|
|
Navigation and Information System for Visually Impaired
Hrbáček, Jan ; Volf, Jaromír (referee) ; Grepl, Robert (referee) ; Singule, Vladislav (advisor)
Poškození zraku je jedním z nejčastějších tělesných postižení -- udává se, že až 3 % populace trpí vážným poškozením nebo ztrátou zraku. Oslepnutí výrazně zhoršuje schopnost orientace a pohybu v okolním prostředí -- bez znalosti uspořádání prostoru, jinak získané převážně pomocí zraku, postižený zkrátka neví, kudy se pohybovat ke svému cíli. Obvyklým řešením problému orientace v neznámých prostředích je doprovod nevidomého osobou se zdravým zrakem; tato služba je však velmi náročná a nevidomý se musí plně spolehnout na doprovod. Tato práce zkoumá možnosti, kterými by bylo možné postiženým ulehčit orientaci v prostoru, a to využitím existujících senzorických prostředků a vhodného zpracování jejich dat. Téma je zpracováno skrze analogii s mobilní robotikou, v jejímž duchu je rozděleno na část lokalizace a plánování cesty. Zatímco metody plánování cesty jsou vesměs k dispozici, lokalizace chodce často trpí značnými nepřesnostmi určení polohy a komplikuje tak využití standardních navigačních přístrojů nevidomými uživateli. Zlepšení odhadu polohy může být dosaženo vícero cestami, zkoumanými analytickou kapitolou. Předložená práce prvně navrhuje fúzi obvyklého přijímače systému GPS s chodeckou odometrickou jednotkou, což vede k zachování věrného tvaru trajektorie na lokální úrovni. Pro zmírnění zbývající chyby posunu odhadu je proveden návrh využití přirozených význačných bodů prostředí, které jsou vztaženy ke globální referenci polohy. Na základě existujících formalismů vyhledávání v grafu jsou zkoumána kritéria optimality vhodná pro volbu cesty nevidomého skrz městské prostředí. Generátor vysokoúrovňových instrukcí založený na fuzzy logice je potom budován s motivací uživatelského rozhraní působícího lidsky; doplňkem je okamžitý haptický výstup korigující odchylku směru. Chování navržených principů bylo vyhodnoceno na základě realistických experimentů zachycujících specifika cílového městského prostředí. Výsledky vykazují značná zlepšení jak maximálních, tak středních ukazatelů chyby určení polohy.
|
|
|
Sensor Calibration for Multispectral Data Fusion in Mobile Robotics
Kalvodová, Petra ; Hanzl, Vlastimil (referee) ; Mazal,, Jan (referee) ; Pospíšil,, Jiří (referee) ; Weigel, Josef (advisor)
Thesis deals with data fusion and calibration of sensory system of Orpheus-X3 robot and EnvMap mapping robot. These robots are parts of Cassandra robotic system that is used for exploration of hazardous or inaccessible areas. Corrections of measured distances are determined for used laser scanners Velodyne HDL-64, Velodyne HDL-32 and range camera SwissRanger SR4000. Software MultiSensCalib has been created and is described. This software is used for determination of intrinsic parameters of heterogeneous cameras of the sensory head and for determination of mutual position and orientation of these sensors. Algorithm for data fusion of CCD camera stereo pair, thermal imager stereo pair and range camera is proposed. Achieved calibration and data-fusion parameters are evaluated by several experiments.
|
|
|
Analysis of Baroque sculpture based on X-ray fluorescence imaging and X-ray\ncomputed tomography data fusion
Vavřík, Daniel ; Kumpová, Ivana ; Vopálenský, Michal ; Lauterkranc, J.
It is advantageous to combine information about geometry and the inner structure of historical artifacts with information about the elemental composition of decorative layers, typically covering historical wooden sculptures. X-ray computed tomography describing artifact structure is quite common and easy. Standard X-ray fluorescence (XRF) analysis of decorative layers is typically done for several selected spots of the artifact’s surface utilizing single pad detector. XRF imaging fully describing the surface’s elemental composition is commonly done for flat objects, while time consuming XRF tomography is applied to relatively small objects. It will be shown in this work that an effective fusion combination of XRF imaging and X-ray tomography describing the whole object can be realized even when using a limited number of XRF images.
|
|
|
Possibilities of Electrochemical Analysis Using a System of Electrodes With Non-Specific Response
Ederer, Jakub ; Nesměrák, Karel (advisor) ; Ludvík, Jiří (referee)
The master thesis present the possibilities of processing of electrochemical data from a group of four electrodes with non-selective response (simple sensor array) for electrochemical analysis with potential application of the results achieved in the construction of the sensor field type "electronic tongue". This simple system was applied to the sample simulating the food product. Electrochemical data were processed through mathematical operations such as Gaussian approximation, deconvolution or using basic mathematical operations.
|
|
|
Data fusion
Janíková, Veronika ; Hovorka, Tomáš (advisor) ; Anděl, Jiří (referee)
This bachelor's thesis deals with a data fusion, which is a one of the possible solutions to the common problem of data availability in praxis. In the first part, practical use of data fusion, especially in marketing, fundamental algorithms and data fusion problems are discussed. The main part of this thesis deals with the so-called "unconstrained statistical fusion". Firstly, one of the possible processes of this type of fusion is described theoretically in detail. This process involves branching into four different types of data fusion. Next, a method of theoretical evaluating the quality of the general fusion model is designed using statistical indicators. The practical part of the thesis contents processes of four types of unconstrained statistical fusion and their evaluation which both are programmed in statistical program R. Furthermore, the fusion is applied to our artificially generated database and also to a real data collected in praxis by Czech public opinion research company Median. In the very last part of the thesis, the results of fusions applied to these two databases are interpreted, evaluated and discussed.
|
|
|
Linked Data Integration
Michelfeit, Jan ; Knap, Tomáš (advisor) ; Klímek, Jakub (referee)
Linked Data have emerged as a successful publication format which could mean to structured data what Web meant to documents. The strength of Linked Data is in its fitness for integration of data from multiple sources. Linked Data integration opens door to new opportunities but also poses new challenges. New algorithms and tools need to be developed to cover all steps of data integration. This thesis examines the established data integration proceses and how they can be applied to Linked Data, with focus on data fusion and conflict resolution. Novel algorithms for Linked Data fusion are proposed and the task of supporting trust with provenance information and quality assessment of fused data is addressed. The proposed algorithms are implemented as part of a Linked Data integration framework ODCleanStore.
|
|
|
Methods for Simultaneous Self-localization and Mapping for Depht Cameras
Ligocki, Adam ; Jelínek, Aleš (referee) ; Žalud, Luděk (advisor)
Tato diplomová práce se zabývá tvorbou fúze pozičních dat z existující realtimové im- plementace vizuálního SLAMu a kolové odometrie. Výsledkem spojení dat je potlačení nežádoucích chyb u každé ze zmíněných metod měření, díky čemuž je možné vytvořit přesnější 3D model zkoumaného prostředí. Práce nejprve uvádí teorií potřebnou pro zvládnutí problematiky 3D SLAMu. Dále popisuje vlastnosti použitého open source SLAM projektu a jeho jednotlivé softwarové úpravy. Následně popisuje principy spo- jení pozičních informací získaných vizuálními a odometrickými snímači, dále uvádí popis diferenciálního podvozku, který byl použit pro tvorbu kolové odometrie. Na závěr práce shrnuje výsledky dosažené datovou fúzí a srovnává je s původní přesností vizuálního SLAMu.
|
|
|
Visualization Environment for Robot Remote Control
Blahož, Vladimír ; Polok, Lukáš (referee) ; Španěl, Michal (advisor)
This thesis presents possibilities of 3D point cloud and true colored digital video fusion that can be used in the process of robot teleoperation. Advantages of a 3D environment visualization combining more than one sensor data, tools to facilitate such data fusion, as well as two alternative practical implementations of combined data visualization are discussed. First proposed alternative estimates view frustum of the robot's camera and maps real colored video to a semi-transparent polygon placed in the view frustum. The second option is a direct coloring of the point cloud data creating a colored point cloud representing color as well as depth information about an environment.
|
|
|
Sensor Data Analysis for Advanced User Interfaces
Chmiel, Filip ; Polok, Lukáš (referee) ; Beran, Vítězslav (advisor)
The paper deals with the creation of interface based on multiple input signals, i.e. multimodal interface. For this purpose analyzes the benefits of the approach to communicate with the device that way. The work also includes an overview of the level at which you can perform data fusion, and different approaches to the layout of the system architecture for multimodal data processing. The important part is the actual design of the system, where for the interface was chosen distributed architecture using software agents for processing inputs. As a method for data integration was picked hybrid fusion based on dialog driven and unification strategy. The result should be an interface for media center control and interaction with other devices around the user.
|
|
|
Advanced Navigation in Heterogeneous Multi-robot Systems in Outdoor Environment
Jílek, Tomáš ; Duchoň,, František (referee) ; Mazal, Jan (referee) ; Žalud, Luděk (advisor)
The doctoral thesis discusses current options for the navigation of unmanned ground vehicles with a focus on achieving high absolute compliance of the required motion trajectory and the obtained one. The current possibilities of key self-localization methods, such as global satellite navigation systems, inertial navigation systems, and odometry, are analyzed. The description of the navigation method, which allows achieving a centimeter-level accuracy of the required trajectory tracking with the above mentioned self-localization methods, forms the core of the thesis. The new navigation method was designed with regard to its very simple parameterization, respecting the limitations of the used robot drive configuration. Thus, after an appropriate parametrization of the navigation method, it can be applied to any drive configuration. The concept of the navigation method allows integrating and using more self-localization systems and external navigation methods simultaneously. This increases the overall robustness of the whole process of the mobile robot navigation. The thesis also deals with the solution of cooperative convoying heterogeneous mobile robots. The proposed algorithms were validated under real outdoor conditions in three different experiments.
|
guest ::
