Nonparametric density estimation for human motion tracking
Fragment książki (Rozdział w monografii)
MNiSW
20
Poziom I
| Status: | |
| Autorzy: | Łukasik Edyta, Skublewska-Paszkowska Maria, Charytanowicz Małgorzata |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Arkusze wydawnicze: | 1,2 |
| Język: | angielski |
| Strony: | 81 - 101 |
| Efekt badań statutowych | NIE |
| Materiał konferencyjny: | NIE |
| Publikacja OA: | TAK |
| Licencja: | |
| Sposób udostępnienia: | Witryna wydawcy |
| Wersja tekstu: | Ostateczna wersja opublikowana |
| Czas opublikowania: | W momencie opublikowania |
| Data opublikowania w OA: | 7 grudnia 2020 |
| Abstrakty: | angielski |
| In today’s world, human motion tracking has truly emerged as a vivid research area. This relates to the task of analyzing the movement of a person over time, using the data obtained by a motion capture device. The results obtained via a motion capture system allowclear identification of the degree of training of the subjects studied, their technique and level of movement efficiency. In our study, a motion capture system (Vicon, Oxford Metrics Ltd., UK) was used to register the three-dimensional movement of rowers. The study was performed on the Concept II Indoor Rower ergometer. The sample population was a group of ten non-rowers and aprofessional rower. The main aim of the study was to construct a mathematical model for analysing the speed and accuracy of the rowing technique. The method presented here is based on the theory of kernel density estimation. The approach is universal, and it can be successfully applied for many tasks in human motion tracking where arbitrary assumptions concerning the form of regression function are not recommended. |
