|
|
Semantic segmentation of images from off-road environment
Spilková, Bára ; Králík, Jan (referee) ; Adámek, Roman (advisor)
Hlavním cílem bakalářské práce je prozukoumání růzých metod sémantické segmentace snímků z off-road terénu. V rešeršní části jsou popsány základní principy sémantické segmentace, různé přístupy k tomuto problému, metody sémantické segmentace a různé datové sady. Dále je popsán proces evaluace a trénování několika modelů s rozdílnými parametry a vytvoření nového evaluačního datasetu. Získané výsledky jsou porovnány s výsledky z rešeršní části a jsou navrhnuty další kroky pro zvýšení přesnosti modelů.
|
|
|
Decreased visibility and image defect detection for vehicle mounted camera
Sedláček, Miloš ; Řičánek, Dominik (referee) ; Svědiroh, Stanislav (advisor)
This bachelor thesis deals with the topic of decreased visibility and image defects detection caused by adverse weather conditions or lighting from a vehicle mounted camera. The thesis describes the basic characteristics of the most common influences and their effects on camera data and presents some existing methods of detecting these influences. Next, a dataset containing selected defects is created and described. Afterwards, the issue of artificial neural networks is described in the thesis. A convolutional neural network is implemented for defect detection, which is trained and tested using the dataset. At the end, the achieved results of the network, its computational complexity and comparison with the results of other works are presented.
|
|
|
Lane detection for autonomous vehicles
Holík, Štěpán ; Píštěk, Václav (referee) ; Kučera, Pavel (advisor)
This thesis focuses on the design and experimental verification of a system for lane detection, trajectory estimation and vehicle position. The goal was to develop a system composed of algorithms with its respective functions. Data collected with ZED 2 camera, the U-Net neural network model, and computer vision were used to reduce false positive predictions using a temporal window. Trigonometric calculations and camera parameters were used to estimate the vehicle’s position relative to the trajectory. One of the outcomes of this thesis is TuSimple dataset extension with the data captured with ZED 2 camera. Experimental verification demonstrated the system's functionality with high detection reliability in simple model situations, such as driving on a straight road segment. As the complexity of the model situations increased, the system's reliability decreases. Despite these shortcomings, the experiments showed that the system is able to detect lane boundaries and estimate an optimal vehicle trajectory. The algorithms for trajectory and vehicle position determination depend on the initial prediction of the lane boundaries, but they are functional and effective.
|
|
|
Evolutionary Design of Convolutional Neural Networks Utilizing a Supernet
Lamačka, Zbyněk ; Piňos, Michal (referee) ; Sekanina, Lukáš (advisor)
This work explores the possibilities of automated design and optimization of convolutional neural networks (CNNs) using evolutionary algorithms with the concept of Neural Architecture Search (NAS). NAS methods facilitate the work of neural network architects and allow access to neural networks by people who would not normally have access to them. Architectures that are created by automated methods are able to outperform architectures that were created by experienced architects. These methods are not bound by conventional design approaches, and therefore innovative architectures can emerge. The goal of this work is to design and implement a neuroevolutionary method using a supernetwork. The supernetwork concept aims to make the process of automatic network design faster and cheaper. This method will be evaluated based on the architectures it generates. The evaluation of the architectures considers two criteria -- accuracy and complexity of the network. The ImageNet dataset is used for the evaluation.
|
|
|
Detection and Classification of Photovoltaic Power Plant Panel Defects from a Drone Thermal Imaging Camera
Haužvic, Filip ; Materna, Zdeněk (referee) ; Bambušek, Daniel (advisor)
The thesis describes the processing of thermal images of photovoltaic power plants captured by a drone. In contemporary solutions, the images are analyzed manually, where an expert in thermal imaging searches for defects in individual panels. This approach is very time-consuming, and introducing some level of automation could ease the process. Therefore, I trained and utilized a U-Net model that detects hot spots in the images. To visualize and present the defects to the user, I designed and created a web-based application that highlights them in a complete orthomosaic of the photovoltaic power plant. Within the application, a user can annotate PV panels in the power plant and manually remove, or add any defect. When the plant is wholly annotated, an export to a spreadsheet can be created, matching defects to the individual annotated panels.
|
|
|
Genetic Programming with Memory for Symbolic Regression
Jůza, Tadeáš ; Bidlo, Michal (referee) ; Sekanina, Lukáš (advisor)
The purpose of this thesis is to evaluate the possibility of extending genetic programming with memory for solving symbolic regression problems. Furthermore, a set of problems for testing the quality of such solutions is developed. The thesis proposes a practical application of such an extension to reduce the energy consumption of loading weights of convolutional neural networks. Instead of retrieving all the weights of the network from external memory, only a small percentage of the weights is retrieved and the remaining ones are generated using the evolved expression. This method was primarily evaluated on reducing the set of weights of convolutional layers of a small convolutional neural network classifying the MNIST dataset. Furthermore, the possibility of generating weights was also tested on other convolutional neural networks solving more complex classification problems. The proposed method has delivered interesting tradeoffs between the classification accuracy and weight memory size.
|
|
|
Registration of the landing aircraft based on image recognition techniques
Juroška, Jan ; Šplíchal, Miroslav (referee) ; Červenka, Miroslav (advisor)
In this diploma thesis, a method automating for the process of registering an aircraft on an uncontrolled airfield using computer vision was created. First, aircraft is detected using neural network form the YOLO family, next, its registration is read using the Tesseract network. In the theoretical part of this work, various methods for solving this issue are introduced, as well as the theoretical basis behind the chosen method. In the practical part of this work, the documentation of the created program is provided. Testing of programs limits is conducted, and instructions for setting up and using the method are provided.
|
|
|
Neural Networks at the Level of Network Packets and Flows
Urbánek, Petr ; Jeřábek, Kamil (referee) ; Poliakov, Daniel (advisor)
Tato diplomová práce se zabývá integrací neuronových sítí do monitorování toků v síti, zejména se zaměřením na ipfixprobe — open-source exportér IP toků sítí vyvinutý společností CESNET. Cílem je zkoumat potenciál neuronových sítí pro klasifikaci a extrakci reprezentací ze síťových toků. Jsou zde zvažovány výzvy spojené s nasazením takových řešení ve velkém měřítku v produkčních prostředích, s konkrétním důrazem na zlepšení efektivity a účinnosti v dynamickém technologickém prostředí.
|
|
|
Support tool for initial phase of penetration testing
Žáček, Dominik ; Gerlich, Tomáš (referee) ; Sikora, Pavel (advisor)
This thesis deals with the development of an advanced tool designed to make team penetration testing more efficient. The tool works by automatically assigning tasks to penetration testers based on skills and historical performance. The theoretical part of the thesis analyzes in detail various methods for solving the assignment problem, in particular the Hungarian method and linear programming. The theoretical part continues with the design of a two-step algorithm for task assignment. Then, the principle of the neural networks underlying the second step of the assignment is described in detail. Unique methods for generating two datasets have also been developed as part of the work. An interface for task assignment has been implemented and metrics to determine the quality of the assignment have been proposed. The result is a tool that significantly streamlines the assignment of tasks to penetration testers and increases the overall efficiency of penetration testing teams.
|
|
|
Visual Anomaly Detection in Industrial Production
Hrabica, Jan ; Richter, Miloslav (referee) ; Horák, Karel (advisor)
This thesis deals with the problem of unary classifiers for anomaly detection in industrial production. It starts with a discussion of classification as a general problem, classification methods and some of their evaluations, and then discusses the main categories of architectures used. Practical part describes the process of scene creation for the acquisitions of a datesed. Acquired dataset is then used for teaching a classifier, on which is then performer a number of experiments to determine its performance.
|
guest ::
