|
|
Target tracking from radar images
Fojtík, Jakub ; Götthans, Jakub (referee) ; Maršálek, Roman (advisor)
This bachelor's thesis deals with data processing methods for target detection and subsequent target tracking from radar images. Two algorithms are presented, namely CFAR (constant false alarm rate) and BSTC (binary successive target cancelation). The BSTC algorithm continues to be used as the default detection algorithm for subsequent target tracking and evaluation, for which several algorithms are described here, however, special attention is paid to the Kalman filter, which, like the CFAR and BSTC algorithms, is developed here in the MATLAB programming environment in a single and multiple target tracking application.
|
|
|
Design of electronic control unit for rotational inverted pendulum
Sopoušek, Radek ; Appel, Martin (referee) ; Brablc, Martin (advisor)
The scope of this thesis is to create a dynamic model of the pendulum, design the control in inverse position, implement the swing-up task and add a controlled fall to a stable position, design and integrate the hardware with the existing pendulum model and implement the control using a state machine. The reader is introduced to the elements of a real device. A model is analytically constructed to be used for parameter identification and control design. Swing-up control is implemented using the moment method and two energy methods representing single and multiple-swing behavior. In the inverse position, the pendulum is controlled using LQR controller. For controlled fall to stable position, PD controller is used. For control purposes, a developmental microprocessor board was selected and integrated into the existing model with minimal changes to the functionality. The control was performed using a state machine whose robustness to parameter changes was experimentally verified.
|
|
|
Multiaxis feedback cooling of particle in optical trap
Číž, Adam ; Adámek, Roman (referee) ; Brablc, Martin (advisor)
This thesis deals with a design and implementation of algorithms for multiaxis feedback cooling (which means positional control) of a particle in an optical trap with use of Kalman filter. Two control methods are proposed here, each of which is intended for use of a different actuator: a laser intensity modulator or a pair of electrodes. Next, the implementation of both methods on hardware with an FPGA is described. Functioning of both proposed algorithms is proven by a numerical simulation. In addition, the functioning of the control using electrodes is demonstrated by an experiment with an optical trap. The second method is fully prepared for use in an experiment.
|
|
|
Object tracking in video
Boszorád, Matej ; Přinosil, Jiří (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis deals with the issue of tracking multiple objects in a video, specifically focusing on non-learning algorithms. The first chapter represents the theoretical part of the thesis, in which some of the often used tracking methods are described, such as mean-shift, scale-invariant object transformation, Kalman filter, particle filter and Gabor wavelet transformation. These algorithms are broken down by properties they use for proper tracking. The chapter also contains section assignment problem, which is mainly concerned with Hungarian algorithm. The next part describes options of merging multiple tracking methods that are broken down by construction type into parallel, cascade, weighted and discriminatory with example for each one. Moreover there is described adaptability of the tracking system. Bellow are described problems which may occur during tracking and possible solutions to them. This section consists of a solution of image noise, changes in illumination, appearance and extinction of an object, focusing mainly on solving the problem of object occlusion. Within the practical part is created algorithm composed of different types of tracking, the results of which are then compared with selected tracking systems from the multiple object tracking benchmark. The practical part includes the tools used and the explanation of the design, in which the main classes and methods used for the tracking are explained. Besides that, this section describes parallel merging and tracking adaptability . The results of the thesis contain a comparison of the use of tracking techniques separately and together. To compare the results, videos for pedestrian tracking and face tracking were used. This thesis was based on the assumption that merging multiple monitoring systems will help with the improvement of the tracking, which was confirmed by the results.
|
|
|
Robot for Robotour 2012
Vass, Robert ; Luža, Radim (referee) ; Rozman, Jaroslav (advisor)
The aim of this article is the theoretical analysis, proposal and implementation of a method for the operation of an autonomous robot for Robotour 2012 with the help of camera and sensor usage. Key issues to be faced are the computer vision, robot sensing uncertainty and the localization problem. Firstly, road extraction is achieved by using colour segmentation. Secondly, for the combination of information of different uncertain sources, Kalman Filter is proposed. Finally, the information received by the camera which serves for the building of an occupancy grid map corrected by sensors is de facto the representation of environment for the robot.
|
|
|
Moving object tracking
Sehnoutka, Martin ; Horák, Karel (referee) ; Richter, Miloslav (advisor)
This thesis deals with application of computer vision for purposes of object tracking in a video record. In first part of this document, algorithms of computer vision are described theoretically. Next part contains design of map of movement in a scene. All these procedures were used during implementation of program for tracking of moving objects. Discussion of program functionality is in the last chapter.
|
|
|
Evolutionary Design of Filters for Signal Processing
Dobiš, Tomáš ; Hrbáček, Radek (referee) ; Dobai, Roland (advisor)
Kalman filter is used for signal filtering dependent on filter configuration and prediction of values. It's configuration is difficult and requires experiences of mathematician. This thesis deals with implementation of method for signal processing with use of Cartesian genetic programming, which advantage includes the automated configuration of filter. Final method is compared on multiple testing examples with Kalman filter. From results we can infer, that implemented method works comparatively efficient on periodic and exponential signal inputs, and works significantly better on constant signal inputs than Kalman filter.
|
|
|
Network Anomaly Detection
Pšorn, Daniel ; Puš, Viktor (referee) ; Kořenek, Jan (advisor)
This master thesis deals with detecting anomalies methods in network traffic. First of all this thesis analyzes the basic concepts of anomaly detection and already using technology. Next, there are also described in more detail three methods for anomalies search and some types of anomalies. In the second part of this thesis there is described implementation of all three methods and there are presented the results of experimentation using real data.
|
|
|
Multifunction data acquisition, measurement and control device
Trávníček, Ivo ; Vlachý, David (referee) ; Grepl, Robert (advisor)
The thesis deals with and tests the Multifunction data acquisition, measurement and control device. The unit is based on the microcontroller ATmega, which was programmed in the language C. The unit contains functions for the measurement of physical quantify, filtering record, regulation of the dynamic systems and communication with PC. Configuration of the unit is real-time in special software created in the language Matlab or by a terminal. The purpose of the unit is controlling a DC motor by the PID regulator, long-term measurement of temperature or measurement of acceleration by an accelerometer.
|
|
|
Analysis of impact of noise in recordings on the automated detection of hypokinetic dysarthria
Havelková, Nikola ; Galáž, Zoltán (referee) ; Kováč, Daniel (advisor)
This thesis deals with the automated detection of hypokinetic dysarthria by analysing the influence of noise present in recordings. Appropriate single-channel methods, specifically the spectral subtraction and Kalman filter, are selected and implemented in the MATLAB R2022a to enhance speech. These methods are also used for noise-free recordings, to which additive white noise was added. Afterwards, the effectiveness of these methods is objectively evaluated by using signal-to-noise ratio values. After enhancing of speech, interferences are extracted from the recordings. The effect of the presence of noise, as well as its subsequent suppression by individual methods, is then evaluated by statistical analysis, specifically using the Kruskal-Wallis test and the post hoc Dunn’s test. The probability of distributing parameters of clean, noisy and enhanced recordings, for which the effect of noise is significant, according to statistical tests, are plotted using violin and box graphs. Finally, the classification was done by logistic regression with the help of machine learning, where the effect of the presence of noise and subsequent speech enhancement on automated detection of hypokinetic dysarthria was described according to the area values under the ROC curve.
|
guest ::
