|
|
Automatic evaluation of fermentation degree of cocoa beans
Sedlmajer, Jakub ; Kůdela, Jakub (referee) ; Škrabánek, Pavel (advisor)
Standardní metodou zjištění výsledné kvality fermentace kakaových semen je tzv. cut-test. Při tomto testu je kakaové semeno rozříznuto na 2 poloviny, a následně je posouzeno vysoce kvalifikovaným odborníkem. Vzhledem k obrovským objemům zpracovávaného kakaa je automatizace tohoto procesu pomocí strojového vidění nevyhnutelná. Tato práce se zabývá návrhem a vytvořením softwarových nástrojů, které to efektivně umožní.
|
|
|
Design and virtual commissioning of an educational robotic cell
Novák, Štěpán ; Bražina, Jakub (referee) ; Vetiška, Jan (advisor)
This master's thesis discusses the creation of a virtual commissioning of a machine vision demonstration program in an educational robot cell. The first section of this thesis deals with the theory in robotics, virtual commissioning and machine vision. Systemic analysis of the problem was addressed in the second section. The third section cotains the design of the cell. The fourth section describes the design of some individual parts of the cell, the process of creating the program and virtual commissioning itself.
|
|
|
Innovation of the existing feeding device solution in the context of an automated and robotic workstation
Porubský, Radek ; Marek, Jiří (referee) ; Knoflíček, Radek (advisor)
This thesis deals with the design of a new version of the production and assembly node, which is part of an automated and robotized workstation for product assembly. The main objective of modifying the original solution is to eliminate the problems of the existing solution and apply innovations to make the work process of the equipment more efficient. The main modification of the original solution is the replacement of the bowl vibratory feeders in combination with linear vibratory feeders by a flexible feeding system with camera and robot. The paper describes the process of designing a new solution for the node, which eliminates the problems of the existing solution and at the same time comes up with new innovations. By solving the problems of the original solution and introducing the innovations, the reliability, speed and smoothness of the working process of the machine is improved. The work includes, among other things, drawings, risk analysis and costing.
|
|
|
Drone position stabilization methods using image data
Koukal, Ondřej ; Raichl, Petr (referee) ; Janoušek, Jiří (advisor)
This bachelor’s thesis focuses on the design of an unmanned aircraft stabilization system. The purpose of this system is to determine the exact position of the unmanned aircraft in space based on image data from two cameras in real time. The theoretical part describes the image processing methods and the algorithm for determining the position of the unmanned aircraft. The practical part describes the implementation and testing of the system.
|
|
|
Robotic selection of 2D objects from a container
Velen, Bohumil ; Parák, Roman (referee) ; Matoušek, Radomil (advisor)
In this thesis, a specific problem of production automation is addressed. Specifically, in this case, it concerns the selection of 2D products from a container by a robot. The thesis briefly presents both the wide range of options that are offered on the market in this regard, and the specific build and programming of a robot that can identify the part, grasp it and manipulate it to get it into the desired position. In this paper, the results of the identification and manipulation of several 2D parts are presented and documented. These experiments have demonstrated the effectiveness of the solution and the practical performance of the machine vision system and the ABB YuMi collaborative robot that was used. This also showed the way to solve similar manipulation tasks in other possible industrial applications.
|
|
|
Machine vision for robotic manufacturing systems
Svoboda, Tomáš ; Šubrt, Kamil (referee) ; Vetiška, Jan (advisor)
The first part of the thesis is a research of components and image processing in the application of machine vision in industry. The parameters required for quality image acquisition are described and the algorithms of programs for image evaluation in practice are selected. The practical part focuses on the description of a model task of Braille control on drug packaging. It includes the design procedure for component selection, parameter settings and the image processing program. The task is divided into two phases, where the first phase involves static testing without movement of the test samples and the second phase involves movement by a fan simulating motion on a conveyor.
|
|
|
Detekce objektů na včelím plástu a spadových podložkách mobilním telefonem
DĚD, Lukáš
This thesis deals with the improvement of the adopted solutions, dealing with the detection of the bee queen and the calculation of the fall of the Varroa destructor mite. These advanced solutions are implemented in a mobile application for Android devices. Furthermore, this work deals with the investigation of methods for the detection of short-lived and long-lived bees. The theoretical part contains a description of the methods used in the field of computer vision and convolutional neural networks. The practical part describes the environment and technologies, which were used to implement the methods described in the theoretical part, as well as the process of porting the results to the mobile platform.
|
|
|
Identifikace železničních vozů na základě obrazové informace
ŠEPS, Pavel
This master's thesis focuses on the design and implementation of railway wagon indetification system based on the identifying information on the side of each wagon. It describes the search for the optimal image preprocessing, comparison of OCR services, search for the suitable technologies and evaluation of the quality of the finished application. Part of this thesis also describes existing solutions and the application development and functionality. To obtain the images of the wagons, a photo trap is designed and assembled, which is then located near the train track. A custom neural network was built to find the identifying information and a custom annotation application was developed to create the test and training sets. The final identification application then implements this neural network. It also uses Azure OCR services. It is designed to automate the manual process and is ready for use in real operation.
|
|
|
Rybí biometrie s využitím metod počítačového vidění
BEKKOZHAYEVA, Dinara
Nowadays, individual fish identification is made by tagging. Tagging is an invasive method of fish identification that can cause injuries to fish and stress to them, leading to increased mortality. Tagging is a time consuming and expensive identification way. The disadvantages of this method are obvious. To solve those problems, identification from the images could be used. Image-based fish individual identification is an excellent alternative. It is cheap, fast and not stressful to the fish. Fish identification from images is widely used in species identification. But not many studies deal with the identification of individual fish. All described reasons motivate us to work toward individual fish identification from the images as a substitute for fish tagging. We have done complex research with different fish species, different data collection conditions, and long-term perspective identification. In chapter 2, we tried the first attempt to automatically identify individuals of ornamental fish Sumatra barb Puntigrus tetrazona in an aquarium. Fish were freely moved in an aquarium with water; the green background was used to do the fish segmentation. Totally 43 individuals were used in this experiment. Identification accuracy was 100% and supported us to continue with the next step experiment. The next step was to increase the number of photographed fish to 330 fish. We used the commercially important Atlantic salmon Salmo salar in this study. We have tested different visible patterns on the fish body, such as dots on the body (chapter 3) and the iris of the eye (chapter 5). The duration of the experiment was six months. In this study, different data collection conditions were tested. Images of fish underwater in an aquarium and out of the water in a photo tent were taken. For the pictures of the fisheye, we used a micro-camera. The best results obtained from those experiments were 100% accuracy for the dot approach and HOG parametrization methods and 95% for fisheye data. The last experiment in this dissertation (chapter 3) was done to prove that the fish species which have no obvious pattern on the body, such as Sumatra barb (black vertical stripes) and Atlantic salmon (dots on the body), could be identified non-invasively from the images. European seabass Dicentrarchus labrax and common carp Cyprinus carpio were used in this study to prove this idea. Totally 300 seabass and 32 carp were photographed out of the water to get high-quality data. Together with the short-term experiment, we collected long-term data (two months for seabass and four months for carp). Different parts of the body were tested for identification (lateral line, scale pattern, operculum). Surprisingly, the identification results were high enough (100% for both species, even for the long term experiments) to conclude that the photo-identification works with species without an obvious pattern on a body. The conclusion supported by the results of the experiments is that the automatic photo-identification of individual fish is possible using machine vision. Data processing and identification procedure were fully automated. The approach works for species with and without an obvious pattern in the body (Sumatra barb, Atlantic salmon, European seabass and common carp), and it is useful for long term individual identification. The method can be used as a substitute for invasive fish tagging.
|
|
|
Computer Vision for Autonomous Vehicles
Lečbych, Michal ; Škrabánek, Pavel (referee) ; Shehadeh, Mhd Ali (advisor)
Percepční systémy v autonomních vozech jsou v dnešní době intenzivně zkoumaným tématem a nezbytnou součástí potřebnou k vytvoření plně autonomních vozidel. Nejprve, stručně shrneme vývoj takových systémů, vysvětlíme si různé přístupy potřebné k vytvoření percepčních systémů a zaměříme se na detekci objektů, protože to bude naše hlavní část pro námi vytvořená systém. Nový model pro detekci objektů je , spolu s několika dalšími částmi jako odhad vzdálenosti a detekce jízdních pruhů.
|
guest ::
