Národní úložiště šedé literatury Nalezeno 3 záznamů.  Hledání trvalo 0.00 vteřin. 
Running Motion Analysis
Eliáš, Radoslav ; Kolářová, Jana (oponent) ; Goldmann, Tomáš (vedoucí práce)
The goal of this thesis is to analyze body movement in running gait. The system works with recordings from two cameras, one from the side and one from the back. The problem is solved using a pose estimation algorithm based on the convolutional method. Multiple estimators are compared in this thesis. The final system uses the OpenPose framework and provides a library with calculations for many metrics used to evaluate the running gait. Results are then visualised in a multiplatform desktop application. Experiments were conducted on a private dataset of running recordings.
Model of Cycling Traffic Intensity in Brno
Eliáš, Radoslav ; Burget, Radek (oponent) ; Hynek, Jiří (vedoucí práce)
The Brno Data Department has access to multiple datasets regarding cycling traffic numbers. The goal of the thesis was developing a model integrating these sources for the Transportation Department of the city planning office to gain insights about how the infrastructure is used daily. Each dataset is aggregated to a different basemap with a slightly different street network. This thesis introduces an algorithmic approach to street matching based on similarity, overlap percentage and other parameters. Two algorithms for matching point-based and polyline-based geometries are presented. As well as a model mapping locations among different datasets and a dashboard visualizing values from them side-by-side. The robustness of the algorithms enables usage in any geographical application using spatial data. The dashboard provides useful information about cycling transport for both casual users and professionals designing the infrastructure of Brno.
Running Motion Analysis
Eliáš, Radoslav ; Kolářová, Jana (oponent) ; Goldmann, Tomáš (vedoucí práce)
The goal of this thesis is to analyze body movement in running gait. The system works with recordings from two cameras, one from the side and one from the back. The problem is solved using a pose estimation algorithm based on the convolutional method. Multiple estimators are compared in this thesis. The final system uses the OpenPose framework and provides a library with calculations for many metrics used to evaluate the running gait. Results are then visualised in a multiplatform desktop application. Experiments were conducted on a private dataset of running recordings.

Viz též: podobná jména autorů
4 Eliáš, Radim
2 Eliáš, Richard
Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.