|
|
Mobile App for Managing Tips in a Restaurant
Kocour, Martin ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
This bachelor thesis deals with an issue of tip evidence. The result is an Android application for tablets, which provides easy tip recording and its transparent division among employees. In the thesis are described problems with developing application for Android operating system. Reader will read about the process of designing and implementing. The paper is supplemented with results of application testing and its future in way of developing.
|
|
|
Multiplayer Minigames in Virtual Reality
Čubík, Dušan ; Špaňhel, Jakub (referee) ; Bambušek, Daniel (advisor)
This thesis deals with the design and implementation of a multiplayer virtual reality game. Specifically, it is a series of fun mini-games in which players compete against each other. The result of the work is a client application with two implemented minigames for Oculus Quest and Quest 2 devices and a server application. Shooting Range is a minigame for shooting competition. Towers is a minigame in which players destroy each other's forts. The minigames have been tested by users. The Unity game engine was used to implement the client application. The XR Interaction Toolkit library was used to implement the virtual reality. The network communication on the client side is implemented by Photon PUN. The server side implementation is provided by Photon Server SDK.
|
|
|
Unique Car Counting
Uhrín, Peter ; Špaňhel, Jakub (referee) ; Juránek, Roman (advisor)
Current systems for counting cars on parking lots usually use specialized equipment, such as barriers at the parking lot entrance. Usage of such equipment is not suitable for free or residential parking areas. However, even in these car parks, it can help keep track of their occupancy and other data. The system designed in this thesis uses the YOLOv4 model for visual detection of cars in photos. It then calculates an embedding vector for each vehicle, which is used to describe cars and compare whether the car has changed over time at the same parking spot. This information is stored in the database and used to calculate various statistical values like total cars count, average occupancy, or average stay time. These values can be retrieved using REST API or be viewed in the web application.
|
|
|
System for Automatic Parking Access Based on License Plate Recognition
Václavek, Patrik ; Sochor, Jakub (referee) ; Špaňhel, Jakub (advisor)
Goal of this thesis was to design and implement system operating in real time, which manages to detect incoming vehicle to the car park terminal, recognize its licence plate and automatically decide on its admission. System uses the Gaussian Mixture Model algorithm for detection of incoming vehicle. For reliable localization of licence plate are used two methods, the first one uses of extraction of Maximally Stable Extremal Regions (MSERs), the second one uses of Top-Hat transformation. Support Vector Machine (SVM) algorithm is used to decide, whether is the found area a licence plate. Character classification is performed using artificial neural network. For implementation was used library OpenCV. Thanks to optimalization is the extraction of MSERs accelerated up to seven times. The accomplished success rate in case of licence plate localization is 92,47% and in case of classification of characters is 90,03%.
|
|
|
Mobile Application with Computer Vision Elements
Dyk, Tomáš ; Bartl, Vojtěch (referee) ; Špaňhel, Jakub (advisor)
Bachelor thesis describes development of mobile applications for loading and solving sudoku. Mobile application is developed for Android. The user loads a sudoku into the application by taking a picture of sudoku from a newspaper or a magazine. The application then detects the sudoku position in the photo, recognizes the numbers in each sudoku field and allows the user to solve the sudoku in the mobile phone. All unresolved sudoku, including newly uploaded, is stored in the application so that the user can solve it at any time.
|
|
|
Vehicles Re-Identification with License Plate
Hažmuka, Tomáš ; Špaňhel, Jakub (referee) ; Sochor, Jakub (advisor)
This thesis describes design and development of an aplication for reidentification of vehicles in multiple camera streams. It explains methods of image processing, object detection and identification of symbols. Created application uses OpenCV library. It is written in the C++ language, standart C++14. Furthemore, this thesis describes testing of application on input data including training of the reference data.
|
|
|
Document Information Extraction
Janík, Roman ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
S rozvojem digitalizace přichází potřeba analýzy historických dokumentů. Důležitou úlohou pro extrakci informací a dolování dat je rozpoznávání pojmenovaných entit. Cílem této práce je vyvinout systém pro extrakci informací z českých historických dokumentů, jako jsou noviny, kroniky a matriční knihy. Byl navržen systém pro extrakci informací, jehož vstupem jsou naskenované historické dokumenty zpracované OCR algoritmem. Systém je založen na modifikovaném modelu RoBERTa. Extrakce informací z českých historických dokumentů přináší výzvy v podobě nutnosti vhodného korpusu pro historickou Češtinu. Pro trénování systému byly použity korpusy Czech Named Entity Corpus (CNEC) a Czech Historical Named Entity Corpus (CHNEC), spolu s mým vlastním vytvořeným korpusem. Systém dosahuje úspěšnosti 88,85 F1 skóre na CNEC a 87,19 F1 skóre na CHNEC. Toto je zlepšení o 1,36 F1 u CNEC a 5,19 F1 u CHNEC a tedy nejlepší známé výsledky.
|
|
|
Explainable Face Liveness Classification
Mičulek, Petr ; Beran, Vítězslav (referee) ; Špaňhel, Jakub (advisor)
Cílem této práce je analýza, vývoj a vyhodnocení vysvětlitelných systémů klasifikace živosti obličeje. Klasifikace živosti obličeje slouží jako bezpečnostní filtr vyřazující podvrhy před provedením rozpoznávání obličeje. Klasifikátory živosti obličeje proto nezbytně stojí v pozadí vzestupu biometrických systémů v chytrých telefonech a bezpečnostních kamerách. Standardní neuronové sítě pro tuto úlohu však neposkytují vysvětlení pro svá rozhodnutí. V této práci jsou tedy prozkoumány a použity metody vysvětlitelnosti, konkrétně atribuce vstupních dat. V rámci těchto metod jsou provedeny experimenty na zhodnocení jejich vhodnosti a jako nejvhodnější je vybrán GradCAM používající dodatečné augmentace. Dosahuje hodnoty AUC metriky při umazávání snímku o hodnotě 0,658 a AUC při vkládání do snímku 0,908. Ačkoli další experimenty ukazují limity věrnosti těchto vysvětlení a jejich ne vždy jasnou srozumitelnost, je ukázáno, že poskytují vodítka pro vylepšení prediktivních schopností systémů pro vyhodnocení živosti obličejů.
|
|
|
Tram Detection in Video by Neural Network
Golda, Vojtěch ; Špaňhel, Jakub (referee) ; Dyk, Tomáš (advisor)
This paper deals with tram detection in video using convolutional neural networks. The basic principles of their function are described. A number of distinct architectures are trained. The usefulness of the resulting models is subsequently compared. The output of this paper is a program capable of detecting trams in video.
|
|
|
Tram Detection in Video by Neural Network
Golda, Vojtěch ; Špaňhel, Jakub (referee) ; Dyk, Tomáš (advisor)
This paper deals with tram detection in video using convolutional neural networks. The basic principles of their function are described. A number of distinct architectures are trained. The usefulness of the resulting models is subsequently compared. The output of this paper is a program capable of detecting trams in video.
|
guest ::
RSS feed.