|
|
Processing of Stereoscopic Video Sequence
Hasmanda, Martin ; Šmirg, Ondřej (referee) ; Říha, Kamil (advisor)
The main goal of this master’s thesis was get up used methods for observation the stereoscopic scene with one couple of cameras and find out good solving for processing these resulting pictures for two-view and multiple-view autostereoscopic displays for three-dimensional perception. For methods for acquisition video was introduced two methods. They were method “Off-axis” with parallel camera axis and method “Toe in” with intersections axis. For fit method was choice the method named as “Off-axis“. It was not produces the vertical parallax and in detail was in this work described principle of this method. Further were describe principles off used methods for three-dimensional perception namely from the oldest method named anaglyph after methods for viewing at autostereoscopic displays. The Autostereoscopic displays were main goal of this thesis and so their principles were described in details. For production the result image for autostereoscopic displays was used generation intermediate images between left and right camera. Resulting videos were acquisition for testing scene in created in 3D studio Blender, where was possible setting system of cameras exactly parallel axis. Then were introduce principles processing video where was extract from the couple of cameras where were connected to PC for help digitizing card and next time with two web cameras. Here is not guaranteed exact parallel axis system. Therefore this work try for real cameras achieve exactly parallel axis system by the help of transformations of frames with stereo rectification. Stereo rectification was solving with OpenCV libraries and was used two methods. Both methods work from principles epipolar geometry that was described in this work also in detail. First method rectifies pictures on the basis fundamental matrix and found correspondences points in two images of the scene and second method rectifies pictures from knowledge intrinsic and extrinsic parameters of stereoscopic system of cameras. In the end of this work was described application for implementation introduced methods.
|
|
|
MR image data processing in study of tissue cultures
Bidman, Petr ; Šmirg, Ondřej (referee) ; Gescheidtová, Eva (advisor)
Techniques based on principle of nuclear magnetic resonance (NMR) belong to the most modern methods for studying physical, chemical and biological properties of materials [1]. Their universality predestinates them for application in a wide range of scientific disciplines, e.g. in medicine to study properties of tissues. Advantages of techniques utilizing principle of NMR consist in their noninvasiveness and thoughtfulness to human health or studied material. In addition, no undesirable effects of magnetic force field have been so far proved by research. Objectives of this Diploma Thesis are evaluation of MR images of tissue cultures and determination of protons amount included in them. Theoretic part of the Thesis is devoted to the bases of NMR and provides basic overview of MR methods. The spin echo method (SE) is described in more details, including the process of assessment of technique’s parameters, e.g. general magnetization. Practical part of Diploma Thesis is focused on determination of integral of image intensity of clusters of early somatic embryos. Intensity integrals characterizing number of protons in growing cluster were calculated from MR images of spruce embryos contaminated by lead. The intensity of an image weighted by spin density is proportionate to the number of proton nuclei in the chosen slice. The Thesis describes further evaluation of relaxation time T2 from MR images weighted by spin density. Following part is dealing with determination of diffusion from MR images with application of compensation methods, three-measurement arrangement and presentation of obtained results. Images were processed by use of MATLAB and MAREVISI programs.
|
|
|
Automatic Verification of Product Assembling Correctness
Doležal, Petr ; Šmirg, Ondřej (referee) ; Říha, Kamil (advisor)
This diploma evaluates methods for verification of key characteristics of a product using digital image processing techniques. At first, reasons why this work has been done are described followed by a list of all methods that were used in this diploma such as Hough Circle Transform and Flood Fill (Seed Fill) algorithm. Also, a new approach how to compensate non regularly illuminated scene, which is based on surface modeling with Bézier Surfaces, was developed. Moreover, the algorithm was implemented in the C++ programming language and some of the parts were also simulated using the MATLAB environment. The algorithm was evaluated based on the percentage level of recognition of the required parameters. Efficiency of the implementation is also important for the author.
|
|
|
A realization of modular web system
Kašparec, Michal ; Šmirg, Ondřej (referee) ; Koutný, Martin (advisor)
This bachelor thesis describes the current conception of PHP frameworks and their main characteristics. Creating the content management system with using sophisticated administration interface and access rights. There is realization a module for recording and evaluation of power consumption with enabling to display the power consumption.
|
|
|
Detection of parts of human body in an image
Křivánek, Filip ; Přinosil, Jiří (referee) ; Šmirg, Ondřej (advisor)
This thesis deals with algorithms for human figure detection in video. It describes, practically tests and evaluates algorithms called Histogram of Oriented Gradients and Haar Cascade Classifier. Testing program was written in C++ language with use of OpenCV library. The aim is to find the approximate location of individual body parts in the area of the detected human figure. The detection was tested on a video sequence and various image processing methods were selected. Techniques such as thresholding, background subtraction, finding the largest of contours or optical flow were employed. The result of thesis is to find points which represent concrete body part.
|
|
|
Object Description in Images
Dvořák, Pavel ; Šmirg, Ondřej (referee) ; Zukal, Martin (advisor)
This thesis consider description of segments identified in image. At first there are described main methods of segmentation because it is a process contiguous before describing of objects. Next chapter is devoted to methods which focus on description identified regions. There are studied algorithms used for characterizing of different features. There are parts devoted to color, location, size, orientation, shape and topology. The end of this chapter is devoted to moments. Next chapters are focused on designing fit algorithms for segments description and XML files creating according to MPEG-7 standards and their implementation into RapidMiner. In the last chapter there are described results of the implementation.
|
|
|
Advanced QR-Code reader for Android
Kubík, Martin ; Přinosil, Jiří (referee) ; Šmirg, Ondřej (advisor)
The aim of this diploma thesis was to created application for detection and decoding QR codes using devices with the Android Operating System. For preprocessing of the visual field camera is used OpenCV library. Designed preprocessing string searches a perspective transforms possible QR codes. This is suppressed a shape distortion QR code that would otherwise reduce the successful decoding. At the same time the preprocessing string applied unsharp mask, which reduces the effect of motion blur image caused by the camera motion. Thus preprocessing scene is finally decoded using ZXing library. Described manner it is possible to achieve a higher success rate detection and decoding of QR codes than other conventional QR readers.
|
|
|
Multiparametric segmentation of MR images
Chovanec, Ján ; Šmirg, Ondřej (referee) ; Dvořák, Pavel (advisor)
The aim of the thesis was familiarity of segmentation methods for automatic segmentation of MR images, using multiparametrical display. The theoretical part focuses on the description of methods of segmentation techniques. In the practical part are implemented K-means and level-set method. The methods are tested on the images of the brain obtained by different sequences (T1, T1c, T2, FLAIR). Segmentation methods are implemented in the program MATLAB. Implemented segmentation accuracy is demonstrated on data which there are reports reference results. Evaluation methods is performed using different classifiers decision. The K-means method is tested different metrics and different combinations of the input image. Finally, both methods are compared with one another and visually evaluated against the reference image.
|
|
|
Videoconferencing Application
Jandera, Pavel ; Šmirg, Ondřej (referee) ; Číka, Petr (advisor)
Videoconferencing is a modern way of communication, in which the participants carry picture and sound and during transmission can also exchange various data. The aim of this work is to create an application for the connection of up to eight participants to videoconferencing and create a web interface to facilitate configuration of this application. Videoconferences types and the feasibility are described in the first part of this work. Furthermore, the SIP (Session Initiation Protocol) protocol used to production of multimedia sessions is described. RADVISION IVP system was selected to the implementation of videoconferencing application. IVP is a complex system for the operation of videoconferencing, which allows implementing and operating various types of services. Basic components of system are described in next section of this work. Second part of this work describes interface for applications creating that IVP offers to programmers. The main part of this work is the design and implementation of video conferencing application that is realized as an IVP service. There is described the implementation and testing. A web interface to facilitate the configuration of video conferencing applications has been designed and implemented. This interface also allows the service provider to manage user accounts. The web interface was implemented in Java EE.
|
|
|
Methods for automated camera focusing
Kičina, Pavol ; Rášo, Ondřej (referee) ; Šmirg, Ondřej (advisor)
This bachelor´s thesis is about methods of focusing with web camera. Edge detection method and Discrete cosine transform method are use in this thesis. In program MatLab I create a program, which take a picture from web camera. With handle focusing this program shows information how much is picture focus. Functional and elementary are subject, which I use to compare. Advantages and disadvantages are in this thesis, with important elements about quality of focus,too.
|
guest ::
