|
|
3D Reconstruction of Human Body Motion (MOCAP)
Černák, František ; Svoboda, Pavel (referee) ; Šolony, Marek (advisor)
This thesis deals with object recognition in image, motion capturing and his transformation into 3D coordination system and 3D reconstruction. The problem was solved by building stereo camera system, detection of markers on a moving object and getting his position in space using triangulation. Hit rate of 95% was achieved in marker detection at close range and accuracy of 3D reconstruction answers to reality at certain extend. The main finding of this work is that it is possible to reconstruct body motions with a pair of simple web cameras.
|
|
|
Movement Identification in the Space
Šolony, Marek ; Beran, Vítězslav (referee) ; Potúček, Igor (advisor)
The aim of this paper is to suggest optical system capable of movement identification in space and its reconstruction. The motion capture system uses markers attached to parts of human body, and a camera pair to capture the movement. This paper describes step-by-step parts of this system. Epipolar geometry is used to deal with problem of object correspondence between two views.
|
|
| |
|
|
Automatic Processing of Recordings from In-Car Camera
Klos, Dominik ; Herout, Adam (referee) ; Španěl, Michal (advisor)
This thesis deals with the automatic processing of recordings from in-car camera, which is used for estimating distances in a scene filmed. To achieve this goal, it uses the methods of image processing, spatial geometry of the scene and 3D reconstruction, whose final output is a partial model. For this aim, the Bundler tool is used. Results of reconstruction are visualized in the application, which then allows to estimate the distance of objects from the camera or the distance between each other.
|
|
|
3D Scene Reconstruction from Images
Ambrož, Ondřej ; Řezníček, Ivo (referee) ; Španěl, Michal (advisor)
Existing systems of scene reconstruction and theorethical basics necessary for scene reconstruction from images data are described in this work. System of scene reconstruction from video was designed and implemented. Its results were analyzed and possible future work was proposed. OpenCV, ArtToolKit and SIFT libraries which were used in this project are also described.
|
|
|
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 Localisation in 3D Space
Šolony, Marek ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
Virtual reality systems are nowadays common part of many research institutes due to its low cost and effective visualization of data. They mostly allow visualization and exploration of virtual worlds, but many lack user interaction. In this paper we suggest multi-camera optical system, which allows effective user interaction, thereby increasing immersion of virtual system. This paper describes the calibration process of multiple cameras using point correspondences.
|
|
|
Stereoscopic Navigation of a Robot
Žižka, Pavel ; Šolony, Marek (referee) ; Žák, Pavel (advisor)
This work describes 3D reconstruction using stereo vision. It presents methods for automatic localization of corresponding points in both images and their reprojection into 3D space. Application created can be used for navigation of a robot and object avoidance. Second part of the document describes chosen components of the robot. Path finding algorithms are also discussed, particulary Voronoi's diagram.
|
|
|
Common Image Stereo-Pair Processing for Simple Stereo-Geometry
Peloušek, Jan ; Schimmel, Jiří (referee) ; Říha, Kamil (advisor)
This Bachelor´s thesis considers the basics of epipolar geometry, explains the process of the automatic correspondency detection, describes principals of the fundamental matrix computation and finally the virtual camera view morphing between two images. There were described some of the basic Intel´s OpenCV library functions joined with this issue and describes de facto the computer stereo-pair processing. As a part of this thesis, there is the application, programmed in the C++ language in the Borland C++ Builder 6.0 developer´s environment by using the OpenCV library. This application demonstrates some of here-mentioned terms such as the fundamental matrix computation and the virtual camera view morphing. In relation to the Borland C++ Builder 6.0 using there was described the integration method of OpenCV to this environment.
|
|
|
Stereoscopic sensor for distance measurement
Vavroš, Ondřej ; Hasmanda, Martin (referee) ; Říha, Kamil (advisor)
This master's thesis will take us through theoretical procedure that allows us to determine the distance of an object by stereoscopic sensor. Part of this work presents the description of the steps to achieve image of objects, calibraton and rectification. At the next part our study provides an overview of algortihms for creating disparity maps and determining the distance of the object from sensor. In the following part of thesis deals with the implementation of these processes into aplication which aim is to measure the distance.
|
guest ::
