This work is focused on classifying photos which are uploaded on dating service Lidé.cz. Pictures are classified into two categories based on whether they contain pornographic content or not. Convolutional neural networks are used for classification and these neural networks are taught by using Caffe framework. The results of this work fulfilled all requirements from Seznam.cz, a.s. company. Classification accuracy of the best model on created testing dataset with 5643 photos was 93,64 % and the time for classification of photography is low enough to perform classification in real time. The first part contains an analysis of the current approaches for image classification. The second part focuses on the analysis and draft of the solution and the third part describes the implementation of the solution and the testing of neural networks models.

Training prototxt file containing the hyperparameter settings for combinations 5 and 15 of optimized training runs.

Plots generated from training logs of combinations 5 and 15 of optimized training runs.

This thesis introduces a 3D body tracking system based on neutral networks and 3D geometry, which can robustly estimate body poses and accurate body joints. This system takes RGB-D data as input. Body poses and joints are firstly extracted from color image using deep learning approach. The estimated joints and skeletons are further translated to 3D space by using camera calibration information. This system is running at the rate of 3 4 frames per second. It can be used to any RGB-D sensors, such as Kinect, Intel RealSense [14] or any customized system with color depth calibrated. Comparing to the sate-of-art 3D body tracking system, this system is more robust, and can get much more accurate joints locations, which will benefits projects require precise joints, such as virtual try-on, body measure, real-time avatar driven.

Tato práce se zabývá rešerší a implementací vybraných architektur konvolučních neuronových sítí pro segmentaci obrazu. V první části jsou shrnuty základní pojmy z teorie neuronových sítí. Tato část také představuje silné stránky konvolučních sítí v oblasti rozpoznávání obrazových dat. Teoretická část je uzavřena rešerší zaměřenou na konkrétní architekturu používanou na segmentaci scén. Implementace této architektury a jejích variant v Caffe je převzata a upravena pro konkrétní použití v praktické části práce. Nedílnou součástí tohoto procesu jsou kroky potřebné ke správnému nastavení softwarového a hardwarového prostředí. Příslušná kapitola proto poskytuje přesný návod, který ocení zejména noví uživatelé Linuxu. Pro trénování všech variant vybrané sítě je vytvořen vlastní dataset obsahující 2600 obrázků. Je také provedeno několik nastavení původní implementace, zvláště pro účely použití předtrénovaných parametrů. Trénování zahrnuje výběr hyperparametrů, jakými jsou například typ optimalizačního algoritmu a rychlost učení. Na závěr je provedeno vyhodnocení výkonu a výpočtové náročnosti všech natrénovaných sítí na testovacím datasetu.

This thesis deals with the current methods of semantic segmentation using deep learning. Other approaches of neaural networks in the area of deep learning are also discussed. It contains historical solutions of neural networks, their development, and basic principle. Convolutional neural networks are nowadays the most preferable networks in solving tasks as detection, classification, and image segmentation. The functionality was verified on a freely available environment based on conditional random fields as recurrent neural networks and compered with the deep convolutional neural networks using conditional random fields as postprocess. The latter mentioned method has become the basis for training of new models on two different datasets. There are various enviroments used to implement neural networks using deep learning, which offer diverse perform possibilities. For demonstration purposes a Python application leveraging the BVLC\,/\,Caffe framework was created. The best achieved accuracy of a trained model for clothing segmentation is 50,74\,\% and 68,52\,\% for segmentation of VOC objects. The application aims to allow interaction with image segmentation based on trained models.

<p>The SPECT-CT machines manufactured by Siemens consists of two heavy detector heads(~1500lbs each) that are moved into various configurations for radionuclide imaging. These detectors are driven by large torque powered by motors in the gantry that enable linear and rotational motion. If the detectors collide with large objects – stools, tables, patient extremities, etc. – they are very likely to damage the objects and get damaged as well. <a>This research work proposes an intelligent real-time object detection system to prevent collisions</a> between detector heads and external objects in the path of the detector’s motion by implementing an end-to-end deep learning object detector. The research extensively documents all the work done in identifying the most suitable object detection framework for this use case, collecting, and processing the image dataset of target objects, training the deep neural net to detect target objects, deploying the trained deep neural net in live demos by implementing a real-time object detection application written in Python, improving the model’s performance, and finally investigating methods to stop detector motion upon detecting external objects in the collision region. We successfully demonstrated that a <i>Caffe</i> version of <i>MobileNet-SSD </i>can be trained and deployed to detect target objects entering the collision region in real-time by following the methodologies outlined in this paper. We then laid out the future work that must be done in order to bring this system into production, such as training the model to detect all possible objects that may be found in the collision region, controlling the activation of the RTOD application, and efficiently stopping the detector motion.</p>

Semantic segmentation is one of classic computer vision problems and strong tool for machine processing and understanding of the scene. In this thesis we use semantic segmentation in mountainous environment. The main motivation of this work is to use semantic segmentation for automatic location of geographic position, where the picture was taken. In this thesis we evaluated actual methods of semantic segmentation and we chose three of them  that are appropriate for adapting to mountainous environment. We split the dataset with mountainous environment into validation, train and test sets to use for training of chosen semantic segmentation methods. We trained models from chosen methods on mountainous data. We let segments from the best trained models get evaluated in electronic survey by respondents and we evaluated these segments in process of camera orientation estimation. We showed that chosen methods of semantic segmentation are possible to use in mountainous environment. Our models are trained on 11, 5 or 4 mountainous classes and the best of them achieve on 4 class mean IU 57.4%. Models are usable in practise. We show it by their deployment as a part of camera orientation estimation process.

The master thesis focuses on disparity map estimation using convolutional neural network. It discusses the problem of using convolutional neural networks for image comparison and disparity computation from stereo image as well as existing approaches of solutions for given problem. It also proposes and implements system that consists of convolutional neural network that measures the similarity between two image patches, and filtering and smoothing methods to improve the result disparity map. Experiments and results show, that the most quality disparity maps are computed using CNN on input patches with the size of 9x9 pixels combined with matching cost agregation and correction algorithm and bilateral filter.

This master's thesis deals with a vehicle detector based on the convolutional neural network and scene captured by drone. Dataset is described at the beginning, because the main aim of this thesis is to create practicly usable detector. Architectures of the forward neural networks which detector was created from are described in the next chapter. Techniques for building a detector based on the naive methods and current the most successful meta architectures follow the neural network architectures. An implementation of the detector is described in the second part of this thesis. The final detector was built on meta architecture Faster R-CNN and PVA neural network on which the detector achieved score over 90 % and 45 full HD frames per seconds.