|
|
Vehicle Counting in Still Image
Hladiš, Martin ; Juránek, Roman (referee) ; Špaňhel, Jakub (advisor)
The goal of this thesis is to compare different models of convolutional neural networks, which use the principle of using density estimation to count the number of vehicles in a still image. The tested models were -- Counting CNN, Scale-adaptive CNN, Multi-Scale Fusion Net a Multi-scale CNN. Their estimation capability was tested using these datasets -- TRANCOS, CARPK, PUCPR+. The most accurate results were achieved by the Multi-Scale Fusion Net model. Its estimation accuracy using the dataset TRANCOS in the Mean Absolute Error metric achieved value of 8.05.
|
|
|
Deep Learning for OCR in GUI
Hamerník, Pavel ; Špaňhel, Jakub (referee) ; Lysek, Tomáš (advisor)
Optical character recognition (OCR) has been a topic of interest for many years. It is defined as the process of digitizing a document image into a sequence of characters. Despite decades of intense research, OCR systems with capabilities to that of human still remains an open challenge. In this work there is presented a design and implementation of such system, which is capable of detecting texts in graphical user interfaces.
|
|
|
Action Game for GearVR
Mladý, Jakub ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
This thesis deals with the study of technologies and techniques for creating virtual reality for mobile devices. It includes a description of the design and implementation of an action game, using Unity Game Engine, which demonstrates Gear VR's capabilities well. The thesis describes the obstacles that arise in the creation of games for virtual reality as well as their possible solutions. Graphic elements of the game were developed based on the results of continuous user testing. Particular attention was paid to exploring the impact of visual effects and game elements used in games on a user in virtual reality.
|
|
|
Mobile App for Management of Transactions with Cryptocurrencies
Bobčík, Pavel ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
The main goal of this bachelor thesis is to create a mobile application which would serve as auxiliary tool in cryptocurrency trading. The application is therefore targeting group of people already engaged in this market. The user can store and keep track of information about his transactions, such as purchase, sale and exchange. The application works with basic information, such as quantity, price, cryptocurrency name and date of proceeding. Based on the information it makes necessary calculations for correct organization in FIFO queue. Transactions can be further modified. Newly gained information are then processed. The user has option to generate PDF file, including all the information about own transactions in selected tax period. Also the overview of the currently registered cryptocurrencies can be displayed in the application. The design and entire looks of the application was consulted with potential users with its aim for maximizing user experience and also simplify orientation. Some observations serve as opportunities for further development.
|
|
|
Automatic Traffic Camera Calibration for Vehicle Speed Measurement
Nociar, Marián ; Bartl, Vojtěch (referee) ; Špaňhel, Jakub (advisor)
This thesis deals with design and development of a system for Automatic Traffic Camera Calibration for Vehicle Speed Measurement. The thesis contains a theoretical introduction to the camera calibration, describes the principles of the methods used in the implementation and displays the proposed solution that was implemented in Python3 using OpenCV and NumPy libraries. The achieved results were evaluated over the BrnoCompSpeed dataset with the average speed measurement error reaching 6.71 km/h.
|
|
|
Easily Configurable Visual Inspection System for Industrial Applications
Andrla, Ondřej ; Špaňhel, Jakub (referee) ; Španěl, Michal (advisor)
The aim of this thesis is to create a prototype of an easily configurable camera system, used to control products on an automated assembly line. The thesis is especially focused on the issue of LED detection. Their very presence in the image is detected and the system also evaluates whether the LED is lit and, if so, in what color. The final solution allows the user to easily define control metric for searching for circular objects in the image in a configuration application with a graphical user interface. The configuration is saved in a JSON file. Furthermore, a runtime which independently processes the recording from the camera, checks the products and reports on them to other components of the system based on the configuration was implemented. The system uses the Hough circular transformation to detect objects in the image. To test the efficiency of the system, a dataset was created using the FitKit tool with a LED matrix. When testing the runtime on the dataset, the overall accuracy of LED detection was 97,79%.
|
|
|
Vehicle Detection in Image and Video
Rozprým, Dalimil ; Juránek, Roman (referee) ; Špaňhel, Jakub (advisor)
The goal of this thesis is comparison of available multiclass detectors abilities to detect road vehicles on purposely created dataset. As multiclass detectors are chosen neural networks for detection and classification of objects in image. Detectors described in this text and used for experimentation are Mask R-CNN, YOLOv4 and YOLACT++. This selection encompasses multiple different architectures and approaches to object detection. Created dataset used for learning and testing is thoroughly described in this text. Detection capability of detectors is tested on images from casual traffic and separately on partially covered objects. The outcome of this thesis is reusable and expandable dataset, measured performance values and their deeper exploration in this text.
|
|
|
Innovative Music Player for Smartphones and PC
Richter, Roman ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
The goal of this thesis is to create a music player for smartphones as well as PCs that works with local music files in the user's device and which can learn which songs does the user like based on their actions during listening to music. The music player can, among other things, remember which songs were skipped by the user, when was volume turned up, or how many times was a certain song played. Each song has a score that is calculated based on these actions. With a higher score, there is also a higher chance of playing the song in the future. The results of my thesis are two full-featured versions of music player, which are capable of communication with each other to ensure synchronization of song scores. The main benefit of this thesis is an improvement of user experience during listening to music, which is achieved by the application's algorithm for song selection and minimalistic user interface.
|
|
|
Deep Learning for OCR in GUI
Hamerník, Pavel ; Špaňhel, Jakub (referee) ; Lysek, Tomáš (advisor)
Optical character recognition (OCR) has been a topic of interest for many years. It is defined as the process of digitizing a document image into a sequence of characters. Despite decades of intense research, OCR systems with capabilities to that of human still remains an open challenge. In this work there is presented a design and implementation of such system, which is capable of detecting texts in graphical user interfaces.
|
|
|
Mobile Application for Studis BUT
Smyčka, Jan ; Sochor, Jakub (referee) ; Špaňhel, Jakub (advisor)
Bachelor thesis deals with the development of mobile application in Android for VUT information system. The theoretical part of the thesis describes Android operating system and its basic elements used in the application development process, the text also describes the architectural design of mobile applications. The main part of the thesis deals with the implementation of the application and its testing on the users. In the final part of the thesis, the application development and user testing are assessed, and further possible development of the application for the future is proposed.
|
guest ::
RSS feed.