|
| |
|
|
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.
|
|
|
Target tracking
Černín, Jan ; Horák, Karel (referee) ; Janáková, Ilona (advisor)
The subject of this bachelor thesis was to program an algorithm, which would be able to process image data from connected camera. Real-time application is working with data in basic of evaluated position of the object and control robotic head that turns and follows selected target. Whole algorithm implements two methods of tracking which are written in program language C/C++ using functions of OpenCV library.
|
|
|
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.
|
|
| |
|
|
moving objects tracking
Bradáč, František ; Gogol, František (referee) ; Richter, Miloslav (advisor)
The thesis deals with founding and tracking of moving objects inside of visual field and prediction of their future position. The created methods combine few approaches for solution this problem. First, the most probable of the static part of the observed scene is created. Then this model is used to detect moving objects. The correspondence of objects between two consecutive pictures is performed by analyzing of motion of these objects. For analyzing of motion of the objects optical flow is used. Prediction of the future position is performed by Kalman filter. Providing suitable condition these methods are able to track the moving objects even if these objects are passing closely or colliding. The methods are implemented in language C++ and their functionality was verified by sample with scanned non static scene.
|
|
| |
|
| |
|
|
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.
|
|
|
Target tracking
Černín, Jan ; Horák, Karel (referee) ; Janáková, Ilona (advisor)
The subject of this bachelor thesis was to program an algorithm, which would be able to process image data from connected camera. Real-time application is working with data in basic of evaluated position of the object and control robotic head that turns and follows selected target. Whole algorithm implements two methods of tracking which are written in program language C/C++ using functions of OpenCV library.
|
guest ::
