|
|
Tracking of Moving Objects in Video
Folenta, Ján ; Bartl, Vojtěch (oponent) ; Herout, Adam (vedoucí práce)
This bachelor thesis deals with the issue of detection, tracking and counting vehicles in different directions in video. To deal with this problem, modern techniques of object detection and tracking using convolutional neural networks are used. The goal of this work is to achieve highest possible accuracy of vehicle counting while maintaining the processing of video recordings in real-time. The problems of the implemented method for detection and tracking are solved by analyzing and working with the trajectories of vehicles. With accuracy of 90,94% and total score of 0,8829, this work participated in AI City Challenge 2020, where it placed 6th.
|
|
|
Extraction of Detailed Information from Palmprint
Folenta, Ján ; Sakin, Martin (oponent) ; Kanich, Ondřej (vedoucí práce)
This master's thesis deals with obtaining information from palmprints. Its main goal is to extract information from the palmprint about the local orientation, frequency and width of the papillary lines, to detect principle lines and triradii and to track main lines, including the determination of the main line index. The result of this work is an application with a~graphical user interface, which, in addition to obtaining information from the palmprint, graphically displays this information, statistically processes it and enables its export. Testing and evaluation took place on a data set provided by the Department of Anthropology, Faculty of Science, Masaryk University in Brno, where detection of triradii achieved a success rate of 84.8 %, main line tracking reached success rate of 85.38 % and main line index determination reached success rate of 78 %.
|
|
|
Extraction of Detailed Information from Palmprint
Folenta, Ján ; Sakin, Martin (oponent) ; Kanich, Ondřej (vedoucí práce)
This master's thesis deals with obtaining information from palmprints. Its main goal is to extract information from the palmprint about the local orientation, frequency and width of the papillary lines, to detect principle lines and triradii and to track main lines, including the determination of the main line index. The result of this work is an application with a~graphical user interface, which, in addition to obtaining information from the palmprint, graphically displays this information, statistically processes it and enables its export. Testing and evaluation took place on a data set provided by the Department of Anthropology, Faculty of Science, Masaryk University in Brno, where detection of triradii achieved a success rate of 84.8 %, main line tracking reached success rate of 85.38 % and main line index determination reached success rate of 78 %.
|
|
|
Tracking of Moving Objects in Video
Folenta, Ján ; Bartl, Vojtěch (oponent) ; Herout, Adam (vedoucí práce)
This bachelor thesis deals with the issue of detection, tracking and counting vehicles in different directions in video. To deal with this problem, modern techniques of object detection and tracking using convolutional neural networks are used. The goal of this work is to achieve highest possible accuracy of vehicle counting while maintaining the processing of video recordings in real-time. The problems of the implemented method for detection and tracking are solved by analyzing and working with the trajectories of vehicles. With accuracy of 90,94% and total score of 0,8829, this work participated in AI City Challenge 2020, where it placed 6th.
|
host ::
RSS.