|
|
Recognition of Objects and Gestures in Image
Johanová, Daniela ; Beran, Vítězslav (referee) ; Zemčík, Pavel (advisor)
This thesis is focused on gesture recognition in video. The main purpose of this thesis was to create an algorithm and an application that can recognize selected gestures using a~video obtained through a~standard webcamera. The intention was to control an application program, such as video player. The approach used to achieve this goal was to exploit methods of feature extraction, tracking, and machine learning.
|
|
|
Mobile App for Measuring the Range from the Preceding Vehicle in Traffic
Henry, Andrii ; Zemčík, Pavel (referee) ; Herout, Adam (advisor)
This master's thesis deals with development of mobile app for measuring the range from the preceding vehicle in traffic using visual-based methods. This paper describes implementation of computer vision algorithms of detection and tracing objects, detection of horizon on desktop and mobile devices. Also deals with visual-based range measuring without any other mechanisms. The output of the work is implemented detectors of vihicles and horizon using OpenCV library on the Windows platfom and draft of user inerface of a mobile phone aplication on the Android platform.
|
|
|
Photorealistic Rendering Using "Photon Mapping" Method
Lysek, Tomáš ; Herout, Adam (referee) ; Zemčík, Pavel (advisor)
This master thesis focuses on photon mapping rendering technique. A simple photon mapping was implemented as a baseline and then progressive photon mapping was prepared for CPU and GPU. After implementing progressive photon mapping on GPU, further acceleration techniques were proposed. Finally, in the thesis, genetic clustering algorithm for suitable clusters on GPU was proposed.
|
|
|
Tabletop Object Detection
Varga, Tomáš ; Zemčík, Pavel (referee) ; Španěl, Michal (advisor)
This work describes the issue of tabletop object detection in point cloud. Point cloud is recorded with Kinect sensor. Designed solution uses algorithm RANSAC for plane detection, algorithm Euclidean clustering for segmentation and ICP algorithm for object detection. Algorithm ICP is modified and mainly it can detect rotational symetric objects and objects without any transformation against it's models. The final package is build on platform ROS. The achieved results with own dataset are good despite of the limited functionality of the detector.
|
|
|
Multispectral Map Building in Mobile Robotics
Burian, František ; Mazal,, Jan (referee) ; Zemčík, Pavel (referee) ; Žalud, Luděk (advisor)
The dissertation deals with utilisation of multispectral optical measurement for data fusion that may be used for visual telepresence and indoor/outdoor mapping by heterogeneous mobile robotic system. Optical proximity sensors, thermal imagers, and tricolour cameras are used for the fusion. The described algorithms are optimised to work in real-time and implemented on CASSANDRA robotic system made by our robotic research group.
|
|
|
Image Registration - Application in ophthalmology and ultrasonography
Harabiš, Vratislav ; Matula,, Petr (referee) ; Zemčík, Pavel (referee) ; Kolář, Radim (advisor)
Image registration is widely used in clinical practice. However image registration and its~evaluation is still challenging especially with regards to new possibilities of various modalities. One of these areas is contrast-enhanced ultrasound imaging. The time-dependent image contrast, low signal-to-noise ratio and specific speckle pattern make preprocessing and image registration difficult. In this thesis a method for registration of images in ultrasound contrast-enhanced sequences is proposed. The method is based on automatic fragmentation into image subsequences in which the images with similar characteristics are registered. The new evaluation method based on comparison of perfusion model is proposed. Registration and evaluation method was tested on a flow phantom and real patient data and compared with a standard methods proposed i literature. The second part of this thesis contains examples of application of image registration in~ophthalmology and proposition for its improvement. In this area the image registration methods are widely used, especially landmark based image registration method. In this thesis methods for landmark detection and its correspondence estimation are proposed.
|
|
|
Výhodnocení úspěšnosti obnovy lesa na požářišti Bzenec
Zemčík, Petr
The aim of this thesis was to evaluate successfulness of forestation at a seat of fire near Bzenec. Several types of planting stock varying in the type of species, plant cover, the way of growing and coverage by surrounding growths after planting were used. Two independent measurings were taken, during which shoot height, root crown thickness, growt length, losses, vitality, diversion from vertical, trunk straightness, damage by biotic agents (mainly by forest cockchafer), the weight of dry matter and root deformations were investigated. The paper strip method executed by a rotary cultivator proved to be little effective, because cockchafer grubs were not affected in any way when the soil was prepared this way. Big losses were found out already during spring evaluation. These losses doubled, even tripled, during a vegetation period. The losses were caused mainly by cockchafer grubs. It is possible to recommend suitable forestation of weeded areas by containerized planting stock of pine and bare-rooted broad-leaved trees as a possible solution.
|
|
|
Modeling Rwanda
Auda, O. ; Bečičková, H. ; Cincibuch, M. ; Čižmár, P. ; Hřebíček, H. ; Janjgava, Batlome ; Kameník, O. ; Katreniaková, D. ; Kejak, Michal ; Lamazoshvili, Beka ; Lukáč, J. ; Machala, J. ; Menkyna, Robert ; Musil, K. ; Rasulova, Khanifakhon ; Remo, A. ; Vávra, D. ; Vlček, J. ; Zemčík, Petr
The report consists of four chapters. Chapter 1 assesses the historical performance of forecasts for Rwanda. Historical forecasts since January 2010 are compared with the actual data as well as with projections of other institutions. Chapter 2 presents the structural macroeconomic model, its changes compared to the December 2009 version, and its properties captured by impulse-response functions and by variance decompositions of model’s variables in terms of the model shocks. Important is the part on the model-consistent interpretation of the recent economic Rwanda history. The section describing Bayesian vector autoregressions used for the near-term forecasting concludes. Chapter 3 evaluates how the models perform empirically. On the contrary to Chapter 1, the forecasting power is assessed both in the sample as well as by using an out-of-thesample comparison with the standard random-walk benchmark. We conclude that the FPAS performs satisfactorily in this comparison. The last chapter gives an overview of the considerable country database that has been compiled.
|
|
|
Modeling Ethiopia
Auda, O. ; Bečičková, H. ; Cincibuch, M. ; Čižmár, P. ; Hřebíček, H. ; Janjgava, Batlome ; Kameník, O. ; Katreniaková, D. ; Kejak, Michal ; Lamazoshvili, Beka ; Lukáč, J. ; Machala, J. ; Menkyna, Robert ; Musil, K. ; Rasulova, Khanifakhon ; Remo, A. ; Vávra, D. ; Vlček, J. ; Zemčík, Petr
The report has three chapters. Chapter 1 summarizes the main features of the Ethiopian economy relevant for building the forecasting and policy analysis system (FPAS). Chapter 2 presents the structural model, and near-term forecast models. Chapter 3 evaluates how the models perform empirically.
|
|
|
Modeling Haiti
Auda, O. ; Bečičková, H. ; Cincibuch, M. ; Čižmár, P. ; Hřebíček, H. ; Janjgava, Batlome ; Kameník, O. ; Katreniaková, D. ; Kejak, Michal ; Lamazoshvili, Beka ; Lukáč, J. ; Machala, J. ; Menkyna, Robert ; Musil, K. ; Rasulova, Khanifakhon ; Remo, A. ; Vávra, D. ; Vlček, J. ; Zemčík, Petr
The report has four chapters. Chapter 2 summarizes the main features of the Haitian economy relevant for building the forecasting and policy analysis system (FPAS). Chapter 3 presents the structural macroeconomic model and its properties captured by the decompositions of variances of the model’s variables in terms of the model shocks and by its impulse-response functions. This chapter also describes Bayesian vector autoregressions used for the near-term forecasting. Chapter 4 evaluates how the models perform empirically. The forecasting power is assessed both in the sample and by using an out-of-the-sample comparison with the standard random-walk benchmark. We conclude that the FPAS performs satisfactorily in this comparison.
|
guest ::
RSS feed.