National Repository of Grey Literature 525 records found  previous11 - 20nextend  jump to record: Search took 0.00 seconds. 
Self-Supervised Learning for Recognition of Hand Poses in Image
Makaiová, Lucia ; Kocur, Viktor (referee) ; Herout, Adam (advisor)
This work focuses on using self-supervised learning for the task of hand poses recognition in image. I have used contrastive method of self-supervised learning and optimized the solution iteratively, using techniques such as early stopping, triplet mining, optimization of hyperparameters or experimenting with various model architectures. The method was implemented with Pytorch framework and Tensorboard was used for data processing and visualization. I have trained the first model using a supervised method, to obtain reference values. I have successfully matched this reference result by training a self-supervised model on Handz dataset and achieving 83% accuracy. The created solution provides findings, which can be applied to similar problems, such as recognition of sport poses. The main contribution of this work is the discovery, that self-supervised methods are particularly effective when using a labeled dataset for downstream task with just a small amount of samples, which in addition have uneven distribution of samples for individual classes. Based on these findings, it is possible to create a method for self-supervised learning for recognition of sport poses or further optimize existing solution for hand poses.
iOS aplikace pro záznam krátkých sportovních videí
Nácar, Arthur ; Tesařová, Alena (referee) ; Herout, Adam (advisor)
The content of this work is a mobile application for the iOS platform. The application is aimed at athletes, whom it should help during their training, and serves as a tool for automatically recording short snippets of video. The implementation is in Swift using the AVFoundation framework. The application has implemented the human pose detector using the CoreML model and can recognize certain game moments which will be captured. The short video snippet recorded with this application then contains the few seconds that preceded the game moment and also the few seconds that followed.
Znovupoužitelný 2D editor pro webové aplikace
Schneider, Martin ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
The goal of this work is to implement a 2D editor as a library for web applications together with a test application. The library primarily targets segmentation neural network and remote use environments with optimizations for data transfer. First, the reader is introduced to frontend application development with a focus on 2D graphics editing and image data display. Next, an analysis of the needs for a 2D editor with applications to annotation editing and displaying results in computer vision tasks is presented. The result of the analysis is then converted into a system design, which is subsequently implemented and tested.
Reidentifikace automobilů v obraze
Ohradzanská, Karolína ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
Vehicle re-identification is a helpful technic for tracking and monitoring traffic in various situations. This thesis deals with the issue of re-identification cars in the image to track vehicles using camera systems. Specifically, it focuses on the multi-camera vehicle tracking task from the international AI City Challenge competition. In this work were trained five types of convolutional networks and one transformer model. It investigated how successfully different convolutional networks worked compared to the transformer model in the re-identification task. Several experiments were performed with these networks on several datasets, while the resNeXt model achieved a success rate of up to 86.35~\% on the VeRi dataset. Participation in the AI City Challenge in 2023 required creating a dataset with people for the re-identification task.
Mobilní aplikace pro podporu evidence majetku
Ponížil, Daniel ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
The goal of the bachelor’s thesis was to create a mobile application that would simplify the registration process of new assets into an inventory software. The application was developed using the React Native framework with the use of the Expo platform. The development and testing process was mainly focused on the Android platform. The application allows scanning serial numbers of new assets using barcodes and QR codes. The type of object being created is selected for the scanned numbers, and the values of individual properties are filled in. OCR technology can also be used to fill in the values of properties. The objects are then created in the inventory system by saving. The application is based on analyses of the story of stocking new assets, deficiencies of the current solution, and competitive products.
BookSharing – Mobile Application for Book Sharing
Baláž, Martin ; Herout, Adam (referee) ; Kapinus, Michal (advisor)
The goal of this bachelor thesis is to create a mobile application for lending books between users. Users can add books to lend and also borrow them from other users, with the option of paying for the loan. The application is developed for the Android operating system using the Kotlin programming language. The application communicates with a server that is also developed in Kotlin using the Ktor framework. The server handles the storage, filtering, and processing of data that are stored in the server database and that are necessary for the proper operation of the application. The application's user interface and user experience were tested with six users and the results were above average.
Understanding of Badminton Videos
Mašláň, Vojtěch ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
The aim of this thesis was to experiment with machine learning models for the understanding of badminton videos. The thesis maps the current state of using computer vision and machine learning for sport videos analysis. In the experimental part of the work, several models for badminton stroke detection were made. All the models are predicting the strokes based on player poses extracted from a pose estimation model. Developed models achieved an accuracy of 80.1 % for detecting 7 different strokes and 84.0 % for detecting 4 different strokes. Trained models were then used to create a simple web application for short badminton video analysis.
Web App for Q-Sorting
Daněk, Tomáš ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The aim of my bachelor's thesis was to become familiar with the Q-methodology and create a web application for conducting research according to this method. The work includes a complete report on the technologies used and the overall implementation of the web application. I focused mainly on the user interface and ease of handling the application for the respondents. Thanks to this application, the client is able to carry out his own research and the respondents of the research are provided with user interface that is very intuitive and easy to use.
A Mobile Application for Capturing and Displaying an Athlete's Training
Zaťko, Tomáš ; Herout, Adam (referee) ; Tesařová, Alena (advisor)
The main goal of this bachelor’s thesis is the design and implementation of a mobile application intended for athletes and people who like to exercise in the comfort of their homes. It focuses on capturing and displaying photos and videos of high-intensity interval Tabata training. The application is implemented for the Android platform using the React Native framework. The main result is a usable application for automatically capturing the exercise of selected exercises and displaying the captured images for comparison with a reference. Such a method of exercise can have a positive effect on the acquisition and observance of the correct exercise technique. The resulting application has been tested by a number of users and is publicly available on Google Play.
Mobile Application for Evaluation and Comparing an Athlete's Training Videos
Duránik, Rastislav ; Herout, Adam (referee) ; Tesařová, Alena (advisor)
This work discusses development of mobile phone applications and design and implementation of a custom application for comparing and sharing training exercises with a trainer/coach. My focus was on the Android operating system. The Figma tool was used for the design of the user interface. The application itself was created with the React Native library using the Expo platform. I managed to create and test an application with all of the required features.

National Repository of Grey Literature : 525 records found   previous11 - 20nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.