Národní úložiště šedé literatury Nalezeno 2 záznamů.  Hledání trvalo 0.01 vteřin. 
Image segmentation using graph neural networks
Boszorád, Matej ; Kolařík, Martin (oponent) ; Myška, Vojtěch (vedoucí práce)
This diploma thesis describes and implements the design of a graph neural network usedfor 2D segmentation of neural structure. The first chapter of the thesis briefly introduces the problem of segmentation. In this chapter, segmentation techniques are divided according to the principles of the methods they use. Each type of technique contains the essence of this category as well as a description of one representative. The second chapter of the diploma thesis explains graph neural networks (GNN for short). Here, the thesis divides graph neural networks in general and describes recurrent graph neural networks(RGNN for short) and graph autoencoders, that can be used for image segmentation, in more detail. The specific image segmentation solution is based on the message passing method in RGNN, which can replace convolution masks in convolutional neural networks.RGNN also provides a simpler multilayer perceptron topology. The second type of graph neural networks characterised in the thesis are graph autoencoders, which use various methods for better encoding of graph vertices into Euclidean space. The last part ofthe diploma thesis deals with the analysis of the problem, the proposal of its specific solution and the evaluation of results. The purpose of the practical part of the work was the implementation of GNN for image data segmentation. The advantage of using neural networks is the ability to solve different types of segmentation by changing training data. RGNN with messaging passing and node2vec were used as implementation GNNf or segmentation problem. RGNN training was performed on graphics cards provided bythe school and Google Colaboratory. Learning RGNN using node2vec was very memory intensive and therefore it was necessary to train on a processor with an operating memory larger than 12GB. As part of the RGNN optimization, learning was tested using various loss functions, changing topology and learning parameters. A tree structure method was developed to use node2vec to improve segmentation, but the results did not confirman improvement for a small number of iterations. The best outcomes of the practical implementation were evaluated by comparing the tested data with the convolutional neural network U-Net. It is possible to state comparable results to the U-Net network, but further testing is needed to compare these neural networks. The result of the thesisis the use of RGNN as a modern solution to the problem of image segmentation and providing a foundation for further research.
Object tracking in video
Boszorád, Matej ; Přinosil, Jiří (oponent) ; Rajnoha, Martin (vedoucí práce)
This bachelor thesis deals with the issue of tracking multiple objects in a video, specifically focusing on non-learning algorithms. The first chapter represents the theoretical part of the thesis, in which some of the often used tracking methods are described, such as mean-shift, scale-invariant object transformation, Kalman filter, particle filter and Gabor wavelet transformation. These algorithms are broken down by properties they use for proper tracking. The chapter also contains section assignment problem, which is mainly concerned with Hungarian algorithm. The next part describes options of merging multiple tracking methods that are broken down by construction type into parallel, cascade, weighted and discriminatory with example for each one. Moreover there is described adaptability of the tracking system. Bellow are described problems which may occur during tracking and possible solutions to them. This section consists of a solution of image noise, changes in illumination, appearance and extinction of an object, focusing mainly on solving the problem of object occlusion. Within the practical part is created algorithm composed of different types of tracking, the results of which are then compared with selected tracking systems from the multiple object tracking benchmark. The practical part includes the tools used and the explanation of the design, in which the main classes and methods used for the tracking are explained. Besides that, this section describes parallel merging and tracking adaptability . The results of the thesis contain a comparison of the use of tracking techniques separately and together. To compare the results, videos for pedestrian tracking and face tracking were used. This thesis was based on the assumption that merging multiple monitoring systems will help with the improvement of the tracking, which was confirmed by the results.

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.