|
|
Using the Kinect sensor in detection of people
Janás, Lukáš ; Šmirg, Ondřej (referee) ; Přinosil, Jiří (advisor)
Bachelor thesis deals with the methods of people detection by using Microsoft Kinect. Depth image captured by this device is further processed by using standard algorithms from freely available OpenCV library. All of image processing methods are described in detail of their function and influence to image. The practical part of the work is focused on the realization of a simple program, which is serving for image segmentation and finding people.
|
|
| |
|
|
Better Chaperone Bounds Using 3D Sensors
Tinka, Jan ; Beran, Vítězslav (referee) ; Najman, Pavel (advisor)
Room-scale tracking encourages users to move more freely and even walk. Even though there has been much research on making the limited physical workspace feel larger in the VR, these approaches have their limitations and require certain conditions to be met. This thesis proposes an alternative approach to the conventional play-area boundaries of high-end VR products such as the HTC Vive and Oculus Rift which are set by the user in a 2-D fashion as a means of enhance workspace utilization. A 3-D scanner is used to make a 3-D point-cloud model of the play area's surroundings. This model is then used to detect collisions and provide feedback to the user. Evaluation based on user tests showed that this approach can be useful, is well accepted by users and might be worth further research.
|
|
|
Leg Bone Posture Analysis Using Microsoft Kinect One
Tatýrek, Ondřej ; Jelínek, Aleš (referee) ; Chromý, Adam (advisor)
This master thesis is engaged in development of software tool intended for measuring of status of lower limb bones. It analyzes status of the feet and lower limb and defines significantpointsonthem.Alsoanalyzesdesignoptionsofmeasuringsceneandmarkers and describe the one selected. In another part is described automated point recognition algorithm. The last part describes graphical user interface, where are these algorithms implemented.
|
|
|
Object Detection Using Kinect
Němec, Lukáš ; Veľas, Martin (referee) ; Španěl, Michal (advisor)
This paper address the problem of object recognition using Microsoft Kinect in the fi eld of computer vision. The objective of this work was to evaluate current methods of detection of objects using depth map (RGB-D sensor). The work deals with the enviroment of point cloud and Viewpoint Feature method. It also describes the use of binary classifi er in the context of object recognition. Object detection was implemented and performed experiments with it.
|
|
|
Object Detection on Robotic Workplace Using Two Kinects
Dragúň, Peter ; Beran, Jan (referee) ; Rozman, Jaroslav (advisor)
This thesis deals with the use of a multi-depth camera Microsoft Kinect V2 for object pose estimation. The main emphasis is on calibration, including mutual and also calibration of a single camera. Which is critical for correct transformation. The theoretical part thesis describes methods for object detection and their pose estimation in space using the robotic operating system. The practical part thesis describes resolving issues with USB saturation by adding a single board computer based on ARM architecture for secondary Kinect.
|
|
|
Vizualizace virtuálních objektů v reálném prostoru s využitím nástroje Unity
Mikulka, Radek
This master thesis is focused on visualization of virtual objects in the real space. The introductory section provides a brief description of Kinect and Unity technologies. Moreover, similar state-of-the-art projects are outlined with regard to the used methodics of interaction. Subsequently, a review of useful libraries is provided. On the basis of these information, the methodics of my project is formu-lated. The subsequent part of the thesis deals with the implementation of experi-mental application in the C# programming language. Finally, the application is evaluated and there is a discussion of its pros and cons.
|
|
|
Inteligentná pracovná plocha
Kozák, Jakub
Interactive collaborative enviroments are solved by many companies and research teams. This thesis is focused on design and development of own system for gesture recognition based on Microsoft Kinect controller. The system is focused on collaboration of multiple users. Therefore, proposed solution can distinguish interactions of different users. The result allows to create an interactive area from a common wall using a computer, projector and Kinect controller.
|
|
|
Better Chaperone Bounds Using 3D Sensors
Tinka, Jan ; Beran, Vítězslav (referee) ; Najman, Pavel (advisor)
Room-scale tracking encourages users to move more freely and even walk. Even though there has been much research on making the limited physical workspace feel larger in the VR, these approaches have their limitations and require certain conditions to be met. This thesis proposes an alternative approach to the conventional play-area boundaries of high-end VR products such as the HTC Vive and Oculus Rift which are set by the user in a 2-D fashion as a means of enhance workspace utilization. A 3-D scanner is used to make a 3-D point-cloud model of the play area's surroundings. This model is then used to detect collisions and provide feedback to the user. Evaluation based on user tests showed that this approach can be useful, is well accepted by users and might be worth further research.
|
|
|
Using the Kinect sensor in detection of people
Janás, Lukáš ; Šmirg, Ondřej (referee) ; Přinosil, Jiří (advisor)
Bachelor thesis deals with the methods of people detection by using Microsoft Kinect. Depth image captured by this device is further processed by using standard algorithms from freely available OpenCV library. All of image processing methods are described in detail of their function and influence to image. The practical part of the work is focused on the realization of a simple program, which is serving for image segmentation and finding people.
|
guest ::
