|
|
Projected User Interface - Card Game
Brestič, Tomáš ; Kapinus, Michal (referee) ; Najman, Pavel (advisor)
Current effort to make human-computer interaction more intuitive leads to utilization of gestures replacing the need to use a conventional input device. At the same time there is a tendency to integrate the output into the physical world around the user and therefore to minimize any artificial means of interaction in general. The aim of this thesis is to implement a card game that can be controlled on the basis of the principles described above. Fundamental issues are human motion tracking, hand detection and gesture recognition. The application uses depth data from the second generation of Kinect sensor, analytical description of gestures and allows up to four players to play the game. Its graphics are projected on the table to maximize compliance with the real situation.
|
|
|
Depth-Based Determination of a 3D Hand Position
Ondris, Ladislav ; Tinka, Jan (referee) ; Drahanský, Martin (advisor)
Cílem této práce je určení kostry ruky z hloubkového obrazu a jeho následné využití k rozpoznání statického gesta. Na vstupu je hloubkový obrázek, ve kterém je nejprve detekována ruka pomocí neuronové sítě Tiny YOLOv3. Následně je obrázek zbaven pozadí a z takto předzpracovaného obrázku je určena kostra ruky v podobě 21 klíčových bodů neuronovou sítí JGR-P2O. K rozpoznání gesta z klíčových bodů ruky byla navržena technika, která porovná kostru na vstupu s uživatelem definovanými gesty. Funkcionalita systému byla otestována na vytvořeném datasetu s více než čtyřmi tisíci obrázky.
|
|
|
Gesture-Based Human-Computer Interface
Chaloupka, Jan ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This bachelor's thesis is about design and implementation of simple interface for hand gesture recognition. The interface is used as an extension of actual GUI elements. Skin color model is used for gesture segmentation, significant hand points (palm, fingers, fingertips) for gesture recognition. Designed interface is used for simple picture explorer controlling. Final application is capable of using simple gestures for scaling, rotation, pointing and click.
|
|
|
3D Drawing Using Leap Motion
Semerák, Jakub ; Zahrádka, Jiří (referee) ; Najman, Pavel (advisor)
The goal of this thesis was to create a simple 3D drawing application that uses Leap Motion controller. This application was designed to test gesture-based interaction versus keyboard controls. It was found that gesture-based interaction is not as effective as interaction combined with keyboard. However, when users interact with the application for a prolonged period of time, the noticeable acceleration of gesture-based interaction could be observed.
|
|
|
Hand gesticulation recognition in image
Mráz, Stanislav ; Petyovský, Petr (referee) ; Horák, Karel (advisor)
This master’s thesis is dealing with recognition of an easy static gestures in order to computer controlling. First part of this work is attended to the theoretical review of methods used to hand segmentation from the image. Next methods for hang gesture classification are described. The second part of this work is devoted to choice of suitable method for hand segmentation based on skin color and movement. Methods for hand gesture classification are described in next part. Last part of this work is devoted to description of proposed system.
|
|
|
User Interface with Mobile Device and Camera
Jelínek, Dalibor ; Kapinus, Michal (referee) ; Najman, Pavel (advisor)
This Bachelor thesis deals with development of user interface which will allow to control mobile device using camera and without use of hands. Thesis includes research on existing non-contact user interface sollutions and relevat computer vision techlologies. The output of the practical part is Android application which serves as a web browser that can be controlled exclusively by facial movements and voice.
|
|
|
Application Control Using Gestures
Lengál, Tomáš ; Zahrádka, Jiří (referee) ; Najman, Pavel (advisor)
This bachelor thesis deals with application control using sensor Microsoft Kinect. The main goal is to explore the possibility and the suitability of the sensor for gesture recognition and their using in control application. The work focuses on three main tasks. Namely, menu control, rotation control and trimming control.
|
|
|
Ground Vehicle Control by User Gestures
Chlud, Michal ; Materna, Zdeněk (referee) ; Beran, Vítězslav (advisor)
This bachelor's work is focused on basic methods leading to successful gesture recognition in video sequence using standard RGB camera. Key steps required for hand classification are described, mainly segmentation of input video based on skin color model. Next there are discussed methods for object tracking and gesture analysis. Main goal of this work is to demonstrate this knowledge by creating application which controls robot's movement by hand gesture analysis. Solution is proposed and individual implementation steps are described.
|
|
|
Active prostetic hand
Brenner, Maximilian ; Sekora, Jiří (referee) ; Harabiš, Vratislav (advisor)
BACKGROUND: Based on mainly vascular diseases and traumatic injuries, around 40,000 upper limb amputations are performed annually worldwide. The affected persons are strongly impaired in their physical abilities by such an intervention. Through myoelectric prostheses, affected persons are able to recover some of their abilities. METHODS: In order to control such prostheses, a system is to be developed by which electromyographic (EMG) measurements on the upper extremities can be carried out. The data obtained in this way should then be processed to recognize different gestures. These EMG measurements are to be performed by means of a suitable microcontroller and afterwards processed and classified by adequate software. Finally, a model or prototype of a hand is to be created, which is controlled by means of the acquired data. RESULTS: The signals from the upper extremities were picked up by four MyoWare sensors and transmitted to a computer via an Arduino Uno microcontroller. The Signals were processed in quantized time windows using Matlab. By means of a neural network, the gestures were recognized and displayed both graphically and by a prosthesis. The achieved recognition rate was up to 87% across all gestures. CONCLUSION: With an increasing number of gestures to be detected, the functionality of a neural network exceeds that of any fuzzy logic concerning classification accuracy. The recognition rates fluctuated between the individual gestures. This indicates that further fine tuning is needed to better train the classification software. However, it demonstrated that relatively cheap hardware can be used to create a control system for upper extremity prostheses.
|
|
|
Video-Based Human-Computer Interface
Chrápek, David ; Švub, Miroslav (referee) ; Španěl, Michal (advisor)
This bachelor´s thesis is focused on video-based human-computer interface controlled by movement of the whole head. By tracking relative positions of eyes and nose angles of head are determined and by movement of head simple gestures are recognized. For image processing Haar-cascades based on Viola-Jones of classifiers were used to recognize head, eyes and nose within the image and for their tracking mainly Lucas-Kanade optical flow method was used.
|
guest ::
