|
|
Figure trracking
Berka, Jiří Michael ; Řičánek, Dominik (referee) ; Richter, Miloslav (advisor)
This bachelor's thesis focuses on the development of software for tracking an exercising person and evaluating deviations from the correct execution of movement tasks. Initially, the thesis theoretically examines the fundamentals of digital image processing, the use of various types of cameras, and computer vision technologies. Subsequently, methods of artificial intelligence and deep learning that enable motion detection and analysis are described. The main part of the thesis focuses on the implementation of the OpenPose system for real-time pose estimation. Technical challenges are discussed, and solutions are proposed to achieve the accuracy and reliability of the system. The practical part includes testing the software on real videos and evaluating its performance. The results show that the developed software can effectively help in correcting movements and preventing injuries in various applications.
|
|
|
Alignment of Sports Pose Images
Kníže, Josef ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
The following thesis deals with image alignment based on sport pose of person in the image. The main result of this thesis is design and implementation of two systems for image alignment based on sport pose. The first system's focus is accuracy and it will be used to create dataset, which will be use to train neural network. Second system aimed at minimal hardware requirement, which was acomplished by using neural networks. Implemented neural net managed to sucessfuly align 81.98 % of images. A set of images, sorted based on the sport pose, has been created as a part of the solution.
|
|
|
Alignment of Sports Pose Images
Kníže, Josef ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
The following thesis deals with image alignment based on sport pose of person in the image. The main result of this thesis is design and implementation of two systems for image alignment based on sport pose. The first system's focus is accuracy and it will be used to create dataset, which will be use to train neural network. Second system aimed at minimal hardware requirement, which was acomplished by using neural networks. Implemented neural net managed to sucessfuly align 81.98 % of images. A set of images, sorted based on the sport pose, has been created as a part of the solution.
|
guest ::
