National Repository of Grey Literature 316 records found  1 - 10nextend  jump to record: Search took 0.01 seconds. 
Road detection in outdoor environment using image processing
Vrbičanová, Antónia ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
The Master’s thesis deals with the issue of the road detection in the outdoor environment using image processing. It is highly required that the methods selected are robust to sudden light changes within the image and effective in detection of wide variety of road surfaces possibly comprising certain kinds of pollution. Two methods have been used in order to reach the desired goal. The initial method uses standard algorithms of the image processing. Main outcome of this method are highlighted road boundaries. The following methodisbasedonconvolutionalneuralnetworks.Inthiscasewehaveclassificationtask. The result of this method is the estimation of the road direction. In the whole process, severalneuralnetworkstructureshavebeendesigned.Afterthenetworktrainingthemost suitable one was selected. Eventually, the results have been retested using newly created test set. Both of these methods are implemented in programming language Python.
The Use of Artificial Intelligence for Decision Making in the Firm
Března, Filip Samuel ; Šebestová, Monika (referee) ; Dostál, Petr (advisor)
Artificial intelligence and fuzzy logic related to it currently belong to very popular and rapidly expanding technological subjects. It finds use in many areas, which also include the process of prediction of future states based on specific finite input characteristics. This master’s thesis deals with predictions that are done in field of agricultural crops growing. Basic principles that are affecting mentioned agricultural growing are explained here, their meaning and significance are specified, these are later on perceived as a key aspect to creation of fuzzy models that are used for prediction. This process is specifically about finding out the most suitable crop on considered parcel for maximization of income. Second part of design section is dedicated to description of approaches for work with fuzzy models and is also used as demonstration of application created for purpose of this thesis.
The Application of Fuzzy Logic for Evaluation of Quality of Customers
Nezbedová, Katarína ; Šebestová, Monika (referee) ; Dostál, Petr (advisor)
This master thesis deals with the evaluation of SAP customer quality using fuzzy logic theory and its application. The core of the work is to create models in the MATLAB and Microsoft Excel development environment. Also to use it to create and compare ratings of several customers with different parameters. Using the results, the company can determine the following procedure to solve customer’s problems.
Game with Non-Player Characters
Tomečko, Lukáš ; Peringer, Petr (referee) ; Janoušek, Vladimír (advisor)
The goal of this project is to create a 2D action strategy videogame, featuring intelligent enemies. The architecture design is based on techniques and patterns used in game industry. Game is written in C++, SFML library is used for graphics and inputs, Box2D library takes care of physics. Enemies' artificial intelligence applies standard algorithms used in videogame industry. Human players and metrics are used for evaluation of final game and enemies' intelligence.
Artificial Intelligence and Industry 4.0
Hirsch, Radim ; Kroupa, Jiří (referee) ; Kovář, Jiří (advisor)
The aim of this work is to provide an overview of the application of artificial intelligence methods in the context of Industry 4.0. The first chapter defines the concept of industry 4.0, previous development of the industry and inclusion of the scientific field of artificial intelligence in this concept. The second chapter is focused on the applications of artificial intelligence methods in the field of machining, manufacturing industry, automation and energetics. The work concludes with evaluation of methods, their advantages and disadvantages from the point of view of individual practical applications and mentions possible directions of future development.
Multi-Agent and Optimalisation Methods for Stealth Games
Láncoš, Jan ; Vídeňský, František (referee) ; Zbořil, František (advisor)
This bachelor thesis deals with the opponents' behaviour in stealth-based video games. It's main focus is the credibility of said behaviour in comparison to the opponents' real life counterparts and the overall immersiveness of the experience. The thesis describes the usage of the A* algorithm for dynamic pathfinding in a two-dimensional space. Furthermore it describes the opponents' patrolling system, their ability to detect the player's presence and also their ability to cooperate and communicate while trying to chase the player down. One playable level demonstrating the described behaviour has also been created as part of this thesis using the C++ language. The thesis can be used as an inspiration for anyone interested in making their own intelligent systems for computer games of a similar type.
Generating Faces with Conditional Generative Adversarial Networks
Venkrbec, Tomáš ; Hradiš, Michal (referee) ; Kolář, Martin (advisor)
The main goal of this thesis is to implement and compare models based on various architectures of conditional generative adversarial networks. Their main purpose is to conditionally generate realistic looking human faces with selected features. Results from models using DCGAN, WGAN-GP and ProGAN architectures were compared. Models were implemented using Tensorflow library and were trained on Flickr-Faces-HQ dataset. Across all used architectures, I managed to train models capable of generating realistic human faces, with an option to select age and gender.
Detecting the Occurrence of Objects in a Video
Šamánek, Jan ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
This bachelor thesis deals with detection of objects in videos by using primarily convolution neural networks and creating simple user interface, which allows user to choose classification model and use it to analyze video or train given model on own dataset. First part is dedicated to description of machine learning and neural networks. After that follows the section about image description and image classification using machine learning algorithms and data augmentation. Last part deals with describtion of own design of  neural network and user interface and describing achieved results.
Implementation of Simple Speech Recognizer in a Web Browser
Crkoň, Jakub ; Glembek, Ondřej (referee) ; Szőke, Igor (advisor)
The goal of this project is to implement simple speech recognizer for web browser. This paper describes fundamental components required for implementing speech recognizer and techniques which are used for optimization process of speech recognition in web browser. At first, the paper focuses on introduction of speech recognition theory. It describes individual parts and principles of speech recognizer. In next section, thesis describes design, implementation and principles of acceleration of speech recognizer with limited computing resources of web browser. The implementation is divided into modules making up the library for usage in web browser. The library is easily extendable and usable in various web applications. Finally, it discusses potential directions of development and usability of this project.
Identification of Persons in the Video from Quadcopter
Mojžiš, Tomáš ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
The aim of this thesis is to make an application capable of recognizing people's faces based on a user-created database in drone footage. The database is made of pictures of people that should be identified in the footage. The output of this application is a video where the demanded people are labeled with their names. Some face detection and recognition state of the art solutions based on neural networks are compared in this work. The final solution consists of the MTCNN detector and a face embedding extractor based on ArcFace. The created multiplatform application allows to recognize people in drone footage even with face width of less than 20 pixels. The final solution was tested on a private dataset comprised of drone footage.

National Repository of Grey Literature : 316 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.