[pt] Ao longo da história a engenharia de fluidos vem se mostrado como uma das áreas mais importantes da engenharia devido ao seu impacto nas áreas de transporte, energia e militar. A medição de campos de velocidade, por sua vez, é muito importante para estudos nas áreas de aerodinâmica e hidrodinâmica. As técnicas de medição de campo de velocidade em sua maioria são técnicas ópticas, se destacando a técnica de Particle Image Velocimetry (PIV). Por outro lado, nos últimos anos importantes avanços na área de visão computacional, baseados em redes neurais convolucionais, se mostram promissores para a melhoria do processamento das técnicas ópticas. Nesta dissertação, foi utilizada uma abordagem híbrida entre correlação cruzada e cascata de redes neurais convolucionais, para desenvolver uma nova técnica de PIV. O projeto se baseou nos últimos trabalhos de PIV com redes neurais artificiais para desenvolver a arquitetura das redes e sua forma de treinamento. Diversos formatos de cascata de redes neurais foram testados até se chegar a um formato que permitiu reduzir o erro em uma ordem de grandeza para escoamento uniforme. Além do desenvolvimento da cascata para escoamento uniforme, gerou-se conhecimento para fazer cascatas para outros tipos de escoamentos. / [en] Throughout history, fluid engineering is one of the most important areas of engineering due to its impact in the areas of transportation, energy and the military. The measurement of velocity fields is important for studies in aerodynamics and hydrodynamics. The techniques for measuring the velocity field are mostly optical techniques, with emphasis on the PIV technique. On the other hand, in recent years, important advances in computer vision, based on convolutional neural networks, have shown promise for improving the processing of optical techniques. In this work, a hybrid approach between cross-correlation and cascade of convolutional neural networks was used to develop a new PIV technique. The project was based on the latest work of PIV with an artificial neural network to develop the architecture of the networks and their form of training. Several cascade formats of neural networks were tested until they reached a format that allowed the error to be reduced by an order of magnitude for uniform flow. In addition to the development of the cascade for uniform flow, knowledge was generated to make cascades for other types of flows.

This dissertation examines multi-antenna transceiver design over flat-fading wireless channels. Bit Interleaved Coded Modulation (BICM) and MultiLevel Coded Modulation (MLCM) transmitter structures are considered, as well as the used of an optional spatial precoder under slow and quasi-static fading conditions. At the receiver, MultiStage Decoder (MSD) and Iterative Detection and Decoding (IDD) strategies are applied. Precoder, mapper and subcode designs are optimized for different receiver structures over the different antenna and fading scenarios. Under slow and quasi-static channel conditions, fade resistant multi-antenna transmission is achieved through a combination of linear spatial precoding and non-linear multi-dimensional mapping. A time-varying random unitary precoder is proposed, with significant performance gains over spatial interleaving. The fade resistant properties of multidimensional random mapping are also analyzed. For MLCM architectures, a group random labelling strategy is proposed for large antenna systems. The use of complexity constrained receivers in BICM and MLCM transmissions is explored. Two multi-antenna detectors are proposed based on a group detection strategy, whose complexity can be adjusted through the group size parameter. These detectors show performance gains over the the Minimum Mean Squared Error (MMSE)detector in spatially multiplexed systems having an excess number of transmitter antennas. A class of irregular convolutional codes is proposed for use in BICM transmissions. An irregular convolutional code is formed by encoding fractions of bits with different puncture patterns and mother codes of different memory. The code profile is designed with the aid of extrinsic information transfer charts, based on the channel and mapping function characteristics. In multi-antenna applications, these codes outperform convolutional turbo codes under independent and quasi-static fading conditions. For finite length transmissions, MLCM-MSD performance is affected by the mapping function. Labelling schemes such as set partitioning and multidimensional random labelling generate a large spread of subcode rates. A class of generalized Low Density Parity Check (LDPC) codes is proposed, to improve low-rate subcode performance. For MLCM-MSD transmissions, the proposed generalized LDPC codes outperform conventional LDPC code construction over a wide range of channels and design rates.

1 Title: Convolutional neural networks and their application in object detection Author: Matej Hrinčár Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: doc. RNDr. Iveta Mrázová, CSc. Supervisor's e-mail address: Iveta.Mrazova@mff.cuni.cz Abstract: Nowadays, it has become popular to enhance live sport streams with an augmented reality like adding various statistics over the hockey players. To do so, players must be automatically detected first. This thesis deals with such a challenging task. Our aim is to deliver not only a sufficient accuracy but also a speed because we should be able to make the detection in real time. We use one of the newer model of neural network which is a convolutional network. This model is suitable for proces- sing image data a can use input image without any preprocessing whatsoever. After our detailed analysis we choose this model as a detector for hockey players. We have tested several different architectures of the networks which we then compared and choose the one which is not only accurate but also fast enough. We have also tested the robustness of the network with noisy patterns. Finally we assigned detected pla- yers to their corresponding teams utilizing K-mean algorithm using the information about their jersey color. Keywords:...

Alex Krizhevsky and his colleagues changed the world of machine vision and image processing in 2012 when their deep learning model, named Alexnet, won the Im- ageNet Large Scale Visual Recognition Challenge with more than 10.8% lower error rate than their closest competitor. Ever since, deep learning approaches have been an area of extensive research for the tasks of object detection, classification, pose esti- mation, etc...This thesis presents a comprehensive analysis of different deep learning models and architectures that have delivered state of the art performances in various machine vision tasks. These models are compared to each other and their strengths and weaknesses are highlighted. We introduce a new approach for human head and shoulder detection from RGB- D data based on a combination of image processing and deep learning approaches. Candidate head-top locations(CHL) are generated from a fast and accurate image processing algorithm that operates on depth data. We propose enhancements to the CHL algorithm making it three times faster. Different deep learning models are then evaluated for the tasks of classification and detection on the candidate head-top loca- tions to regress the head bounding boxes and detect shoulder keypoints. We propose 3 different small models based on convolutional neural networks for this problem. Experimental results for different architectures of our model are highlighted. We also compare the performance of our model to mobilenet. Finally, we show the differences between using 3 types of inputs CNN models: RGB images, a 3-channel representation generated from depth data (Depth map, Multi-order depth template, and Height difference map or DMH), and a 4 channel input composed of RGB+D data.

No description available.

Context. Image enhancement algorithms can be used to enhance the visual effects of images in the field of human vision. So can image enhancement algorithms be used in the field of computer vision? The convolutional neural network, as the most powerful image classifier at present, has excellent performance in the field of image recognition. This paper explores whether image enhancement algorithms can be used to improve the performance of convolutional neural networks. Objectives. The purpose of this paper is to explore the effect of image enhancement algorithms on the performance of CNN models in deep learning and transfer learning, respectively. The article selected five different image enhancement algorithms, they are the contrast limited adaptive histogram equalization (CLAHE), the successive means of the quantization transform (SMQT), the adaptive gamma correction, the wavelet transform, and the Laplace operator. Methods. In this paper, experiments are used as research methods. Three groups of experiments are designed; they respectively explore whether the enhancement of grayscale images can improve the performance of CNN in deep learning, whether the enhancement of color images can improve the performance of CNN in deep learning and whether the enhancement of RGB images can improve the performance of CNN in transfer learning?Results. In the experiment, in deep learning, when training a complete CNN model, using the Laplace operator to enhance the gray image can improve the recall rate of CNN. However, the remaining image enhancement algorithms cannot improve the performance of CNN in both grayscale image datasets and color image datasets. In addition, in transfer learning, when fine-tuning the pre-trained CNN model, using contrast limited adaptive histogram equalization (CLAHE), successive means quantization transform (SMQT), Wavelet transform, and Laplace operator will reduce the performance of CNN. Conclusions. Experiments show that in deep learning, using image enhancement algorithms may improve CNN performance when training complete CNN models, but not all image enhancement algorithms can improve CNN performance; in transfer learning, when fine-tuning the pre- trained CNN model, image enhancement algorithms may reduce the performance of CNN.

Visual object detection is a popular computer vision task that has been intensively investigated using deep learning on real data. However, data from virtual environments have not received the same attention. A virtual environment enables generating data for locations that are not easily reachable for data collection, e.g. aerial environments. In this thesis, we study the problem of object detection in virtual environments, more specifically an aerial virtual environment. We use a simulator, to generate a synthetic data set of 16 different types of vehicles captured from an airplane. To study the performance of existing methods in virtual environments, we train and evaluate two state-of-the-art detectors on the generated data set. Experiments show that both detectors, You Only Look Once version 3 (YOLOv3) and Single Shot MultiBox Detector (SSD), reach similar performance quality as previously presented in the literature on real data sets. In addition, we investigate different fusion techniques between detectors which were trained on two different subsets of the dataset, in this case a subset which has cars with fixed colors and a dataset which has cars with varying colors. Experiments show that it is possible to train multiple instances of the detector on different subsets of the data set, and combine these detectors in order to boost the performance.

Continuous authentication using behavioral biometrics can provide an additional layer of protection against online account hijacking and fraud. Mouse dynamics classification is the concept of determining the authenticity of a user through the use of machine learning algorithms on mouse movement data. This thesis investigates the viability of state of the art deep learning technologies in mouse dynamics classification by designing convolutional neural network classifiers taking mouse movement images as input. For purposes of comparison, classifiers using the random forest algorithm and engineered features inspired by related works are implemented and tested on the same data set as the neural network classifier. A technique for lowering bias toward the on-screen location of mouse movement images is introduced, although its effectiveness is questionable and requires further research to thoroughly investigate. This technique was named 'centering', and is used for the deep learning-based classification methods alongside images not using the technique. The neural network classifiers yielded single action classification accuracies of 66% for centering, and 78% for non-centering. The random forest classifiers achieved the average accuracy of 79% for single action classification, which is very close to the results of other studies using similar methods. In addition to single action classification, a set based classification is made. This is the method most suitable for implementation in an actual authentication system as the accuracy is much higher. The neural network and random forest classifiers have different strengths. The neural network is proficient at classifying mouse actions that are of similar appearance in terms of length, location, and curvature. The random forest classifiers seem to be more consistent in these regards, although the accuracy deteriorates for especially long actions. As the different classification methods in this study have different strengths and weaknesses, a composite classification experiment was made where the output was determined by the least ambiguous output of the two models. This composite classification had an accuracy of 83%, meaning it outperformed both the individual models.

Segmentation of mammograms pertains to assigning a meaningful label to each pixel found in the image. The segmented mammogram facilitates both the function of Computer Aided Diagnosis Systems and the development of tools used by radiologists during examination. Over the years many approaches to this problem have been presented. A surge in the popularity of new methods to image processing involving deep neural networks present new possibilities in this domain, and this thesis evaluates mammogram segmentation as an application of a specialized neural network architecture, U-net. Results are produced on publicly available datasets mini-MIAS and CBIS-DDSM. Using these two datasets together with mammograms from Hologic and FUJI, instances of U-net are trained and evaluated within and across the different datasets. A total of 10 experiments are conducted using 4 different models. Averaged over classes Pectoral, Breast and Background the best Dice scores are: 0.987 for Hologic, 0.978 for FUJI, 0.967 for mini-MIAS and 0.971 for CBIS-DDSM.

Fantastic progress has been made within the field of machine learning and deep neural networks in the last decade. Deep convolutional neural networks (CNN) have been hugely successful in imageclassification and object detection. These networks can automate many processes in the industries and increase efficiency. One of these processes is image classification implementing various CNN-models. This thesis addressed two different approaches for solving the same problem. The first approach implemented two CNN-models to classify images. The large pre-trained VGG-model was retrained using so-called transfer learning and trained only the top layers of the network. The other model was a smaller one with customized layers. The trained models are an end-to-end solution. The input is an image, and the output is a class score. The second strategy implemented several classical image processing algorithms to detect the individual defects existed in the pictures. This method worked as a ruled based object detection algorithm. Canny edge detection algorithm, combined with two mathematical morphology concepts, made the backbone of this strategy. Sandvik Coromant operators gathered approximately 1000 microscopical images used in this thesis. Sandvik Coromant is a leading producer of high-quality metal cutting tools. During the manufacturing process occurs some unwanted defects in the products. These defects are analyzed by taking images with a conventional microscopic of 100 and 1000 zooming capability. The three essential defects investigated in this thesis defined as Por, Macro and Slits. Experiments conducted during this thesis show that CNN-models is a good approach to classify impurities and defects in the metal industry, the potential is high. The validation accuracy reached circa 90 percentage, and the final evaluation accuracy was around 95 percentage , which is an acceptable result. The pretrained VGG-model reached a much higher accuracy than the customized model. The Canny edge detection algorithm combined dilation and erosion and contour detection produced a good result. It detected the majority of the defects existed in the images.