|
|
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.
|
|
|
Simulation of electroporation process in stent oclussion therapy
Hemzal, Martin ; Cipín, Radoslav (referee) ; Novotná, Veronika (advisor)
This masteral thesis describes phenomenon of electroporation and it’s use to deal with occluded self-expandable metalic stent. Thesis briefly summarizes theory of electroporation, currently used medical treatments of occluded stents. The next part of the thesis is dedicated to current state of mathematical simulations of electroporation. The core of the thesis are simulations of electroporation effects on tissue of occluded metal stents.
|
|
|
Thrombi detection in main brain arteries in CT image data
Líška, Martin ; Nemček, Jakub (referee) ; Chmelík, Jiří (advisor)
The master’s thesis deals with automatic preprocessing, segmentation and consecutive analysis of volume data of anonymized patient CTA acquisitions with an indication of stroke. Preprocessing of volume data is an essential step for proper vascular tree segmentation and analysis. The region growing method was used to segment the vascular tree of the brain. After extracting the vascular tree, the labeling of individual branches was applied in the algorithm and the appropriate features were extracted. The analysis examined the features of vessel lengths, their diameter and local brightness profiles, which are important indicators of possible stenosis or occlusion of the main vessels of the brain. The output of the algorithm are various modalities of diagnostic, assisted visualizations of the segmented vascular tree. The segmentation and analysis algorithm of cerebrovascular system was created in the MATLAB programming environment.
|
|
|
Influence of temporomandibular dysfunction on head position
Veselá, Nikola ; Čakrt, Ondřej (advisor) ; Kučerová, Klára (referee)
Dysfunction in the temporomandibular joint appears to varying extents, depending on the chosen criteria, in at least half of the world's population. Altered afferentation from the orofacial area (for example due to dysfunction in the temporomandibular joint) can, according to research, have an effect on the position of the head, cervical spine and postural stability. However, the issue of the influence of temporomandibular dysfunction on head position or postural stability is still not sufficiently explored and conflicting opinions appear in the literature. The aim of this thesis is to reveal the correlation between dysfunction in the temporomandibular region and changes in postural stability, head position and subjective visual vertical. In the theoretical part, the current knowledge of the influence of the temporomandibular region on the surrounding structures and body posture will be presented using research. The aim of the practical part will be to investigate to what extent and in what time modulated afferentation from the orofacial area will affect the posture, head position and possibly also the subjective perception of the vertical. Measurements will take place on a stabilometric platform, using the Bucket method and further using QR codes and a computer program. The results will be...
|
|
|
Study of the effect of tissue conductivity on electroporation
Hemzal, M. ; Aubrecht, V.
This paper deals with two different dynamic models of electrical conductivity and a static model for electroporation. Those models were used to calculate electric field distribution in the tissue, the current and the volume of the tissue that will be subjected to electroporation. The results are than compared to the experimental model. Improved model can be used to better predict ablation zones.
|
|
|
Thrombi detection in main brain arteries in CT image data
Líška, Martin ; Nemček, Jakub (referee) ; Chmelík, Jiří (advisor)
The master’s thesis deals with automatic preprocessing, segmentation and consecutive analysis of volume data of anonymized patient CTA acquisitions with an indication of stroke. Preprocessing of volume data is an essential step for proper vascular tree segmentation and analysis. The region growing method was used to segment the vascular tree of the brain. After extracting the vascular tree, the labeling of individual branches was applied in the algorithm and the appropriate features were extracted. The analysis examined the features of vessel lengths, their diameter and local brightness profiles, which are important indicators of possible stenosis or occlusion of the main vessels of the brain. The output of the algorithm are various modalities of diagnostic, assisted visualizations of the segmented vascular tree. The segmentation and analysis algorithm of cerebrovascular system was created in the MATLAB programming environment.
|
|
|
The effect of exercise with blood flow restriction on the development of muscle strength - meta analysis
Uher, Dominik ; Baláš, Jiří (advisor) ; Vomáčková, Helena (referee)
Title: The effect of exercise with blood flow restriction on the development of muscle strength Objectives: The aim of this work was to assess the magnitude of the effect of exercise with blood flow restriction on the development of muscle strength on the basis of a systematic research and to determine the main factors that moderate this increase. Methods: Primary sources were searched in the scientific databases Academic Search Ultimate, Web of Science and Taylor and Francis. Individual training interventions were found in the included studies. Based on the training interventions, possible moderating factors of the magnitude of the effect on the development of muscular strength of the upper or lower limbs were defined. From the results of the studies, the effect size values of Cohen's d and Hedge's g were calculated. The influence of concrete parameters of application of the vascular occlusion and blood flow restriction exercise on the magnitude of the effect was evaluated on the basis of correlation analysis. Results: A total of 27 studies were included in this diploma thesis, in which 39 different trainings using blood flow restriction exercises were found and included. Based on the correlation analysis, no direct relationship was found between the exercise parameters and the magnitude of the...
|
|
|
Visual constrains in badminton serve
Ďurčo, Dominik ; Carboch, Jan (advisor) ; Petružela, Jan (referee)
Title: Visual constrains in badminton serve Objectives: Main goal of this bachleor's theses was to examine whether and to what extent does the visual feedback influences short badminton serve, whether the accuracy and success rate will change. Methods: Data were obtained experimentally, later evaluated by the method of indirect observation - video analysis. Ten players were tested. Each player was subjected to four tests. The first serve test was with occlusion, the player's vision was occluded at the moment of contact of the shuttlecock with the racket using the occlusion glasses that the players wore. The second and third tests were performed under normal conditions. The last test was the same as the first test with occlusion. Results: By comparing the average distances of the shuttlecock impact points between the short backhand serve tests in badminton, a statistically significant effect of visual feedback p = 0.04 on the accuracy of short serve was demonstrated. In the occlusion tests, the average distance between the line and the point of impact of the shuttlecock was 32.5 ± 23.9 cm and under normal conditions 27.7 ± 20.8 cm. The difference between number of fouls under two conditions was only 1.5%, with more foul attempts being recorded in the tests under normal conditions. Keywords:...
|
|
|
Simulation of electroporation process in stent oclussion therapy
Hemzal, Martin ; Cipín, Radoslav (referee) ; Novotná, Veronika (advisor)
This masteral thesis describes phenomenon of electroporation and it’s use to deal with occluded self-expandable metalic stent. Thesis briefly summarizes theory of electroporation, currently used medical treatments of occluded stents. The next part of the thesis is dedicated to current state of mathematical simulations of electroporation. The core of the thesis are simulations of electroporation effects on tissue of occluded metal stents.
|
|
|
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.
|
guest ::
