|
|
Identification of 3D objects for Robotic Applications
Hujňák, Jaroslav ; Návrat, Aleš (referee) ; Matoušek, Radomil (advisor)
This thesis focuses on robotic 3D vision for application in Bin Picking. The new method based on Conformal Geometric Algebra (CGA) is proposed and tested for identification of spheres in Pointclouds created with 3D scanner. The speed, precision and scalability of this method is compared to traditional descriptors based method. It is proved that CGA maintains the same precision as the traditional method in much shorter time. The CGA based approach seems promising for the use in the future of robotic 3D vision for identification and localization of spheres.
|
|
|
Big Block File System
Rajman, Jakub ; Lampa, Petr (referee) ; Čejka, Rudolf (advisor)
Master's thesis treats of implementation of big block file system for FreeBSD operating system. The introduction of this document is dedicated to theoretically analysis, which is oriented on history, sense and usage of file systems. Next chapter describes the architecture of UFS/FFS file system. Implementation part starts with introducing design of new file system, which was isnpired by MSDOSFS file system. Last part of this thesis presents implementation of file system with great emphasis on problems, which can happen during programming.
|
|
|
Image Retrieval Based on Color Histograms
Sailer, Zbyněk ; Hradiš, Michal (referee) ; Beran, Vítězslav (advisor)
This thesis deals with description of existing methods of image retrieval. It contains set of methods for image description, coding of global and local descriptor (SIFT, etc.) and describes method of effective searching in multidimensional space (LSH). It continues with proposal and testing of three global descriptors using color histograms, histogram of gradients and the combination of both. The last part deals with similar image retrieval using proposed descriptors and the indexing method LSH and compares the results with the existing method. Product of this work is an experimental application which demonstrates the proposed solution.
|
|
| |
|
|
Hodnocení sortimentu třapatkovek (Echinacea) v klimatických podmínkách středoevropského termofytika
Marešová, Monika
This diploma thesis Evaluation of the assortment of coneflowers (Echinacea) in the climatic conditions of Central European thermophytic deals with the evaluation of the genus Echinacea (L.) Moench assortment. The thesis is focused on topics dealing with history, morphology, taxonomy, cultivation and breeding of the family Coneflowers. Regarding the practical part, 45 cultivars of the genus Echinacea were observed and evaluated. Measured and evaluated characters were compared with other authors ratings.
|
|
|
Možnosti péče a obnovy genofondu rodu Rheum L.
Kostovská, Lucie
The aim of this thesis is to describe the items of the gene pool of the species Rheum L. located in the experimental garden of the Faculty of Horticulture of Mendel University in Lednice, to propose the procedure of relocation of this gene pool and evaluate the results of this relocation and to record the wintering of plants and the overall condition of the gene pool as at 30 March 2016. Included in this thesis is the process of monitoring and evaluation of the items of this gene pool. Descriptors were evaluated upon the basis of the valid classification system for the Rheum L species. A total of 44 items were evaluated. These evaluations were combined with laboratory tests of vitamin C, oxalic acid, mononitrate and fibre contents in stems. Tests for refractive solids, solids and overall antioxidant capacity were carried out. Samples of roots of medicinal species of rhubarb were obtained but laboratory tests for the contents were not carried out due to technical difficulties.
|
|
|
Identification of 3D objects for Robotic Applications
Hujňák, Jaroslav ; Návrat, Aleš (referee) ; Matoušek, Radomil (advisor)
This thesis focuses on robotic 3D vision for application in Bin Picking. The new method based on Conformal Geometric Algebra (CGA) is proposed and tested for identification of spheres in Pointclouds created with 3D scanner. The speed, precision and scalability of this method is compared to traditional descriptors based method. It is proved that CGA maintains the same precision as the traditional method in much shorter time. The CGA based approach seems promising for the use in the future of robotic 3D vision for identification and localization of spheres.
|
|
|
Utilisation of shape analysis methods for object classification in medical images
Karela, Jiří ; Odstrčilík, Jan (referee) ; Chmelík, Jiří (advisor)
Bachelor thesis deals with problems of shape analysis. It describes some procedures and methods related to this kind of analysis. The thesis is divided into theoretical part, practical part and conclusion. In the theoretical part we describe in greater detail some methods, with the help of which the practical part was solved. But other theories related to the topic are also described. The practical part then follows the given theory and solves the problem of shape analysis due to the knowledge gained in the theory. The algorithm is tested on medical data from CT of vertebrae. The conclusion serves as a summary and evaluation of the shape analysis solution. It also serves as a reflection on the realization of our method, ie how our solution and result could be improved.
|
|
|
Content-Based Searching for Similar CT Scans
Hošek, Pavel ; Klíma, Ondřej (referee) ; Španěl, Michal (advisor)
The work deals with the design and implementation of tool for Content-Based Searching for similar CT scans. This work also deals with comparision of individual methods for searching for similar CT scans. Third-party libraries are used to extract individual descriptors. Furthermore, this work presents results of the implemented searching tool and also presents results of the comparision of individual methods for Content-Based Searching for similar CT scans and suggests possible improvements.
|
|
|
Bin Picking and Robotic Vision
Múčka, Jan ; Parák, Roman (referee) ; Matoušek, Radomil (advisor)
The aim of this master’s thesis is to describe the Robotic Vision for Bin Picking usage and creating an application for the realization of this task. This application will be able to distinguish several objects based on data from a camera with deep perception and should find the location of object, recognize it and determine its location and orientation. Bin Picking is one of the biggest challenges in today's automation.
|
guest ::
