|
|
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.
|
|
|
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.
|
|
|
3D model
Sládeček, Martin ; Petyovský, Petr (referee) ; Richter, Miloslav (advisor)
This paper concerns the task three-dimensional scene using image sequence obtained with an ordinry camera. First portion of this thesis outlines the principles used in solving of the task, the second chapter describes a reconstucion algorithm and it's implementation in the Python programming language. The output of this program is demonstrated on several selected scenes. Final remarks discuss the quality of resulting models, shortcomings of the program and possible improvements.
|
|
|
Detection and Correspondence of Image Features
Hasmanda, Martin ; Kohoutek, Michal (referee) ; Říha, Kamil (advisor)
The main goal of this bachelor‘s thesis was obtain basic knowledge about image processing. Especially was this work specialized on features detection in images captured from different perspectives and for finding correspondences between those images. Preliminary were to be described the basic principles for understanding computer vision such as perspective projection, description model of the camera and two views geometry. From methods of the detection was introduced best-known and most widely used of the detectors Harris corner detector. He is independent of images rotation and he is analyzed in detail. Further was described SIFT detector, that is independent of images scale. In this work further be described to several methods for finding correspondences of images features. First were to be described and derived two basic transformation matrixes that arrange to the association with features of two images. The first homography matrix describes transformation of two 2D views and fundamental matrix. Fundamental matrix obtains from two images full information of captured 3D scene and projection matrixes of cameras. For to primary definition correspondences were to be used to methods SSD and NCC. These methods match correspondences after similarities surroundings of features. These methods unfiled correct assignment features. Therefore uses stochastic RANSAC algorithm. The RANSAC algorithm was in detail described in this work in basic form and further modified on MLESAC algorithm. This algorithm can find better correspondences than RANSAC. In the end was described simple application for implementation introduced methods.
|
|
|
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.
|
|
|
3D Reconstruction from two views
Myška, Milan ; Minář, Jiří (referee) ; Hasmanda, Martin (advisor)
This bachelor thesis deals with 3D reconstruction process using two 2D pictures of one scene taken with uncalibrated cameras. The first chapter focuses on mathematical theory behind this process. Epipolar geometry, locating keypoints method SURF, fundamental matrix, stereo rectification and stereo correspondence using block-matching method are explained here. The next chapter of my thesis describes a practical view of this topic and my own C++ program is introduced at the same time.
|
|
|
3D Reconstruction from two views
Myška, Milan ; Minář, Jiří (referee) ; Říha, Kamil (advisor)
This bachelor thesis deals with 3D reconstruction process using two 2D pictures of one scene taken with uncalibrated cameras. The first chapter focuses on mathematical theory behind this process. Epipolar geometry, locating keypoints method SURF, fundamental and essential matrix, projection matrices, stereo rectification process and searching for stereo correspondences are explained here. The next chapter of my thesis describes a practical view of this topic and my own C++ program is introduced at the same time.
|
|
|
3D model from multiview
Zemčík, Tomáš ; Klečka, Jan (referee) ; Richter, Miloslav (advisor)
Reconstruction of 3D model from multiple view images allows us to perform a contactless measurement of real world objects. This work contains theoretical and mathematical background necessary for understanding problems of 3D reconstruction. It also proposes possible hardware and software solutions for the task of measuring a hood with EEG sensors while on patients head.
|
|
|
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.
|
|
| |
guest ::
