|
|
Fusing image and non-grid-like data for object segmentation
Repka, Samuel ; Nosko, Svetozár (oponent) ; Zemčík, Pavel (vedoucí práce)
Quite often, a phenomenon of interest can described by more than one data source. For example, a car's appearance shows its colour and brand, but not its engine status. However, other data sources do provide us with this information, be it a sound or mere touch. Such data source is often referred to as a modality. While using a single data source to extract the needed information may be sufficient, the addition of more modalities can be beneficial, because of their complementary nature. This data fusion, however, may be a quite challenging process. Different kinds of data have different properties, structures and various challenges connected to them. A plethora of different methods has been proposed, but usually, the methods are very data-dependent. This thesis presents a new approach to the fusion of two modalities, primarily for the purpose of image segmentation. One of the modalities is image, and the second one is any non-grid-like modality. The method uses a graph to jointly represent both modalities, aiming to capture the intra and inter-modalities relationships as accurately as possible. The graph is then processed, producing a graph with fused data, or a direct segmentation. The proposed method was evaluated on two datasets (from the fields of mineralogy and timber processing) and compared to another solution, showing both the potential and limitations of the method. In case of the mineralogy dataset, the results are very encouraging, showing that the method is capable of data fusion, even outperforming a contemporary method. In case of the timber dataset, the results were not as conclusive, as the method failed to improve the results when compared to a baseline solution, which may have been caused by a challenging dataset.
|
|
|
Radar Altimeter for Ultramicro Aircraft
Huba, Quido ; Nosko, Svetozár (oponent) ; Zemčík, Pavel (vedoucí práce)
The purpose of this bachelor thesis was to create a radar device with reasonable price and simple construction, that would help pilots of ultralight aircrafts with altitude monitoring during the flight and during landing. Radar device consists of a milimeter wave radar module produced by Texas Instruments company, of a microcomputer, audio device and a control diode button. Radar receives data, that are processed by a microcomputer in actual time. These data are transfered via bluetooth technology to audio device. Here data is presented in the form of a signal, that changes according to the aircraft’s altitude. Buttons control the device that is supposed to be helpful to beginning pilots during landing.
|
|
|
Using dense X-ray reconstructions for developing virtual sawing method
Kunda, Matej ; Nosko, Svetozár (oponent) ; Zemčík, Pavel (vedoucí práce)
The usage of machine learning and computer optimisation is growing and reaches many fields, and the sawmilling industry is no exception. With optimisation algorithms and virtual sawing, sawmills can produce boards and other wooden products of much higher quality. The main factor that degrades the quality of boards is knots. Knots are the leftovers of branches present in every piece of log and sawn boards. However, their position can be altered with sawing optimisation methods, and the board grade and price maximised. This Master's thesis aimed to develop one of the sawing optimisation methods -- sawing angle optimisation. Before sawing, the log can be rotated, and the location of knots on boards can be controlled. The optimisation method works by converting X-ray data to a function that represents knot locations along the polar angles in the wood and another function that contains Gaussian curves at the corner points of boards in the sawing pattern. Finally, a cross-correlation is computed and minimised between these two functions, resulting in knots avoiding the corner areas. The proposed method works on a simple principle, is computationally effective and can be deployed in real-time applications. The developed method was evaluated by applying virtual sawing using the angles obtained on a challenging dataset containing annotated X-ray data of logs, which was compared with ground truth data and an average result. The thesis resulted in an impressive decrease in arris knots count in an already highly optimised sawing environment.
|
|
|
Robotic Manipulator Exploiting RC Components and Servos
Liška, Jakub ; Nosko, Svetozár (oponent) ; Zemčík, Pavel (vedoucí práce)
The aim of this thesis was to create a valid robotic manipulator, using RC(radio control) components and servomotors. As part of the solution, it was necessary to equip the robotic manipulator with sensors that enable the detection of collisions with the environment and thus ensure the safety of the operator in the working area of the manipulator. The robotic manipulator is also equipped with absolute encoders for sensing the position of individual joints, an accelerometer and sensors for measuring the loads acting on individual joints. Standard stepper motors take care of the arm movement. The body of the robotic manipulator itself has been designed with the individual components in mind and can be fabricated using 3D printing. The solution also includes a user interface that can be used to control the robotic arm.
|
|
|
Evaluation of Image Quality and Camera Setup
Ondris, Ladislav ; Fučík, Otto (oponent) ; Zemčík, Pavel (vedoucí práce)
This work aims to develop a foundation for a general-purpose camera capable of updating its parameters based on the observed scene. This approach combines image quality assessment metrics with scene recognition. A set of metrics was collected, such as those used to assess contrast and sharpness. Additionally, a scene recognition machine learning model was developed to identify the scene, which serves as the basis for selecting appropriate camera parameters tailored to the specific scene. The work demonstrates the practical application of utilizing the metrics to optimize selected Image Signal Processor parameters and to detect optical aberrations.
|
|
|
Vláček řízený počítačem
Černák, Filip ; Maršík, Lukáš (oponent) ; Zemčík, Pavel (vedoucí práce)
Cílem této práce bylo zjednodušení automatického ovládání modelové železnice pomocí mobilního zařízení. Zvolený problém je vyřešen pomocí programu, který snímá danou železnici. Na snímcích detekuje modelové vláčky a porovnává, zda se nacházejí v uživatelem vyznačených oblastech na nich. Pokud k tomu dojde, program pošle sekvenci příkazů specifických pro daný vlak a oblast zadané příkazové stanici. Vytvořené řešení umožňuje automaticky ovládat výhybky a návěstidla, nastavit rychlost lokomotiv v jednotlivých úsecích tratě a zastavovat vlaky ve stanicích. Řešení dále nedovolí vjezd dvou modelových vlaků do jednoho úseku tratě. Přínosem této práce je jednoduchý způsob automatického ovládání modelového kolejiště pro začínající modeláře. Práce postupně popisuje koncepci řešení, jeho následnou implementaci a výsledky testů, ověřujících splnění zadání.
|
|
|
Vláček řízený počítačem s webovým rozhraním
Smažinka, Petr ; Maršík, Lukáš (oponent) ; Zemčík, Pavel (vedoucí práce)
Cílem bakalářské práce bylo nastudovat současné způsoby řízení modelových kolejišť, provést jejich analýzu a následně navrhnout nový způsob bezdrátového ovládání. Důležitou vlastností nového způsobu řízení je způsob rozpoznání vlaku, kdy kolejiště je neustále snímáno kamerou, která v reálném čase rozpoznává vlaky na trati dle jejich pohybu a zároveň provádí jejich identifikaci pomocí jedinečného kódu vysílaného každým vláčkem pomoci infračervené diody. Práce si rovněž kladla za cíl sestrojit minimalistické a přehledné webové uživatelské rozhraní k ovládání celého systému. Celý systém je plně funkční, umožňuje manuální i poloautomatický provoz a podporuje souběžnou jízdu více lokomotiv, včetně automatického řízení světelné signalizace, plánování jízd a přestavování výhybek. Během implementace byla zjištěna výkonnostní omezení použitého hardwaru znemožňující dekódování adres vysílaných infračervenými diodami. K rozpoznání vláčků se používá pouze analýza jejich pohybu, což se však během testování ukázalo jako dostačující.
|
|
|
Robotic Arm Exploiting RC Components and Servos
Bobčík, Petr ; Kapinus, Michal (oponent) ; Zemčík, Pavel (vedoucí práce)
The goal of this work was to create own robotic arm using RC components, servos and provide own graphical user interface to control it. I decided that the solution should use sensors that provides some kind of autonomous beahviour. For my solution I modified existing stepper motor based robotic arm with five degrees of freedom. As a sensors, the accelerometer, encoders, current sensor, laser distance sensor and camera were used. Thanks to these sensors, the robotic arm is able to detect stall, position of disconnected stepper motors, grabbing of an object or measure distance to the object to compute its position in a space. My solution offers own graphical user interface that allows to control each joint separately, autonomous controlling using camera or hand driven controlling.
|
|
|
On-the-fly compression in time-domain ultrasound simulations
Klepárník, Petr ; Fura, Łukasz (oponent) ; Krupa, Petr (oponent) ; Zemčík, Pavel (vedoucí práce)
This work proposes a new compression method and its application in the framework of time-domain ultrasound simulations, specializing in high-intensity focused ultrasound (HIFU). Large-scale numerical simulations of HIFU, important for model-based treatment planning, generate large amounts of data. A simulation typically requires hundreds of gigabytes of storage. The goal of using this method is to significantly save computing resources while maintaining sufficient quality of the simulation outputs. At the core of this work, experimental simulations are presented, which show that the proposed compression method and its use for on-the-fly calculation of the average acoustic intensity during the simulation bring significant improvements. The main advantage is to a large extent (up to 99 %) reduced consumption of precious disk space and approximately the same requirement for operational memory during simulation, which can significantly reduce the price of the computing platform. Compression does not adversely affect the overall simulation time. The accuracy of the new method was evaluated using thermal simulations. Using the new method, the same results are achieved in ablated tissue determination as in other approaches.
|
|
|
Tvorba multispektrálních map v mobilní robotice
Burian, František ; Mazal,, Jan (oponent) ; Zemčík, Pavel (oponent) ; Žalud, Luděk (vedoucí práce)
Dizertační práce pojednává o využití multispektrálního optického měření pro datovou fúzi, kterou je možné využít pro vizuální teleprezenci a mapování uvnitř budov i ve vnějším prostředí v systému složeném z heterogenních mobilních robotů. Pro fúzi jsou použity dálkoměrné optické snímače, termovizní kamery a barevné kamery. Popsané algoritmy jsou optimalizovány pro práci v reálném čase a implementovány na robotický systém CASSANDRA vytvořený naší robotickou skupinou.
|
host ::
RSS.