|
| |
|
| |
|
|
Efficient implementation of deep neural networks
Kopál, Jakub ; Mrázová, Iveta (advisor) ; Střelský, Jakub (referee)
In recent years, algorithms in the area of object detection have constantly been improving. The success of these algorithms has reached a level, where much of the development is focused on increasing speed at the expense of accuracy. As a result of recent improvements in the area of deep learning and new hardware architectures optimized for deep learning models, it is possible to detect objects in an image several hundreds times per second using only embedded and mobile devices. The main objective of this thesis is to study and summarize the most important methods in the area of effective object detection and apply them to a given real-world problem. By using state-of- the-art methods, we developed a traction-by-detection algorithm, which is based on our own object detection models that track transport vehicles in real-time using embedded and mobile devices. 1
|
|
|
Comparison of least squares methods for problems with errors in the model
Dvořák, Jan ; Hnětynková, Iveta (advisor) ; Kopal, Jiří (referee)
In this work we study the least squares and the total least squares problem for the solution of linear aproximation problems. We introduce both formulations and we discuss the existence and uniqueness of their solutions. We show selected computational methods based on the singular value decomposition. Further we focus on algebraic relations between both solutions and associated residuals. We present several estimates for the norm of the difference between the least squares and total least squares solution. We discuss their dependance on singular values of A and ( A b ) . Finally we illustrate the methods on selected test problems in the Matlab enviroment. 1
|
|
|
Local sharpness prediction and image segmentation
Kopál, Jakub ; Šikudová, Elena (advisor) ; Horáček, Jan (referee)
The problem of automatic segmentation turned out to be complicated andtothisday, notcompletelysolved.Sinceitisacomplexproblem,thispaperis not- tryingtosolveitinitsmostgeneralform. Instead,itisfocusedonautomatic, bina- rypicturesegmentation,withtheoptiontochooseattributes, basedonwhich the seg- mentation should operate. Among these attributes are the focus and color of the picture. The results of the segmentation based on the assumption "focused object, blurry background" turned out to be very similar to the groundtruth in pictures, which fulfill this assumption. 1
|
|
|
Deterministic Aperiodic Image Device
Horáček, Miroslav ; Meluzín, Petr ; Krátký, Stanislav ; Knápek, Alexandr ; Mika, Filip ; Chlumská, Jana ; Matějka, František ; Král, Stanislav ; Brunn, Ondřej ; Giričová, D. ; Kopal, Jaroslav ; Kolařík, Vladimír
The paper deals with the analysis, design and preparation of a diffractive optically variable imaging device consisting of a deterministic aperiodic mesh formed by basic optical elements. The theoretical basis is complemented by numerical analysis and presentation of the implemented master and its replicas.
|
|
|
Application of computational methods in classification of glass stones
Lébl, Matěj ; Hnětynková, Iveta (advisor) ; Kopal, Jiří (referee)
Application of computational methods in classification of glass stones Bc. Matěj Lébl Abstrakt: The goal of this thesis is to employ mathematical image processing methods in automatic quality control of glass jewellery stones. The main math- ematical subject is a matrix of specific attributes representing digital image of the studied products. First, the thesis summarizes mathematical definition of digital image and some standard image processing methods. Then, a complete solution to the considered problem is presented. The solution consists of stone localization within the image followed by analysis of the localized area. Two lo- calization approaches are presented. The first is based on the matrix convolution and optimized through the Fourier transform. The second uses mathematical methods of thresholding and median filtering, and data projection into one di- mension. The localized area is analyzed based on statistical distribution of the stone brightness. All methods are implemented in the MATLAB environment. 1
|
|
|
Freestyle skiing, New School.
Kopal, Jan ; Finková, Dana (advisor) ; Matošková, Petra (referee)
Univerzita Karlova v Praze, Fakulta tělesné výchovy a sportu Abstrakt Název práce: Freestylové lyžování, New School Freestyle skiing, New School Cíle práce: 2 Vytvořit komplexní pohled na New school freestylové lyžování a pomocí literární rešerše popsat problematiku freestylu ve vybraných oblastech. Metoda: Při řešení byla použita rešeršní metoda analýzy dokumentů, které se zabývají freestylovým lyžováním. Výsledky: Byl vytvořen ucelený pohled na problematiku New School freestylového lyžování. Vznikla tak práce, která se komplexně zabývá vznikem a vývojem New School ve světě a v ČR, freestylovými disciplínami, materialním vybavením a lyžařskými lokalitami pro freestyle. Klíčová slova: Freestyle, New School, freeskiing, lyžování, lyže.
|
|
| |
|
|
Epidemiology of viral hepatitis E
KOPAL, Jiří
To write this thesis, I chose a topic related to viral hepatitis E. In my opinion, this topic is clearly highly topical and the issue of VHE will be increasingly discussed in the future. Viral hepatitis are in general frequent diseases in developed countries, as well as in the Czech Republic. Nowadays there are known 5 types of hepatitis that to a greater or lesser extent occur in the population. In the Current Status section I will acquaint the reader with the basic anatomical and physiological patterns of functions and structures of the liver tissue, because viral hepatitis - as the name suggests - affects hepatocytes, thus the liver cells. Furthermore, I described from the literature all types of viral hepatitis and introduced differences which occur between them. In particular, I focused intensely on hepatitis E. Before writing this thesis I have identified several hypotheses and objectives. H1: The overall morbidity of VHE for the period 2000-2010 in the Czech Republic is comparable with morbidity in other European countries during the same period. H2: In the Czech Republic, the case of an infection of VHE is more of an occupational disease. From the available literature it was determined that the incidence of VHE in Europe is increasing. The literature also introduced several known cases of occupational disease of VHE for professionals working with pork or pigs and veterinarians, but these cases are rather sporadic. Thus, hypothesis 2 was not confirmed. In my thesis I have also determined a few objectives. Objective 1: To provide an overview of the prevalence of VHE for the period of 2000-2010 in Europe and in the Czech Republic and to determine whether the patterns of the spread of VHE differ in the Czech Republic and in Europe. Objective 2: To determine whether the case of viral hepatitis E in the Czech Republic is a greater occurrence as an occupational illness or a disease with a traveling history. Objective 3: To evaluate the efficacy of preventive and anti-epidemic measures which are applied as a protection against the infection with hepatitis E. The overview of the incidence of infection is presented in tables and graphs in the chapter Results, part of it is listed in the chapter Attachments. Scientific researches of VHE are still basically in the world and in Europe at their beginning. From the literature, I found that not only in Czech Republic but also in other European countries, the VHE is more abundant. Currently it is not known much unambiguous information that would lead to improved effectiveness transmission prevention of VHE in developed countries. Increase in incidence of VHE is here attributed to more frequent examinations of chronic liver disease, thorough diagnosis of drug-induced liver failure and other diseases whose cause has not been definitely clarified. Until recently, the idea of VHE infection amongst patients with no history of traveling was almost taboo. Only further research in this area may help us to better understand the disease and to ensure the prevention, diagnosis and specific treatment. In the meantime, we should follow the precautionary principle.
|
guest ::
RSS feed.