|
|
System for tracking and classification of objects in the sky
Franka, Jakub ; Honec, Peter (referee) ; Janáková, Ilona (advisor)
This work deals with the use of computer vision in the field of detection, tracking and classification of flying objects in a real environment. The goal is to create a robust system, capable of working effectively in adverse conditions and accurately identifying different types of objects in the sky. The work progresses from theoretical foundations, choice of methods, to the design and implementation of a computer vision system.
|
|
|
AI-based classification of RF signals
Turák, Samuel ; Ulovec, Karel (referee) ; Polák, Ladislav (advisor)
Táto práca sa zameriava na klasifikáciu rádiofrekvenčných (RF) signálov založenú na hlbokom učení. Pre tento účeľ, tri neuronové siete sú vybrané a prezentované: Konvolučná Neurónová Sieť (CNN), Sieť s Bránovými Rekurentnými Jednotkami (GRU), Konvolučná Hlboká Neurónová Sieť s Bránami (CGDNN). Všetky sú trénované a vyhodnotené na viacerých datasetoch, ovplyvnené rôznymi RF rušeniami, pre klasifikáciu rôznych bezdrátových štandardov. Signály v jednotlivých datasetoch boli vytvorené pomocou aplikácie Wireless Waveform Generator v programu MATLAB. Jeden verejne dostupný dataset na klasifikáciu modulácie je takisto testovaný na modeloch. Použité prístupy k predspracovaniu dát, tréningu modelov a vyhodnoteniu modelov sú implementované v programovacom prostredí Python s využitím knižníc ako Scikit-learn a Keras. \mbox{Získané výsledky} sú prehľadne prezentované a diskutované.
|
|
|
Machine Learning from Intrusion Detection Systems
Dostál, Michal ; Očenášek, Pavel (referee) ; Hranický, Radek (advisor)
The current state of intrusion detection tools is insufficient because they often operate based on static rules and fail to leverage the potential of artificial intelligence. The aim of this work is to enhance the open-source tool Snort with the capability to detect malicious network traffic using machine learning. To achieve a robust classifier, useful features of network traffic were choosed, extracted from the output data of the Snort application. Subsequently, these traffic features were enriched and labeled with corresponding events. Experiments demonstrate excellent results not only in classification accuracy on test data but also in processing speed. The proposed approach and the conducted experiments indicate that this new method could exhibit promising performance even when dealing with real-world data.
|
|
|
Identification of specified segments in the audio signal using machine learning
Pařízek, Radim ; Galáž, Zoltán (referee) ; Zvončák, Vojtěch (advisor)
The bachelor thesis deals with the design of a system for the identification of natural environmental sounds in audio recordings. The datasets and models used for this type of tasks are surveyed and their structure is described. A system for the identification of sounds in one layer and in two layers has been proposed for seven selected labels. The classifier used for this system was created by fine-tuning a transformer model from the Hugging Face platform. The results of two training approaches and one identification system were evaluated.
|
|
|
QR code detection using deep learning
Černohous, Matěj ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This bachelor thesis deals with the design of an algorithm for detecting and decoding QR codes in images using deep learning techniques. The work involved the construction of 2 datasets, a YOLOv7 neural network model for detecting QR codes in images, a YOLOv4-tiny neural network model for detecting position markers of QR codes, and a Python program utilizing these models to read QR codes in images. For evaluation, the algorithm was compared with other options for QR code reading.
|
|
|
Image Completion Using Depth Maps
Valeš, Ondřej ; Brejcha, Jan (referee) ; Čadík, Martin (advisor)
The aim of this thesis is to design and implement aplication for dataset driven scene completion utilizing data from similar dataset images and test the posibility of generating data used in reconstruction directly from depth map. For scene matching in dataset novel modification of GIST descriptor including depth data is used. Furthermore, depth maps can be used to split reconstructed image into parts with similar depth, simplifying reconstruction process. Part of this thesis is also computing GIST descriptors for datset images and implementation of tools for searching datset for similar images using depth maps.
|
|
|
Detection and Recognition of License Plates
Tykva, Jiří ; Zemčík, Pavel (referee) ; Juránek, Roman (advisor)
Cílem této bakalářské práce je návrh, implementace a testování systému, který v reálném čase pomocí neuronových sítí bude detekovat a rozpoznávat registrační značky vozidel. Nasbíraná data budou ukládána do databáze. Architektura systému je rozdělena do tří hlavních částí. První část řeší detekci registrační značky v obraze pomocí TensorFlow Object Detection API. Detektor dosahuje přesnosti 98.15 % AP při rychlosti kolem 14 fps. Druhá část se zabývá sledováním značek ve videu pomocí algoritmu SORT. Třetí část systému se věnuje holistickému rozpoznávání textu registrační značky a dosahuje až 0.6% chybovosti při rozpoznávání jednotlivých znaků a 2% chybovosti při rozpoznávání celého textu. Výsledný systém lze použít například pro policejní oddělení za účelem sledování kradených vozidel či automatického vybírání dálničních poplatků.
|
|
|
Face Detection, Invariant to Rotation
Bureš, Václav ; Herout, Adam (referee) ; Beran, Vítězslav (advisor)
This bachelor thesis focuses on the detection of type uniform objects (concretely faces) in an image. Furthermore the thesis concentrates on the detection of objects in various rotations. The thesis covers a brief overview of methods available, such as Logical Binary Patterns, Histogram Of Gradients, Eigen Faces and more closely specified AdaBoost. Next, freely available datasets are presented, with a descripiton of their chosen characteristics. At the end of the thesis, experiments using AdaBoost algorythm and their evaluation are described.
|
|
|
Image Super-Resolution Using Deep Learning
Mojžiš, Tomáš ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
The aim of this thesis is to create a deep neural net capable of super-resolution on images acquired by electron microscopes. The thesis consists of two parts - finding appropriate data and creating a dataset for the super-resolution task and designing a neural net architecture capable of solving the super-resolution task. Within the thesis, two datasets comprised of images acquired by electron microscopes were created. The datasets differ in the approach to data augmentation. They allow to train a neural network which fulfills the super-resolution task. To solve this task, two U-Net based and one GAN based architecture were trained. The resolution of images was upscaled by a factor of two and four. The best artificially upscaled images were created by neural network Real-ESRGAN. The values of metrics were not higher than the tested interpolation method, but the images seem more visually pleasing especially when they were upscaled four times. Thanks to this thesis, two datasets were created allowing to train other possible neural network architectures to improve the quality of the artificially upscaled images. The neural networks trained in this thesis can be utilized in the process of acquiring higher quality data from low resolution electron microscope images.
|
|
|
Pedestrian Attribute Analysis
Studená, Zuzana ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
This work deals with obtaining pedestrian information, which are captured by static, external cameras located in public, outdoor or indoor spaces. The aim is to obtain as much information as possible. Information such as gender, age and type of clothing, accessories, fashion style, or overall personality are obtained using using convolutional neural networks. One part of the work consists of creating a new dataset that captures pedestrians and includes information about the person's sex, age, and fashion style. Another part of the thesis is the design and implementation of convolutional neural networks, which classify the mentioned pedestrian characteristics. Neural networks evaluate pedestrian input images in PETA, FashionStyle14 and BUT Pedestrian Attributes datasets. Experiments performed over the PETA and FashionStyle datasets compare my results to various convolutional neural networks described in publications. Further experiments are shown on created BUT data set of pedestrian attributes.
|
guest ::
