|
|
Automatic Creation of Animated Video based on Textual Story
Kuchař, Josef ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The aim of this work is to link a diffusion model for generating human motion with a diffusion model for generating video. The solution uses current methods for generating video and motion. Video generation is carried out using an image generator equipped with an adapter for temporal consistency. The work introduces a method of connecting both diffusion models using the ControlNet network. The created solution allows for generating video from a simple text description, or a detailed scenario. The program was tested in a user study.
|
|
|
Creating Advertisement Video Using Neural Models
Taipova, Evgeniya ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The aim of this work is to create a system for the automatic generation of advertising videos based on textual descriptions, which will help users without video production experience save time and money. The work consists of two main parts. The first part uses generative models Stable Diffusion and Stable Video Diffusion for the creation of visual content and GPT-3.5 Turbo for creating scripts for advertising videos. The second part is a web application that allows users to input the necessary information for advertisements and to display the finished videos. This system simplifies and accelerates the process of creating various types of advertisements.
|
|
|
Web Application for Inspecting Results of Automatic Video Processing and Manual Annotations
Červíček, Petr ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The thesis pursues the implementation of the web application for obtaining valuable data for anotation. Data are mainly collected from videos and images, but they can be obtained from deepfakes images and gifs as well. The YOLO - You Only Look Once is used for object detection in the videos. Whole application is developed in node.js and react. Node.js for backend and react for frontend. For a better understanding of web application, there is also historical description of the web technologies.
|
|
|
Analysis of Surveillance Camera Recordings
Ščavnická, Šárka ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
This thesis deals with the systems for analyzing records from security cameras. It aims to create a functional solution that analyzes records and answers questions from the user. The created system combines the YOLO algorithm for object detection and DeepSORT for their subsequent tracking. It contains five models that detect specific situations. Individual models achieved varying degrees of success during testing, with the lowest success rate being 58 % for the getting out of car situation. The highest success rate, 83 %, was obtained by a model for detecting a meeting between two people.
|
|
|
Supporting Board Game Nemesis on Android Mobile Phone
Štěpánek, Miroslav ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to create a mobile application for the board game Nemesis designed for the Android system, which will allow the user to find out information about the game components during the game. The solution consists of two main parts the first is a model created with the help of the Tensorflow library, which is responsible for the detection of these components. The second is the application itself, which receives results from the model and displays the resulting information to the user. This makes the game easier for the user and helps to speed it up. The resulting system can be modified so that the application can be used for other games.
|
|
|
Reinforcement Learning for Robotic Soccer Playing
Brychta, Adam ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to create a reinforcement learning agent that is able to play a soccer. I'm working with the deep Q-learning algorithm, which uses deep neural network. The practical part of this work is about implementing the agent for reinforcement learning. The goal of the agent is to choose the best action possible for a given situation. The agent is being trained in a variety of scenarios. The result of this thesis shows an approach to control soccer player using machine learning.
|
|
|
Recognizing People and Their Activities in Video from Security Cameras
Saloň, Juraj Samuel ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to design and develop a system capable of recognizing the activities of people from surveillance cameras. Special attention is paid to the concept of complex situations or events that are defined by relations between identified objects. The first part surveys state-of-the-art techniques for object recognition, object tracking, and recognition of activities relevant to the realized solution. The second part describes the design and implementation of the devised system. It takes advantage of specific relations among two or more objects that are identified in video recordings, such as "person getting out of the car" or "one or more people met with a person of interest and they left together". Results are evaluated on video data extracted from available datasets and manually annotated. The mean average precision metric (MAP) on the data is reported.
|
|
|
Multiple-Context Trust Model for a Social Network Using Personality Analysis
Švec, Tomáš ; Zbořil, František (referee) ; Samek, Jan (advisor)
Tato diplomová práce navazuje na bakalářskou práci, ve které byl vytvořen model důvěry pro sociální síť Facebook. Do tohoto modelu jsou zapracovány připomínky z konference UMAP 2013 a ověřena jeho škálovatelnost a flexibilita. V další části práce jsou uvedeny základní termíny z psychologie osobnosti a zkoumána závislost důvěry na osobnosti uživatele. Je vybrán model Big Five k reprezentaci charakteru uživatele a navržen dotazník, u nějž bude zkoumána korelace s modelem důvěry. Tato korelace je na základě sociologických poznatků odhadnuta a později ověřena na reálných uživatelích sociální sítě Facebook.
|
|
|
Support for Sagrada Game on Mobile Phone with OS Android
Trněný, Jan ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to create support application for board game Sagrada on mobile devices with OS Android. The solution consist of detection and recognition of the game pattern card and dices on board using the OpenCV library. Subsequently, support is provided, in any state of the game, for points calculation and rules checking for any number of players. These functions allow management of data for multiple users on one mobile device and help with faster rules checking and points calculation. Functions also help for beginners in understanding the game.
|
|
|
Evaluation of Trust or Reputation Based on Social Network Analysis
Švec, Tomáš ; Malačka, Ondřej (referee) ; Samek, Jan (advisor)
This thesis' goal is to apply the terms trust and reputation from the point of view of artificial intelligence to social network analysis methods. It evaluates current available interactions for a model of trust considering various social networks. A mathematical model of trust for Facebook is designed and described in further parts. This model had been implemented in Python programming language. Experiments regarding this thesis are conducted on a sample amount of Facebook users and furthermore analyzed from the perspective of both artificial intelligence and social psychology.
|
guest ::
