|
|
Augmented Reality based on Planar Object and Local Image Features
Bárta, Milan ; Chrápek, David (referee) ; Beran, Vítězslav (advisor)
This bachelor's thesis deals with creating an augmented reality application which allows mapping of planar object and camera position localization with possibility of rendering additional information into the picture. Procedures used in image stitching process using local features are described in detail. These are the fundamental techniques for creating augmented reality applications. The thesis focuses on designing and implementation of such an application.
|
|
|
Robust Detection of Moving Objects in Video
Klicnar, Lukáš ; Herout, Adam (referee) ; Beran, Vítězslav (advisor)
Motion segmentation is an important process for separating moving objects from the background. Common methods usually assume fixed camera, other approaches exist as well, but they are usually very computational intensive. This work presents an approach for scene segmentation to regions with coherent motion, which works faster than similar methods and it is capable of online processing with no prior knowledge of objects or camera. The main assumption is that the points belonging to a single objects are moving together and this applies as well in the opposite direction. The proposed method is based on tracking of feature points and searching for groups with similar motion by using RANSAC-based algorithm. Short-range repair of broken tracks is applied to increase the overall robustness of tracking. Found clusters are subsequently processed to represent separate moving objects.
|
|
|
Camera Orientation in Real-Time
Župka, Jiří ; Herout, Adam (referee) ; Beran, Vítězslav (advisor)
This work deals with the orientation of the camera in real-time with a single camera. Offline methods are described and used as a reference for comparison of a real-time metods. Metods work in real-time Monocular SLAM and PTAM methods are there described and compared. Further, paper shows hints of advanced methods whereas future work is possible.
|
|
|
Object Detection Based on Edges
Caha, Jaroslav ; Švub, Miroslav (referee) ; Španěl, Michal (advisor)
This work presents a door detection method in images for mobile robot navigation. The method is able to detect doors in an input picture on the basis of found image edges. It is important to distinguish the door from similar objects like windows, paintings, or floor patterns. Therefore, the picture is divided into more parts (a floor, a wall, a ceiling) so that the potential placement of the door can be better drawn.
|
|
|
Analysis of ZED stereocamera in outdoor environment
Svoboda, Ondřej ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
The Master thesis is focused on analyzing stereo camera ZED in the outdoor environment. There is compared ZEDfu visual odometry with commonly used methods like GPS or wheel odometry. Moreover, the thesis includes analyses of SLAM in the changeable outdoor environment, too. The simultaneous mapping and localization in RTAB-Map were processed separately with SIFT and BRISK descriptors. The aim of this master thesis is to analyze the behaviour ZED camera in the outdoor environment for future implementation in mobile robotics.
|
|
|
Merging of Images and Video Sequences
Krym, David ; Seeman, Michal (referee) ; Zemčík, Pavel (advisor)
This bachelor thesis deals with image and video sequence frames stitching when the camera undergoes a pure rotation. It involves design and implementation of application with focus on quality and performance. Modern techniques and algorithms are used, such as SURF, ORB, k-nearest neighbors and bundle adjustment. The application is able to create a panoramic images automatically without any assumptions about the scene or camera.
|
|
|
Stitching of Retinal Images
Hladyuk, Vadym ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
The purpose of this work is to create a complete picture of the retina, by stitching together a number of partial photos. Since there is no working solution which would be able to capture the entire retina in one picture, this is an important problem to cover. The results will be demonstrated at the end of the text. The problem of stitching partial pictures together was solved by extracting vessels in retinal images, finding key points in images, finding common key points, calculating a transformation matrix and transforming one image into another. After a consultation with an ophthalmologist I was able to define steps which will allow me to further improve the work, which are analyzed in texts. The thesis will provide the reader knowledge about the eye apparatus. It will also introduce field of color models, image formats, algorithms for searching for key points, the transformation of the images themselves and it will also provide a possible way to compose retinal images and also suggest possible improvements.
|
|
|
Traffic Violation Detection on Crossroads
Karpíšek, Miroslav ; Bartl, Vojtěch (referee) ; Špaňhel, Jakub (advisor)
This bachelor thesis presents procedure for the detection of red-light violation. In the theoretical part of the thesis, the current solution aproaches used in image processing are described. The practical part focuses on creation of program for automatic traffic corridors detection, vehicle tracking and the current traffic light state detection. The results obtained by experimenting with the proposed procedure and the possibilities of its further improvement are also discussed.
|
|
|
Panorama Automatically
Motáček, Vladimír ; Španěl, Michal (referee) ; Beran, Vítězslav (advisor)
This paper concerns automatic panoramic image mosaicing. Images can be taken in any direction and in any order. This work uses basic technics such as Harris corner detection, correlation of image patches for finding correspondences and computing homography using RANSAC. The images are mapped to the reference image plane.
|
|
|
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 ::
