|
|
Weather Estimation Based on Images of Clouds
Kukaň, Tomáš ; Goldmann, Tomáš (referee) ; Orság, Filip (advisor)
The main purpose of this thesis is a creation of a simple mobile application that would be able to give weather predictions based on a cloud photo through the usage of convolu- tional neural networks. I have analyzed all types of clouds and joined them with weather prediction. Then there are the results of experiments with different neural networks archi- tectures and different datasets. In the end of this thesis I have described the creation of the Android application as well as the problems I had to solve.
|
|
| |
|
|
Detector of the Human Head in Image
Svoboda, Jakub ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Detection of human head is an important part of person detection and identification algorithms. This thesis is focused on the detection of human head with methods based on neural networks. The majority the of conventional detectors can identify objects within a limited range of positions, whereas models based on neural networks offer a more robust approach. In this thesis we trained the current state-of-the-art models and compared their accuracy and speed. The most accurate model proved to be RetinaNet which has reached 85.15% AP. This detector can be used to improve current available algorithms for person detection, identification and tracking.
|
|
|
Biometric Sensor for Hand Vein Recognition
Švestka, Jan ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
This work describes the area of the biometric sensor for identifying using hand veins. It proposes the construction of a sensor made up of a camera, an infrared LED, an ultrasonic distance meter and an Arduino development device. The sensor cover and removable arm support are modeled and constructed using 3D printing. A software with user-interface is created for a sensor. The work describes the experiments carried out to find the ideal lighting and camera parameters settings. It is possible to take a photo of a hand veins and identify a person stored in a database based on the captured image.
|
|
|
Reconstruction of Missing Parts of the Face Using Neural Network
Marek, Jan ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
Cílem této práce je vytvořit neuronovou síť která bude schopna rekonstruovat obličeje z fotografií na kterých je část obličeje překrytá maskou. Jsou prezentovány koncepty využívané při vývoji konvolučních neuronových sítí a generativních kompetitivních sítí. Dále jsou popsány koncepty používané v neuronových sítích specificky pro rekonstrukci fotografií obličejů. Je představen model generativní kompetitivní sítě využívající kombinaci hrazených konvolučních vrstev a víceškálových bloků schopný realisticky doplnit oblasti obličeje zakryté maskou.
|
|
|
Software Management
Kyzlink, Jiří ; Goldmann, Tomáš (referee) ; Orság, Filip (advisor)
The thesis deals with updating applications written for the .NET Framework platform and monitoring their status. Thesis solves both requirements with two frameworks. The first framework is based on the Squirrel.Windows library allowing updating the application to version selected by a user via the graphical or terminal user interface and it also supports release channels. The second framework simplifies registration of an application and its services to the consul health checking tool and also obtaining information about available application and services from the tool. Consul provides the ability to monitor availability and health of the registered applications and its services. Both frameworks are modular, targeting the broad range of applications with use of the .NET Standard. Frameworks were successfully internally deployed in Y Soft Corporation.
|
|
|
Running Motion Analysis
Eliáš, Radoslav ; Kolářová, Jana (referee) ; Goldmann, Tomáš (advisor)
Cieľom tejto práce je analyzovať pohyb a držanie tela pri behu. Systém pracuje so záznamom z dvoch kamier, zboku a zozadu. Využíva nástroj na detekciu postoja ľudského tela založenú na konvolučnej metóde. Práca porovnáva niekoľko detektorov. Výsledný systém používa detektor OpenPose a implementuje knižnicu s výpočtami pre rôzne metriky používane na ohodnotenie formy behu. Výsledky sú zobrazené v multiplatformnej aplikácii. Ohodnotená bola niekoľkými experimentmi na osobnej dátovej sade videí behu.
|
|
|
Multicameras Biometric Gateway to Identify People
Kosík, Dominik ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
This thesis is about creating biometric gate to identify people. The Identification is achieved with 5 RGB cameras and one thermal camera. Thermal camera is used for detection of person. Then, from images acquired from RGB cameras, is created 3D model of photographed person. This model is then used for the identification. However due to inaccuracies in created model, identification isn't precise enough. Because of that, it's necessary to modify used algorithms processing 3D model, so better precision is achieved.
|
|
|
Pedestrian Detection and Recognition in a Multi-Camera System
Macák, Filip ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
The main purpose of this bachelor's thesis is to create an application for person detection and recognition from scenes captured in a multi-camera system. The output of the application is a video on which the detected persons are highlighted and each person is assigned an identification number through which it can be recognized across the input scenes. Several solutions to the problem of person detection and recognition were examined and the text of this work serves as an overview of these problems. The application is built on PyTorch and Torchreid libraries. A detector with a Faster-RCNN network is used for detection and recognition is based on the OSNet network. The application also includes a simple user interface to facilitate work with the application. The application serves as a demonstration of the state-of-the-art for person detection and recognition.
|
|
|
Determining Head Rotation in Video from Security Camera
Blucha, Ondřej ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
This thesis attempts to create an application to determine head rotation angle in video recorded from a security camera. The application consists of three parts: face detection, facial landmarks detection and determination of person's head rotation. The face detection has been implemented using Viola-Jones and HOG algorithms. Facial landmarks detection has been done using algorithm based on active shape model. Two methods to calculate the head rotation angles have been used: the first method works with anthropometric head features. The second method uses Perspective-n-Point algorithm to find the right rotation angles. Finally, all algorithms implemented have been tested and the proper parameters have been determined.
|
guest ::
