|
|
Detekce typu a bodového ohodnocení kartiček ve hře Hobiti
Hlinský, Martin ; Kohút, Jan (referee) ; Vaško, Marek (advisor)
This thesis aims to create a card detector that can train a model that can detect the score of a card and its type using the synthetic generation of the dataset. The YOLOv8 model is used for training. The first step is to take pictures of the cards, which then go through a pre-processing stage so they do not contain background and are aligned. These pre-processed card images are combined with photos from other datasets in a generator that randomly translates, rotates, and otherwise simulates photos of possible card placements. This generator’s output is roughly 50 000 annotated images in the case of the Hobiti game, but different dataset sizes and pre-trained weights are compared in the experiments. The latest generation of trained detectors was validated on a real dataset for unbiased testing, and the most accurate model trained on purely synthetic datasets achieved precision up to 81.5 % according to the 50 metric. It is then possible to implement, for example, a point counter on the final detector, a prototype of which is also described in this paper.
|
|
|
Road Transport Analysis Using Neural Networks
Žárský, Daniel ; Musil, Petr (referee) ; Smrž, Pavel (advisor)
Cílem této bakalářské práce je zjednodušit analýzu silničního provozu, která využívá kamerové záznamy, a to poskutnutím prostředku pro automatickou annotaci scény. Práce popisuje obecné technické pricipy využité v kamerovém systému monitorujícím dopravu a navrhuje postup zpracování dat, získaných metodami počítačového vidění, s cílem automatizovaného nasazení systému. Následné zpracování dat využívá klastrovacích algoritmů pro identifikaci a lokalizaci hlavních směrů pohybu účastníků dopravnícho provozu. Na základě těchto výsledků je scéna automaticky annotována. Anotace scény je použitelná jako základ pozdější detekce anomálií v dopravě v reálném čase.
|
|
|
Object Detection on the i.MX RT Microcontroller
Kravchuk, Marina ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
This work focuses on the use of machine learning, particularly convolutional neural networks, in industrial applications. The course of work involves investigating the implementation of these networks directly on embedded devices, specifically NXP i.MX RT microcontrollers. During the course of the study, materials related to the training and use of neural networks and their optimization for deployment on low power devices were reviewed. Several neural network models were trained and tested, the best of which was used in the final version of the application. The application itself is divided into two parts: one part is written in C/C++ in the MCUXpresso IDE, where the main functionality of the program is implemented, while the other part of the work, i.e. the creation of a graphical user interface to control the program, is done in Python. The result is a functional application for the MIMXRT1170-EVK microcontroller that is able to detect and recognize small colored objects of certain shapes from a predefined data set.
|
|
|
Detection of Material Surface Damage Based on a Photograph
Marek, Radek ; Sakin, Martin (referee) ; Dyk, Tomáš (advisor)
This work focuses on the use of various types of neural networks for detecting surface damage of materials from photographs and evaluates their effectiveness. Identifying different types of damage, such as cracks, scratches, and other defects, is essential for assessing the condition of materials and may indicate the need for further maintenance or repairs. The use of advanced neural networks allows for more precise detection and classification of damage, which is crucial for applications in areas such as construction, the automotive industry, and aerospace engineering, where rapid and reliable diagnostics of material defects are critical. Integrating these technologies into regular inspection processes can significantly improve accident prevention and extend the lifespan of structural components. The work also discusses the possibilities for improvement and adaptation of algorithms to specific materials and types of damage. Thus, this work demonstrates how advanced machine learning technologies can significantly contribute to more effective and reliable material condition monitoring, opening paths for future innovations in maintenance and safety.
|
|
|
Segmentation of logical units in text
Kostelník, Martin ; Kišš, Martin (referee) ; Beneš, Karel (advisor)
Cílem projektu bylo vytvořit systém pro automatickou segmentaci textu do logických celků. Práce staví na systému PERO-OCR a cílí na zlepšení zpracovávání českých historických dokumentů a jejich vyhledávačů používaných knihovníky a vědci. Práce zahrnovala vytvoření a anotace vlastní datové sady složené celkem z 4044 stránek z knih, slovníků a novin. K problému segmentaci textu je přistoupeno inovativních přístupem, kdy je brán jako shlukovací problém jednotlivých řádků textu. Metoda je dvoufázová: nejprve probíhá detekce regionů textu pomocí modelu YOLOv8 a následuje jejich spojení grafovou neuronovou sítí. Vyhodnocení je provedeno pomocí shlukovací metriky V-measure a na testovacím datasetu dosahuje hodnot 77.93 % pro knihy, 95.79 % pro slovníky a 90.23 % pro noviny.
|
|
|
Detection of a Semi-Structured Semi-Finished Product from a Defined Area Using Artificial Intelligence Methods
Zmrzlý, Jan ; Škrabánek, Pavel (referee) ; Juříček, Martin (advisor)
This thesis addresses the issue of machine vision in the context of Industry 4.0, with an emphasis on the detection of semi-structured objects from surfaces. The first part of the thesis discusses the theoretical aspects of the task, including selected machine vision algorithms and the use of neural networks in this area. Furthermore, a survey of the available methods for solving this problem is conducted, as well as the current state of the art of the EDUset ONE robotic cell with respect to machine vision. Based on the analysis, a hardware solution in the form of camera, lighting and other components is proposed. Subsequently, the design and implementation of different methods for detecting multiple types of objects is carried out, with emphasis on modularity, efficiency and accuracy. Finally, the work compares these methods and verifies their functionality in interaction with a real robotic cell.
|
|
|
Neural networks used in autonomous vehicles
Ryšavý, Jan ; Píštěk, Václav (referee) ; Kučera, Pavel (advisor)
This bachelor thesis deals with the use of neural networks in autonomous vehicles. The first part of the thesis presents the basic principles of neural networks and learning methods that are used in autonomous vehicles. Then the thesis describes the architecture and functions of neural networks. The second part of the thesis also describes the different types of autonomous vehicles, their classifications and an overview of the sensors used by autonomous vehicles. The last part of the thesis deals with the implementation of neural networks in ECUs using programming languages and libraries, and applications such as object detection and marker recognition.
|
|
|
Visualization of Detected Objects from Drone in Microsoft HoloLens 2
Osvald, Filip ; Materna, Zdeněk (referee) ; Bambušek, Daniel (advisor)
Drony se stávaji stále cennějšími v různých oblastech, jako je bezpečnost, řízení krizových situací a záchranné operace. Přenos dat a geografických informací zachycených drony k pozemnímu personálu však představuje významné výzvy. Úkol se stává ještě složitějším při použití více dronů, což způsobuje, že zpracování informací jedním operátorem dronu je velmi neefektivní. Cílem této práce je vyvinout systém schopný zobrazovat objekty detekované dronem v Rozšířené Realitě. Práce posuzuje použitelnost takového systému pro přenos informací a identifikuje vhodná zařízení a technologie, které lze do systému začlenit.
|
|
|
Object Detector for Robotic Workplace
Kneslík, Martin ; Bambušek, Daniel (referee) ; Materna, Zdeněk (advisor)
The main goal of this thesis was to create an algorithm for detection and tracking of colored cubes using the Kinect Azure depth camera and integrate this algorithm into the ARCOR2 system. The solution uses color filtering of the input image, the DBSCAN algorithm for finding clusters in the pointcloud, and RANSAC for plane detection. The detection is evaluated on a custom dataset with an accuracy of 91%. The user of the ARCOR2 system can use the results of this work in a demonstration workstation in the robotics lab, where robots will manipulate the colored cubes detected by the algorithm.
|
|
|
QR code detection using deep learning
Černohous, Matěj ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This bachelor thesis deals with the design of an algorithm for detecting and decoding QR codes in images using deep learning techniques. The work involved the construction of 2 datasets, a YOLOv7 neural network model for detecting QR codes in images, a YOLOv4-tiny neural network model for detecting position markers of QR codes, and a Python program utilizing these models to read QR codes in images. For evaluation, the algorithm was compared with other options for QR code reading.
|
guest ::
