tracking of Military Objects in a Videosignal
Hamada, Ondřej ; Váňa, Jan (referee) ; Orság, Filip (advisor)
First part of this thesis briefly describes the main problems of object tracking in video and methods to deal with them. Main attention is paid towards usage of these methods for target tracking in videos taken by both normal and thermal camera. It propose solution to this problem based on the kernel-based method which uses mean-shift algorhitm and on the template matching. Both tracking methods results are supervised and corrected by Kalman filter. Proposed solution is implemented using C++ with OpenCV library.
|
|
|
Descriptor for Identification of a Person by the Face
Coufal, Tomáš ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Thesis provides an overview and discussion of current findings in the field of biometrics. In particular, it focuses on facial recognition subject. Special attention is payed to convolutional neural networks and capsule networks. Thesis then lists current approaches and state-of-the-art implementations. Based on these findings it provides insight into engineering a very own solution based of CapsNet architecture. Moreover, thesis discussed advantages and capabilitied of capsule neural networks for identification of a person by its face.
|
|
|
Map Generator and Path Search in a Map for the Strategy Games
Karásek, Štěpán ; Mráček, Štěpán (referee) ; Orság, Filip (advisor)
This thesis consists of two parts. The first part deals with procedural map generation aiming at terrain generation. For the most part, the bases of terrain generation, usable algorithms and the ways of generating other landscape elements are followed up. A terrain generator using diamond-square algorithm is then implemented and integrated into the existing game engine. The second part of the thesis analyses the pathfinding problem, describes usable algorithms and one of them in detail. Furthemore, the post-processing of the path is being solved and possibilities of hierarchical pathfinding algorithms are presented. Pathfinding using A* algorithm is also implemented and integrated into existing game engine. Finally, functioanality of both the algorithms is demonstrated in an interactive application.
|
|
|
Software for the Spectroscopy Method LIBS
Vyroubalová, Jana ; Mráček, Štěpán (referee) ; Orság, Filip (advisor)
This thesis discusses creating of software for the LIBS spectroscopy method (for an electronic chamber). In the first part the reader will learn about the LIBS method and about a short description of a workplace, where the project is being created. Then I write about an application design for laboratories, which are going to use this method. Next I describe an implementation of software, where the reader can find some details about used algorithms for autofocus (an evaluation of image sharpness and an iterative determination of the position of the camera). The end of this work is focused on the assessment of GUI and testing the application.
|
|
|
Face Features Extraction Methods
Adamček, Ľubomír ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
The face has been one of the most attractive available human biometries for a long time due to it's easy and convenient way to obtain it. Possibilities of it's utilization are broad - from security, through monitoring up to enternainment industry. This work presents the domain of face biometry and analyses 3 extraction methods of facial features - PCA, LBP and HOG. A part of this work is also an efficient implementation of these algorithms including GUI designed to experiment with this implementation and to evaluate its performance on a set of images capturing people in various conditions.
|
|
|
Design of a Mobile Robotic Platform
Kolář, Vít ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This thesis focuses on a design of a mobile robotic platform for an autonomous grass-reaping machine controlled by wireless connected computer. There is some information about the creation and objects of this project in the beginning and than the reader is made familiar with two autonoumous grass-reaping machines that are already on the market. The main chapter describes all the robots subsystems such as senzory, motoric and control subsystem. The issue of power supply and navigation is also mentioned. All these parts are beeing described both theoretically and from the point of autonomous grass-reaping machine as well.
|
|
|
Design of a Body and Sensor System of a Robot
Marvan, Aleš ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This thesis deals with a problematic of mobile robot design. There is proposed a design and realization of a mobile robot intended for an international competition - Minisumo. The first step in the development process is collecting of information, which helps us to find the most suitable elements. The next step is choosing of the individual elements fulfilling the design requirements according to their specification.
|
|
|
Experiments with Images of Eye Retina
Floryček, Jan ; Orság, Filip (referee) ; Fiala, Jiří (advisor)
The layout of blood vessels in human eye retina is one of the important physiological biometric characteristics of every individual. The processing of color retinal images and extraction of the blood vessel structure is an important phase in diagnostics of many eye diseases as well as in gathering biometric data. An automatic method for image processing, extracting the blood vessel structure and saving a template for usage in a biometric system will be described in this bachelor thesis. The method was developed and tested on actual retinal images acquired by digital fundus camera and it was implemented in language C++ with the use of OpenCV library. This thesis also contains a brief introduction to biometrics, computer graphics and medicine.
|
|
|
Detection of Anomalies in Pedestrian Walking
Pokorný, Ondřej ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
The goal of this work was to create a system that would be able to detect anomalies in pedestrian walking. As the core of my application, I have used OpenPose, which is an application for detecting human skeletons. Then I used a bidirectional LSTM neural network to detect anomalies in video sequences. This architecture was chosen during the experiment because it outperformed other solutions. I trained my model to detect three types of anomalies. The output of my application is a video with marked sequences of anomalies. The whole system is implemented in Python.
|
|
|
Estimate the Height of a Persons from the Video Data
Jelen, Vilém ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
The aim of this bachelor thesis is to create an application that can detect pedestrians and make an estimate of their height from the video data. In the main part of the thesis I introduced security cameras and image processing methods suitable for detecting and classifying objects. Based on the comparison of these methods, I realized the pedestrian detection using Histograms of Oriented Gradients. As the input parameters of the proposed height estimation algorithm, I used the position and properties of the camera and reference objects or points.
|
guest ::
