Global ETD Search

11	Hluboké neuronové sítě pro rozpoznání tváří ve videu / Deep Learning for Facial Recognition in Video Mihalčin, Tomáš January 2018 (has links) This diploma thesis focuses on a face recognition from a video, specifically how to aggregate feature vectors into a single discriminatory vector also called a template. It examines the issue of the extremely angled faces with respect to the accuracy of the verification. Also compares the relationship between templates made from vectors extracted from video frames and vectors from photos. Suggested hypothesis is tested by two deep convolutional neural networks, namely the well-known VGG-16 network model and a model called Fingera provided by company Innovatrics. Several experiments were carried out in the course of the work and the results of which confirm the success of proposed technique. As an accuracy metric was chosen the ROC curve. For work with neural networks was used framework Caffe.
12	Návrh marketingové strategie pro firmu / Marketing Strategy Proposal for a Company Zeman, Milan January 2014 (has links) This master’s thesis identifies current marketing processes and tools of cafe Caffe Marco. After that the analyses of the evolution of the external and internal environment are realized and proposed relevant marketing strategy based on researches and analyses. The proposed actions are fully reflected in the measures in related parts of organizational and financial character, and the key factors for successful implementation of the proposed measures are set.
13	Identifikace osob pomocí hlubokých neuronových sítí / Deep Neural Networks for Person Identification Duban, Michal January 2016 (has links) This master's thesis deals with design and implementation of convolutional neural networks used in person re-identification. Implemented convolutional neural networks were tested on two datasets CUHK01 a CUHK03. Results, comparable with state of the art methods were acheved on these datasets. Designed networks were implemented in Caffe framework.
14	Automatic image-based road crack detection methods Some, Liene January 2016 (has links) Pavement crack detection is an important procedure in road maintenanceand traffic safety. Traditionally, the road inventory was performed by field inspection, now it is replaced by the evaluation of mobile mapping system images. The acquired images are still a significant source of temporal condition of thepavement surface. The automatisation of crack detection is highly necessarybecause it could decrease workload, and therefore, maintenance costs. Two methods for automatic crack detection from mobile mapping imageswere tested: step by step pixel based image intensity analysis, and deep learning. The objective of this thesis is to develop and test the workflow for the streetview image crack detection and reduce image database by detecting no-cracksurfaces. To examine the performance of the methods, their classification precisionwas compared. The best-acquired precision with the trained deep learningmodel was 98% that is 3% better than with the other method and it suggeststhat the deep learning is the most appropriate for the application. Furthermore, there is a need for faster and more precise detection methods, and deep learningholds promise for the further implementation. However, future studies areneeded and they should focus on full-scale image crack detection, disturbingobject elimination and crack severity classification. Road cracks Crack detection Mobile mapping Deep learning CrackIT Caffe Civil Engineering Samhällsbyggnadsteknik Other Civil Engineering Annan samhällsbyggnadsteknik Infrastructure Engineering Infrastrukturteknik
15	Co-designing Communication Middleware and Deep Learning Frameworks for High-Performance DNN Training on HPC Systems Awan, Ammar Ahmad 10 September 2020 (has links) No description available. Computer Science Artificial Intelligence Data Parallelism Model Parallelism Hybrid Parallelism Keras Caffe TensorFlow PyTorch, MPI, Eager Execution Deep Learning Scalable DNN Training MVAPICH2-GDR CUDA-Aware MPI
16	Polyfunkční objekt Pardubice / Multifunctional building Pardubice Dvořáková, Jana January 2013 (has links) The Master thesis presents a design of the multifunctional building in City of Pardubice. The building has three functions: caffe house, administration and also housing. The building has four floor without basement and there is a level roof. I tis designed as a reinforced concrete frame and walls with ventilated fasade do not have a bearing function. Design of building mens the general technical requirements for the construction.
17	Klasifikace obrazů s pomocí hlubokého učení / Image classification using deep learning Hřebíček, Zdeněk January 2016 (has links) This thesis deals with image object detection and its classification into classes. Classification is provided by models of framework for deep learning BVLC/Caffe. Object detection is provided by AlpacaDB/selectivesearch and belltailjp/selective_search_py algorithms. One of results of this thesis is modification and usage of deep convolutional neural network AlexNet in BVLC/Caffe framework. This model was trained with precision 51,75% for classification into 1 000 classes. Then it was modified and trained for classification into 20 classes with precision 75.50%. Contribution of this thesis is implementation of graphical interface for object detction and their classification into classes, which is implemented as aplication based on web server in Python language. Aplication integrates object detection algorithms mentioned abowe with classification with help of BVLC/Caffe. Resulting aplication can be used for both object detection (and classification) and for fast verification of any classification model of BVLC/Caffe. This aplication was published on server GitHub under license Apache 2.0 so it can be further implemented and used.
18	Odhad hloubky pomocí konvolučních neuronových sítí / Depth Estimation by Convolutional Neural Networks Ivanecký, Ján January 2016 (has links) This thesis deals with depth estimation using convolutional neural networks. I propose a three-part model as a solution to this problem. The model contains a global context network which estimates coarse depth structure of the scene, a gradient network which estimates depth gradients and a refining network which utilizes the outputs of previous two networks to produce the final depth map. Additionally, I present a normalized loss function for training neural networks. Applying normalized loss function results in better estimates of the scene's relative depth structure, however it results in a loss of information about the absolute scale of the scene.
19	Service robot for the visually impaired: Providing navigational assistance using Deep Learning Shakeel, Amlaan 28 July 2017 (has links) No description available. Electrical Engineering Robotics Computer Science Assistive technology Deep learning Robotics Indoor navigation Computer vision Robot Operating System ROS Caffe Faster R-CNN Convolutional Neural Networks CNN Microsoft Kinect Service robots visually impaired mobility depth perception
20	Detektor ohně ve videu / Detection of Fire in Video Poledník, Tomáš January 2015 (has links) {This thesis deals with fire detection in video by colour analysis and machine learning, specifically deep convolutional neural networks, using Caffe framework. The aim is to create a vast set of data that could be used as the base element of machine learning detection and create a detector usable in real application. For the purposes of the project a set of tools for fire sequences creation, their segmentation and automatic labeling is proposed and created together with a large test set of short sequences with artificial modelled fire.

Search results