|
|
Transcription and annotation components for web editor in React
Dugovič, Jakub ; Herout, Adam (referee) ; Szőke, Igor (advisor)
Cieľom tejto práci je implementovať modulárne užívateľské rozhranie na prepis zvukových nahrávok a ich anotáciu. Rozširuje dotrajšiu prácu s cieľom umožniť a zjednodušiť prácu s hodiny dlhými nahrávkami rozhovorov. Riešenie je implementované v TypeScripte pomocou Reactu a ďalších knižníc z reactového ekosystému. Aplikujúc princípy naštudované z literatúry, vyhýbajúc sa chybám identifikovaným počas prieskumu obdobnej platformy a overujúc užívateľské rozhranie počas vývoja pomocou kvalitatívneho testovania, vyvýjané rozhranie sa usiluje dosiahnuť vysokú mieru dobrej užívateľskej skúsenosti.
|
|
|
Capturing of Detailed and Very Large Photograph and Localization Within
Dubovec, Pavol ; Vaško, Marek (referee) ; Herout, Adam (advisor)
The goal of this work was to create a large image and a new technique to localize the photo in the larger image to increase the speed and accuracy of conventional methods. The proposed technique uses CNN architecture to extract embeddings from the queried image which will be used to search the database of embeddings from the large photo. Two models have been trained on a large dataset: based on classification (CE) and distance (triplet) Conventional methods were used to determine the location of the images and to generate the large image. A database of embeddings was created by partitioning the large image using the trained model. The database is searched for the K-nearest embeddings of the cutouts of the query image. These embeddings are generated by dividing the query photo into the same size parts as the CNN inputs. The optimal homography model is determined by random selection based on the positions of the four query image cutouts and their corresponding positions in the big picture. The homography model with the lowest harmonic mean of the embedding distance is selected as the final position. The homography is optimized using template matching where possible. The method shows sufficient accuracy and high speed on test datasets. The best model achieved a top-1 accuracy of 97.71% and a top-3 accuracy of 99.67%. Future research will investigate the performance of the method under increasing surface heterogeneity, the possibility of automating video retrieval to obtain a large dataset with photos, and its effectiveness in locating photos when conventional methods fail.
|
|
|
Optimal Crop For Photographing Individuals During Sports Activities
Lebedenko, Anastasiia ; Tesařová, Alena (referee) ; Herout, Adam (advisor)
Cílem této bakalářské práce je vyvinout řešení pro zpracování záběrů lidských subjektů za účelem generování videí optimálních rozměrů zaměřených na jednotlivce a eliminujících nadbytečné pozadí. Pomocí modelů počítačového vidění program identifikuje a sleduje lidské pozice ve vstupních videích a poté aplikuje specializovaný algoritmus oříznutí pro generování výstupních snímků. Řešení nabízí možnosti přizpůsobení poměru stran a režimu oříznutí ve výstupním videu. Eliminuje tak nutnost pořizovat více videí, aby byly splněny různé technické nebo estetické požadavky, což umožňuje vytváření různých výstupů z jednoho videa s vysokým rozlišením pomocí předdefinovaných parametrů oříznutí.
|
|
|
Shared transport for hospital staff
Lukášek, Ondřej ; Herout, Adam (referee) ; Tesařová, Alena (advisor)
This thesis focuses on the design and development of a mobile application for the employees of Olomouc University Hospital, who face a shortage of parking spaces on the premises. The application addresses this issue through shared rides for commuting to and from work. It is implemented for Android and iOS platforms using the React Native framework, with Firebase used as the backend service. The main contribution of this work is the extensive user research involving over 1000 hospital employees. Besides the research and overall mobile development, this thesis deals with the actual implementation of the application using modern approaches. The resulting application is ready for imminent release and pilot operation in the hospital, representing an important step towards practical deployment in a real-world setting.
|
|
|
Voice-controlled app for capturing photos and clips
Jurčík, Adam Dalibor ; Španěl, Michal (referee) ; Herout, Adam (advisor)
The goal of this work is to create an application that solves the problems of video and photo recording while the same person is playing sports. These problems are, for example, the need to carry a remote control or the constant interruption of the activity due to manual activation. This is solvedby using voice control and keywords to trigger the taking of a photo. This paper discusses in detail how voice control can be implemented on Android operating system in Java programming language. It also includes an explanation of how to store these files and how to control hardware devices such as the camera. The thesis includes a more detailed description of two approaches to voice recognition and describes their functionality in different applications.
|
|
|
Mobile App for Precise Navigation of Agricultural Machinery
Košák, Václav ; Bambušek, Daniel (referee) ; Herout, Adam (advisor)
The aim of this thesis is to develop a field navigation and GNSS system for precise localization. In the field, it is advisable to drive precisely along the lines to avoid repeated crossings or, on the contrary, free spaces. Driving accurately can save seeds, sprays, fuel, and more. Field navigation manages fields, machines, etc. The goal of the application is to navigate along generated guidance lines. In addition to the mobile application, a GNSS system has been developed to receive precise signals with RTK correction. Test results show that with an accurate receiver, the application can be practically used for everyday tasks.
|
|
|
Research and Development of Communication Infrastructure for Q Sorting
Krajňák, Sebastián ; Beran, Vítězslav (referee) ; Herout, Adam (advisor)
V dynamickom prostredí spolupráce pri vývoji softvéru sa požiadavky na interakciu v reálnom čase a zefektívnenie procesov nasadenia stala nevyhnutnosťou. Táto práca sa zameria na vylepšenie aplikácie nášho kolegu Michala Janu o funkciu spolupráce v reálnom čase prostredníctvom WebSocket spojenia. Táto funkcia umožní viacerým používateľom spolupracovať na jednom Q-sorte. Okrem toho na zefektívnenie procesu softvérového projektu pre viacerých vývojárov, ktorého je táto práca súčasťou, nastavíme CI/CD postup využívajúci Dokcer kontajnery, Jenkins a nakoniec webový server Nginx používaný na hostovanie aplikácií každého vývojára.
|
|
|
Administrativní rozhraní pro Q řazení
Kováčik, Jakub ; Beran, Vítězslav (referee) ; Herout, Adam (advisor)
This thesis focuses on the development of an administrative interface in the form of a web application that allows the creation and management of card decks for Q-methodology, while enabling efficient research management. Q-methodology is a research approach used in the social sciences to analyse the subjective perspectives of participants. The application allows the management of multiple versions of card decks and the implementation of repeated research cycles with the ability to send email notifications to participants, supporting a dynamic and iterative approach to research. The application allows the sharing of card decks and research, which greatly supports collaboration and knowledge sharing between users.
|
|
|
Algorithms and Methods of Statistical Processing of Q Sorting
Burešová, Zuzana ; Beran, Vítězslav (referee) ; Herout, Adam (advisor)
The goal of this bachelor thesis was to learn about Q-methodology, create a Q-sort for test data extraction, convert test data into JSON format, experiment with data visualization and evaluation, and create a library for evaluating and visualization of the Q-sort data. The paper includes a report on the technologies used and a description of each tool implemented in the developed library. My main focus was on data visualization, where I experimented with different graphs and visualization libraries. With this library, the user can easily evaluate and visualize the data obtained from the Q-sort.
|
|
|
Controlling Mobile App by Voice
Cologna, Adam ; Szőke, Igor (referee) ; Herout, Adam (advisor)
The aim of this bachelor's thesis is to explore, analyze, and compare available libraries for controlling mobile applications with voice commands. According to the thesis requirements, I solved the problem primarily for the Android operating system. I have considered not only libraries for keyword detection but also those using the speech recognition technology. For the selected libraries, I conducted accuracy testing for voice command detection and performance testing. To facilitate the integration of the chosen libraries, an application was developed in the modern programming language Kotlin using Jetpack Compose. The main contribution of this work is the experiments carried out and the resulting recommendations regarding the examined libraries. Among the most effective solutions were those from Microsoft Azure and the Android Speech Recognizer class. The main obstacles for each library were the distance between the speaker and the microphone, as well as distracting background music.
|
guest ::
