|
|
Automatic People Counting from Panoramic Photography
Blucha, Ondřej ; Kolář, Martin (referee) ; Veľas, Martin (advisor)
This bachelor thesis deals with automatic people counting from panoramic photography. This is very useful for counting large number of people, such as on the stadium or on the concerts. It consists of the two parts. The first one is image stitching, which process the images by the feature-based methods. The second part is people counting using face detection, where were used Viola-Jones detector. The ideal setting of parameters for used methods was experimentally selected.
|
|
|
The Segmentation of Ultrasound Images for Artery Wall Detection and Intima-Media Thickness Measurement
Beneš, Radek ; Chromý,, Erik (referee) ; Dostál, Otto (referee) ; Říha, Kamil (advisor)
The thesis focuses on the measurement of intima media thickness, which seems to be a significant marker of the risk of cardiovascular events. Intima media thickness is measured in ultrasound image displaying the common carotid artery in its longitudinal section. In the longitudinal section the intima and media layers are visible. Thesis is discussing both technical and medical background and summarizes state of the art in this field. The main part of the thesis describes the novel automatic system for measurement of intima media thickness. Proposed system includes also robust method for artery localization and therefore is able to process raw B-mode data from ultrasound station without any initialization or manual preprocessing.
|
|
|
Birds Eye Panorama
Sobotka, Lukáš ; Pavelková, Alena (referee) ; Kolář, Martin (advisor)
The goal of this paper is to create panorama from the collection of photographies, which are taken from randomly moving device with OS Android. The device is placed on flying vehicle (a kite, a helium balloon, a drone etc.). The photographies are taken from birds eye view. The Android application was created and tested. This application creates a collection of photographies and then runs an algorithm to create panorama. This algorithm specifies descriptors using SURF, which are filtered by RANSAC algorithm for finding the optimal homography.This algorithm is perfomed iteratively over the collection. The image data is processed using the OpenCV library.
|
|
| |
|
|
Mobile Video Manual with Automatic Object Recognition
Nedbálek, Stanislav ; Maršík, Lukáš (referee) ; Španěl, Michal (advisor)
This thesis deals with potential of us computer vision and augmented reality on mobile platform - OS Android. The goal of this thesis is to demonstrate practical potential of mentioned technologies on nowdays real situations. This thesis aims to design and implementation of mobile application, which is able to show video manual for automatic detected object. The created application has been tested on group of users, which approved useability and intuitivness of this application.
|
|
|
Ellipse Detection
Hříbek, Petr ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The thesis introduces methods used for an ellipse detection. Each method is theoretically described in current subsection. The description includes methods like Hough transform, Random Hough transform, RANSAC, Genetic Algorithm and improvements with optimalization. Further there are described modifications of current procedures in the thesis to reach better results. Next to the last chapter represents testing parameters of speed, quality and accuracy of implemented algorithms. There is a conclusion of testing and a result discussion at the end.
|
|
| |
|
| |
|
|
Approximation surfaces for 3D data
Valachová, Alžbeta ; Novák, Jiří (referee) ; Procházková, Jana (advisor)
This bachelor thesis is dealing with approximation surfaces for 3D data using methods such as RANSAC, least square method and B-spline surface. Its goal is to study and program these methods. First, the methods are described and then the actual programs are analysed. In the end of the thesis, we compare all three methods using data from 3D scanning. Through this effort we can assess their positives and negatives.
|
|
|
Deep Neural Networks for Landmark Detection on 3D Models
Kubík, Tibor ; Kodym, Oldřich (referee) ; Španěl, Michal (advisor)
Detekcia významných bodov je častým krokom pri analýze medicínskych dát. Čoraz bežnejšie sú tieto dáta reprezentované vo forme 3D modelov, príkladom sú povrchové skeny zubného oblúka pacienta. Hlboké neurónové siete sú vhodný spôsob, ako detekovať významné body v obraze. V prípade 3D dát je však toto spracovanie časovo i pamäťovo náročné, čo nevyhovuje požiadavkám kladeným medicínskymi aplikáciami. V tejto práci navrhujem metódu, ktorá tento problém eliminuje a detekuje významné body na povrchu polygonálnych modelov čeľustí. V metóde sú použité rôzne architektúry neurónových sietí, založené na architektúre U-Net. Viacpohľadový prístup presúva spracovanie do 2D, kde navrhnuté architektúry detekujú body regresiou tepelných máp z niekoľkých pohľadov. Pomocou konsezus metódy je následne z týchto pohľadov určená konečná pozícia bodov v 3D priestore. V práci sú predstavené experimenty s dvoma konsenzus metódami: stredná hodnota predikcií a geometrický prístup založený na algoritme RANSAC a metóde najmenších štvorcov. Experimenty ukázali, že varianta kombinujúca Attention U-Net, 100 pohľadov a geometrickú konsenus metódu je schopná detekovať významné body s chybou 1.20 +- 1.81 mm, pričom 94.01% predikcií dosahuje chybu menšiu ako 2 mm.
|
guest ::
