|
| |
|
|
3D object detection from pointcloud
Červený, Patrik ; Richter, Miloslav (referee) ; Zemčík, Tomáš (advisor)
The bachelor thesis deals with the detection of 3D objects in a point cloud acquired by a LIDAR sensor. The thesis describes the sensors that collect the data for the point cloud, the methods to process the data and the final representation of the collected data, using the chosen application. By using a LIDAR sensor we detect a 3D image of the point cloud at the railway stations in Brno and with the help of the available methods for processing and application we try to describe what the sensor shows us through the data.
|
|
|
UIC codes detection and recognition
Zemčík, Tomáš ; Richter, Miloslav (referee) ; Janáková, Ilona (advisor)
Machine detection and reading of UIC identification codes on railway rolling stock allows for automation of some processes on the railway and makes running of the railway safer and more efficient. This thesis provides insight into the problem of machine text detection and reading. It further proposes and implements a solution to the problem of reading UIC codes in line camera scanned images.
|
|
|
Balancing Shafts Support Optimalization for Zetor 4V UŘ III Engine
Zemčík, Tomáš ; Franz, Rudolf (referee) ; Rauscher, Jaroslav (advisor)
To make a check of an contemporary balancing verification of diesel engine Zetor UŘ III with type identification 1505, the engine power 90 kW and especially friction bearing design, which could replace existing needle bearing HK 4520 type, is the aim of this diploma thesis. Bearing type modification requires constructional adjustment of engine block and balancing shaft and therefore this proposal for construction another aim in my diploma thesis. The last part of my diploma thesis is an economic balance original imposition against newly designed. Calculations are made using mathematical software MathCad, the balancing shaft is made using ProEngineer software and control calculations of bearing stresses are made with ADAMS and FEM of ANSYS system. Motivation to write this work is to prove the possibility how to decrease manufacturing costs of ZETOR TRACTORS a.s. company.
|
|
|
3D model from multiview
Zemčík, Tomáš ; Klečka, Jan (referee) ; Richter, Miloslav (advisor)
Reconstruction of 3D model from multiple view images allows us to perform a contactless measurement of real world objects. This work contains theoretical and mathematical background necessary for understanding problems of 3D reconstruction. It also proposes possible hardware and software solutions for the task of measuring a hood with EEG sensors while on patients head.
|
|
|
Simulation of cutting force during milling process with straight tooth plain milling cutter.
Zemčík, Tomáš ; Sedlák, Josef (referee) ; Zemčík, Oskar (advisor)
To make a simulation of cutting force during milling process with cilindrical cutter is the aim of this diploma thesis. Preliminary part is devoted to technology of milling, milling cutters and cutting materials. The next section is aimed at kinematics of the cutting process, a theoretical analysis of power proportion, the possibility of measurement of force actions. General information about the programming software, a theoretical simulation model, graphical environment of created application, are the other points of this diploma thesis. The work also includes evaluation of the experimentally measured values and compared with values obtained from the created application.
|
|
|
Image based road surface segmentation with lane detection
Turoň, Rudolf ; Honec, Peter (referee) ; Zemčík, Tomáš (advisor)
This bachelor thesis deals with road semantic segmentation with lane lines detection. The aim of the thesis is to conduct a survey of methods used for general segmentation and lane lines detection, collect a representative dataset for testing, design a data processing system including implementation for semantic segmentation and detection of lanes in image, video and live camera input. In preprocessing phase images are filtered using morphological transformations. The segmentation is performed using the watershed method with labels, and an adaptive algorithm is designed to find the labels. The lanes are searched for in the thresholded projectively transformed image using the sliding window technique. As a result, a segmentation accuracy of 88.3% is achieved based on the IoU metric. The thesis concludes with a discussion of the obtained results and summarizes the possibilities for further improvements of the system.
|
|
|
Detection of changes in the image
Čech, Jan ; Zemčík, Tomáš (referee) ; Richter, Miloslav (advisor)
The aim of this thesis is finding changes in two similar pictures made in different periods of time. This task belongs to the field of computer vision. To solve this problem different methods of computer vision are used. First the angle of scanning has to be found. Then pictures go through the proces of preprocessing, afterwards the segmentation and the determination of descriptors are carried out. Finally, the pictures are compared and the differences are pointed out.
|
|
|
On Hyperspectral Analysis of Water Soluble Writing Inks
Zemčík, Tomáš ; Horák, Karel
In this short paper a possibility of using HyperspectralImaging based analysis of water soluble inks is investigated.The current research has investigated this method mostly formarker inks, ballpoint pen inks and gel inks, yet curiously thewhole water soluble ink class seems underrepresented. Sampleswere prepared and hyperspectral images of said samples taken,and some preliminary statistical analysis was performed. Thedata at this stage suggests that at least some samples arevisually distinguishable from other samples, while certain othersamples are virtually indistinguishable. A method for applyingthis knowledge in a handwritten text ink identification is brieflyoutlined and implemented in a simplified way, the results arepromising on good input data, but poor on subpar images.The weaknesses of the method are discussed and potentialimprovement strategies proposed.
|
|
|
Detection of changes in the image
Čech, Jan ; Zemčík, Tomáš (referee) ; Richter, Miloslav (advisor)
The aim of this thesis is finding changes in two similar pictures made in different periods. This task belongs to the field of computer vision. To solve this problem different methods of computer visions are used in several solution versions. Program is working with two scenes. In final version are objects from both scenes compared. The result is written into logging file.
|
guest ::
