|
|
Research of the dynamics of the laser welding process
Horník, Petr ; Mendřický, Radomír (referee) ; Šebestová, Hana (referee) ; Mrňa,, Libor (advisor)
Laser welding is a modern welding method that has been widely adopted by the industry. With the increasing demands on weld quality, automated welding is being applied with advantage. There are requirements to implement welding process monitoring in accordance with the concept of Industry 4.0. This thesis develops methods for laser welding process monitoring. The resulting weld quality is largely influenced by the behaviour of the vapour-gas channel called the keyhole generated by the laser beam. However, direct observation of the keyhole during the welding process is difficult and indirect methods are often chosen, with an emphasis on non-contact optical methods. First, the observation of the plasma plume using a photodiode is verified, and then an innovative approach of detecting the back-reflected laser radiation using a camera is proposed. An optical extension for monitoring the welding process coaxially at the laser wavelength is assembled for this purpose. The aim of this thesis is to summarize the possibilities of detecting the welding process status and to propose a variant acceptable for industrial application. The image data obtained during the process represent the intensity distribution of the back-reflected laser radiation. Descriptive statistics and image segmentation methods are used to extract features from the intensity distribution. The distribution of back-reflected laser radiation is related to process parameters, keyhole geometry and some weld defects.
|
|
|
Automatic Determination of Positioning System Devices Coordinates from Point Cloud Data
Bucher, Michal ; Vašíček, Zdeněk (referee) ; Šimek, Václav (advisor)
Thesis describes the problem and solution of detecting anchors of localization systems and evaluating anchor position in 3D space. Position system from Sewio Networks s. r. o. requires position in 3D space for individual anchors. These anchors then gather informations about the position of individual tags in their range. The work describes some commonly used technologies for object detection and 3D data reconstruction. Compares the existing solutions in context of this work. Based on the results chooses one approach and implements it. Final gathered data with implementation are compared with real existing measurements used in the RTLS Sewio Networks s. r. o. system.
|
|
|
Exploitation of Neural Networks for Fusion of Image and Non-Image Data
Pařilová, Michaela ; Reich, Bořek (referee) ; Zemčík, Pavel (advisor)
This bachelor's thesis deals with exploitation of neural networks for fusion of image and non-image data. It primarily focuses on comparing detection algorithms for image data (data obtained from a camera) with detection algorithms using the fusion of image data and non-image data (data obtained from a camera and radar). As part of the comparison of these two approaches, an own fusion model was created, which was subsequently tested on the selected data set.
|
|
|
Computational model of the environment of an autonomous vehicle
Doležel, Radek ; Píštěk, Václav (referee) ; Kučera, Pavel (advisor)
The aim of this thesis is to develop a functional computational model for vehicle motion prediction based on a search of sensors and their locations on the vehicle, neural networks for computer vision, datasets for network learning, and programs for creating simulations and virtual environments. The paper describes the process of creating the vehicle virtual environment and simulation. In addition, sensor placement designs including their parameters are developed. Subsequently, the programmed vehicle trajectory prediction algorithm including learning and neural network implementation is presented. Finally, the results of the developed algorithm are presented.
|
|
|
Robotic Arm Exploiting RC Components and Servos
Bobčík, Petr ; Kapinus, Michal (referee) ; Zemčík, Pavel (advisor)
Cílem této práce bylo postavit vlastní robotické rameno, s využitím RC komponent, serv a dodat k němu i vlastní uživatelské rozhraní, které umožní jeho řízení. Součástí řešení bylo také opatřit robotické rameno potřebnou senzoriku, která by umožnila jistou míru autonomnosti. Pro mé řešení jsem se rozhodl upravil již existující design robotického ramene, s pěti stupni volnosti, založeném na krokových motorech. Přidal jsem senzory, jako je akcelerometr, enkodér, měřič proudu, laserové měření vzdálenosti a kameru. Na základě těchto senzorů je robotické rameno schopné detekovat náraz, pozici odpojených motorů, uchopení předmětu uchopovacím mechanizmem nebo měřit vzdálenost předmětu v prostoru za účelem inverzní kinematiky. Vytvořil jsem také jednoduché uživatelské rozhraní, které umožňuje tři typy ovládání, jako je ovládání jednotlivých kloubů samostatně, autonomně s využitím kamery nebo ručním napozicováním.
|
|
|
A modular streaming service with cloud storage
Kluka, Daniel ; Richter, Miloslav (referee) ; Kratochvíla, Lukáš (advisor)
This thesis deals with the design of a modular streaming system with cloud storage. The aim is to design a cheap and reliable solution using smart home. An open-source Home Assistant system running on Raspberry Pi 4 with an application available for Android and iOS has been chosen as the control system of the smart home. For this system, two versions of smart cameras are proposed in this thesis, one with colour vision and the other with black and white vision with the possibility of seeing infrared light at night. The main microcontroller of the cameras is ESP32-CAM model AI-THINKER. Both cameras are used to test computer vision methods with image streaming capability.
|
|
| |
|
|
Camera testing
Frigyik, Tomáš ; Kratochvíla, Lukáš (referee) ; Richter, Miloslav (advisor)
This bachelor's thesis deals with the issue of capturing raster images using cameras and the current state of this issue, the appropriate setting of camera parameters that include external and internal parameters, the design of a measuring set for testing these parameters, while using the designed patterns generated on the monitor. This work also deals with the design of suitable models for setting parameters, the method of their generation and processing. The next part of this work shows a set of images and their processing, evaluation of the properties of the proposed processing procedure and determination of applicability of patterns.
|
|
|
Analysis of methods for vehicle speed estimation from video recordings
Woletz, Jakub ; Bradáč, Albert (referee) ; Křižák, Michal (advisor)
The thesis deals with methods that deal with the evaluation of speed from CCTV footage, either from a static camera (e.g. security cameras) or from a dynamic camera (e.g. dashboard cameras). The entire thesis first discusses the various methods available, then shows their application to specific camera footage and evaluates their accuracy. The result of the work is an analysis of the applicability and accuracy of these methods for specific types of video footage.
|
|
|
Unconventional Methods for Interacting with a Robotics Workplace
Dvořák, Jakub ; Beran, Vítězslav (referee) ; Materna, Zdeněk (advisor)
The bachelor thesis focuses on non-traditional methods of interaction with a robotic workplace, with an emphasis on camera tracking of the user, control of the workplace using camera outputs and human-robot interaction. The main focus of the work is the integration of Azure Kinect, a human detection device, into the ARCOR2 robot programming system. This thesis presents an extension to ARCOR2 that uses Azure Kinect to obtain information about the users' location and motion, which is then used to control the workplace using gestures, and explores the possibilities of interacting with the robot workplace. This extension enables easier and more natural human-workplace interaction, contributing to more effective use of robots in industry and research. The result of this work is a functional system for tracking the user with a camera, including the possibility of using this information to program the robotic workstation. The result of the work further increases the efficiency of human-robot interactions and opens the door for further innovations in robot programming using the ARCOR2 system.
|
guest ::
