|
|
Robotic Shopping Cart
Kuřátko, Jiří ; Beran, Vítězslav (referee) ; Materna, Zdeněk (advisor)
This bachelor’s thesis deals with the project of application about planning the robot’s movement in order to follow the specified person. At the beginning of the work, the Microsoft Kinect sensor which is used for sensing nearby objects is described. Hereinafter the possible methods how to identify human figures on the basis of depth data from the Microsoft Kinect sensor are discussed as well. The reader is also familiar with the methods determining the direction of arrival of acoustic signals. Last chapters of the work are dedicated to the motion control of the robot. Finally the complete implementation of the robot software for the platform of Robotic Operating System (ROS) is described.
|
|
| |
|
|
Kinect-Based Gesture Recognition
Zapletal, Filip ; Šolony, Marek (referee) ; Žák, Pavel (advisor)
This paper describes methods of obtaining position data of individual body parts using different technologies, with particular focus on Kinect. Based on this knowledge was designed and implemented library for the detection of dynamic motion gestures, which has been tested on a set of designed gestures.
|
|
|
User Hand Detection in Depth Data
Malík, Pavol ; Šimon, Martin (referee) ; Beran, Vítězslav (advisor)
The aim of this thesis is to detect hand of user above the interactive table and show its position with respect to the table. Used sensor was Kinect so the depth data approach was selected. The detection is realized using registration method SAC-IA, which works on the template matching principle. Thesis deals with existing solutions of hand detection as well as procedure used in this work. Dataset was defined, containing hand templates and testing scenes, from which the classifier was evaluated. Final testing was performed on more than a hundred objects and the success rate reached 82 %.
|
|
|
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.
|
|
|
Projected User Interface - Dungeons & Dragons
Dymáček, Petr ; Kapinus, Michal (referee) ; Najman, Pavel (advisor)
This thesis deals with the using of an interactive table for playing Dungeons & Dragons board game. Application, that was made, is controlled by touch screen and gestures. The gestures are detected from depth data captured by Kinect. The work solves calibrations of input devices and the design of the user interface appropriate for the application.
|
|
|
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.
|
|
|
Board Games on Interactive Table
Svoboda, Petr ; Najman, Pavel (referee) ; Beran, Vítězslav (advisor)
This thesis focuses on the application of the tangible user interface and spatial augmented reality principals for playing board games. For this purpose, a system called interactive table was developed. It is both hardware and software solution. The hardware part solves the installation of a depth camera and a projector located above the table. The software solution deals with calibration of the depth camera and projector system using known procedures for camera calibration on the one hand, on the other hand it solves tasks from the field of computer vision. This perceptional part is the core of the whole thesis and for the purposes of playing board games it provides information about the location of the physical game object, physical game board and the calculations of mask for masking distracting objects. An educational application was developed for the purposes of demonstration of the system options. The interactive table offers new possibilities for playing board games in a real-world environment by the combination of the augmented reality elements with real-world objects and the related new user experience.
|
|
|
Robotic Mirror
Vopálenský, Radek ; Materna, Zdeněk (referee) ; Kapinus, Michal (advisor)
The aim of this work is to design and implement a module through which robotic platform PR2 repeated movements of a man standing before her. User's movement is sensed using Kinect and detected by monitoring skeletal model. The embedded module can control robotic head, robotic arms and move the base in all directions. The work describes all the technologies used, description and design solutions and test results.
|
|
|
Doors and Door Handle Localization for PR2
Botka, Roland ; Španěl, Michal (referee) ; Kapinus, Michal (advisor)
The aim of this work is to design and create a module for locating doors and handles for the robotic platform PR2. Finding the doors should be done separately, which means that the robot finds a door in the room without assistance. Handle position is stored in a file which the data are read from based on the AR code affixed to the door. The result of this module should be a program for the Robotic operating system that will locate the door in the room, and give information about them. These informations will be the basis for the work of another module, which open the door. The final test took place in a faculty robotic laboratory
|
guest ::
