National Repository of Grey Literature 160 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Classification of Czech sign language alphabet letters using cnn – preliminary study
Krejsa, Jiří ; Věchet, Stanislav
Abstract: The paper deals with the classification of Czech sign language single hand alphabet letters from static images using convolutional neural network (CNN). Proposed CNN architecture exhibits about 71% successful rate of classifying the letters signed by the person not included in the training data set.
Anomalies detection in time-series data for the internal diagnostics of autonomous mobile robot
Věchet, Stanislav ; Krejsa, Jiří ; Chen, K.S.
Autonomous mobile robots are complex mechatronic machines which consists of numerous hardware and software modules working asynchronously to achieve desired behaviour. As there are many frameworks which helps to overcome the flat learning curve the problem of internal diagnostics arises. While users and developers are able to focus only on solving the high level problem algorithm or methods the internal states of the system is hidden. This helps to separate the users from solving hardware issues, which is helping until everything works properly. We present an algorithm which is able to detect anomalies in time based behaviour of the robot to improve the users confidence that the internal robot framework works correctly and as desired. The algorithm is based on probabilistic patterns detection based on Bayesian probabilistic theory.
Design and realization of manipulator for mobile robot
Konečný, Martin ; Brablc, Martin (referee) ; Krejsa, Jiří (advisor)
This Bachelor’s thesis describes a design and prototype realization of manipulator for mobile robot. One of the possible uses of the robot is to transport mail in a company to individual departments. The aim of this thesis is to design a device, that would enable loading and unloading of the packages to a mobile robot.
Design and implementation of user interface for ROS framework using Android
Podolinský, Ondřej ; Spáčil, Tomáš (referee) ; Krejsa, Jiří (advisor)
This bachelor’s thesis deals with developing new mobile application, which enables ROS data visualization and administration. Application development, structure of ROS system, communication in ROS are described too. Thesis contains summary of available applications.
Evaluation of image processing methods for flying object tracking using drone
Daniš, Stanislav ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
The bachelor thesis was focused on the evaluation of tracking algorithms contained in the OpenCV library against the motion blur effect. A dataset of videos was created with defined ranges of selected parameters that influenced the motion blur effect (speed, distance from the object, position of light and others). Each of the videos was processed using a tracking algorithm. From these results, findings on the effectiveness of each of the algorithms for a defined situation were formulated in the conclusion.
Vibration of faulty bearing depending on the load
Slaninová, Barbora ; Marcián, Petr (referee) ; Krejsa, Jiří (advisor)
The subject of the presented bachelor thesis is an analysis of a bearing vibration during its failure on inner race with varying load. The work aims to create a model simulating the time course of vibrations in the event of a bearing failure depending on the load and speed of the bearing. The work compares the frequency and time model of the rolling bearing error spectrum. A model of bearing error frequencies was also created, which is supplemented by a force action in the next step. To parameterize the model, data were experimentally measured on a bearing that takes on three possible states. The first bearing has a defect on inner race measuring 0.25 mm, the second bearing 0.5 mm and the third is free of defects. The measurement takes place on a test bed in 135 repetitions. Inventor is used to design the bearing with defect. The measured data are processed and visualized with MATLAB. The measured values show that the rate of vibration is not only dependent on the load and speed, but also the size of the defect.
Sign language detection methods - review
Petr, Luboš ; Venglář, Vojtěch (referee) ; Krejsa, Jiří (advisor)
The Aim of this work is to describe various methods of sign language detection. The output of individual methods is a functional translation of sign language into text in real time. In addition to glove and kinect detection, this work deals with the possibilities of sign language detection from image recording, which is the most prospective method of detection in the future. The thesis is also focused on sign classification using neural networks.
Road detection in outdoor environment using image processing
Vrbičanová, Antónia ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
The Master’s thesis deals with the issue of the road detection in the outdoor environment using image processing. It is highly required that the methods selected are robust to sudden light changes within the image and effective in detection of wide variety of road surfaces possibly comprising certain kinds of pollution. Two methods have been used in order to reach the desired goal. The initial method uses standard algorithms of the image processing. Main outcome of this method are highlighted road boundaries. The following methodisbasedonconvolutionalneuralnetworks.Inthiscasewehaveclassificationtask. The result of this method is the estimation of the road direction. In the whole process, severalneuralnetworkstructureshavebeendesigned.Afterthenetworktrainingthemost suitable one was selected. Eventually, the results have been retested using newly created test set. Both of these methods are implemented in programming language Python.
Semantic segmentation of images using convolutional neural networks
Špila, Filip ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
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.
Design of communication interface in WBAN systems
Kandera, Tomáš ; Najman, Jan (referee) ; Krejsa, Jiří (advisor)
Táto diplomová práca sa zaoberá technickou realizáciou WBAN zariadenia, ktoré je schopné súbežne komunikovať prostredníctvom dvoch bezdrôtových komunikačných protokolov. Rešerš dostupných riešení je dostupná s hodnotením jednotlivých produktov podľa vopred stanovených kritérií. Návrh z hľadiska software obsahuje tvorbu vlastného BLE servisu, konfiguráciu Timeslot API a periférií často využívaných vo WBAN zariadeniach. Výroba dosiek plošných spojov pre zariadenie a dedikovaný ovládač zahŕňa vlastnú anténu, nabíjací obvod batérie a nRF52810 čip. Testovanie prototypov je zhrnuté v poslednej kapitole spoločne s experimentálnym meraním útlmu živočíšneho tkaniva.

National Repository of Grey Literature : 160 records found   1 - 10nextend  jump to record:
See also: similar author names
2 KREJSA, Jakub
10 KREJSA, Jan
10 Krejsa, Jan
1 Krejsa, Josef
Interested in being notified about new results for this query?
Subscribe to the RSS feed.