|
|
Surface Reconstruction from Point Clouds
Knot, Stanislav ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This diploma thesis deals with the processing of point clouds captured by the Kinect sensor from single position. As part of this thesis an application was designed, which is able to register and reconstruct surface using selected methods. The registration of overlapping frames is based on computation of key points and their FPFH histograms from which the estimation of correspondence is computed. This estimation is then refined and redundant point filtering is performed. Surface is reconstructed from the registered and modified point cloud using Greedy Projection Triangulation. All computations are performed offline. The output of this application is textured polygonial model and an image for texture creation. With assumption of correctly set parameters the results are in a good quality for creation of virtual tours and visualization.
|
|
|
The Use of Photogrammetry in the Real Estate Practice
Viktora, Jakub ; Daňhel, Petr (referee) ; Klika, Pavel (advisor)
This diploma thesis aims to explore possibilities of using IT in real estate and projection practice. It deals with simplification of difficult or insolvable tasks. It focuses on rapidly developing field of photogrammetry and its further processing via software. The work presents methods of measurement of existing realties without using standard methods (tape line, laser). Instead of these tools, the author uses photographic data and program PhotoModeler for surveying and creating a 3D model of the facade. The thesis verifies further serviceability of gained data up to the render phase of the surveyed building facade.
|
|
|
Localisation of Mobile Robot in the Environment
Němec, Lukáš ; Hradiš, Michal (referee) ; Veľas, Martin (advisor)
This paper addresses the problem of mobile robot localization based on current 2D and 3D data and previous records. Focusing on practical loop detection in the trajectory of a robot. The objective of this work was to evaluate current methods of image processing and depth data for issues of localization in environment. This work uses Bag of Words for 2D data and environment of point cloud with Viewpoint Feature Histogram for 3D data. Designed system was implemented and evaluated.
|
|
|
Head Pose Estimation and Tracking
Pospíšil, Aleš ; Krajsa, Ondřej (referee) ; Přinosil, Jiří (advisor)
Diplomová práce je zaměřena na problematiku detekce a sledování polohy hlavy v obraze jako jednu s možností jak zlepšit možnosti interakce mezi počítačem a člověkem. Hlavním přínosem diplomové práce je využití inovativních hardwarových a softwarových technologií jakými jsou Microsoft Kinect, Point Cloud Library a CImg Library. Na úvod je představeno shrnutí předchozích prací na podobné téma. Následuje charakteristika a popis databáze, která byla vytvořena pro účely diplomové práce. Vyvinutý systém pro detekci a sledování polohy hlavy je založený na akvizici 3D obrazových dat a registračním algoritmu Iterative Closest Point. V závěru diplomové práce je nabídnuto hodnocení vzniklého systému a jsou navrženy možnosti jeho budoucího zlepšení.
|
|
|
Surface Reconstruction from Point Clouds
Jarůšek, Tomáš ; Zemčík, Pavel (referee) ; Španěl, Michal (advisor)
Surface reconstruction from point clouds represents very modern and widespreadly used method for digitalization of real surfaces. The main focus of this work is on a comparison of several algorithms (Poisson surface reconstruction, Ball Pivoting Algorithm, Fourier surface reconstruction, Wavelet surface reconstruction and Multi-level Partition of Unity implicits) that reconstruct original surface in a form of triangle mesh from an oriented point cloud. Every algorithm was used in a series of tests on both real and synthetic datasets which were also modified to suit more complicated experiments. The following evaluation is done in various categories. The results are evaluated both visualy and with calculated measures (such as Hausdorff distance). Together these experiments depict a detailed analysis of the state of surface reconstruction algorithms. Our experimets show that the selection of optimal algorithm depends on a concrete task. Overall Possion surface reconstruction and Fourier surface reconstruction provide the best results.
|
|
|
Better Chaperone Bounds Using 3D Sensors
Tinka, Jan ; Beran, Vítězslav (referee) ; Najman, Pavel (advisor)
Room-scale tracking encourages users to move more freely and even walk. Even though there has been much research on making the limited physical workspace feel larger in the VR, these approaches have their limitations and require certain conditions to be met. This thesis proposes an alternative approach to the conventional play-area boundaries of high-end VR products such as the HTC Vive and Oculus Rift which are set by the user in a 2-D fashion as a means of enhance workspace utilization. A 3-D scanner is used to make a 3-D point-cloud model of the play area's surroundings. This model is then used to detect collisions and provide feedback to the user. Evaluation based on user tests showed that this approach can be useful, is well accepted by users and might be worth further research.
|
|
|
Processing of images taken from UAV
Ptáček, Ondřej ; Plánka, Ladislav (referee) ; Hanzl, Vlastimil (advisor)
This diploma thesis deals with the processing and evaluation of the pictures taken by unmanned aerial vehicles - UAV. The introductory part is devoted to the definition, use, applications and types of UAV especially for photogrammetric purposes. Also the software equipment is described, including a description and examples of several types of possible outcomes. Further the measurements, computational works and process of elaboration in used software programs are described. Achieved outcomes of elaboration are also presented. In conclusion, the overall evaluation and assessment of the results of measurement is done of set of points.
|
|
|
Object Detection Using Kinect
Němec, Lukáš ; Veľas, Martin (referee) ; Španěl, Michal (advisor)
This paper address the problem of object recognition using Microsoft Kinect in the fi eld of computer vision. The objective of this work was to evaluate current methods of detection of objects using depth map (RGB-D sensor). The work deals with the enviroment of point cloud and Viewpoint Feature method. It also describes the use of binary classifi er in the context of object recognition. Object detection was implemented and performed experiments with it.
|
|
| |
|
|
Creation of 3D model of building using laser scanning
Sabo, Stanislav ; Kalvodová, Petra (referee) ; Kalvoda, Petr (advisor)
The aim of this thesis is to scan the part of the interior and exterior of the Faculty of Electrical Engineering and Communication building using the FARO Focus3D X 130 scanner, and the creation of a 3D model in the WGS 84 system. Subsequently, methods, status and utilization research of this technology and point cloud processing software is provided. The collected data are processed in the SCENE. Three-dimensional model is designed using the Pointfuse and Microstation V8i programs. In the end, the registration accuracy of the scans and the resulting 3D model accuracy are evaluated.
|
guest ::
