Advancing Motion Words for Human Motion Classification – Bc. David Procházka
Bc. David Procházka
Master's thesis
Advancing Motion Words for Human Motion Classification
Advancing Motion Words for Human Motion Classification
Abstract:
Práce rozvíjí techniku na reprezentaci krátkých pohybů pomocí tzv. pohybových výrazů, angl. motion words. Prezentujeme novou kvantizační techniku kompozitních pohybových výrazů (composite motion words) založenou na rozdělení kostry na nepřekrývající se části. Problémy neefektivního indexování sekvencí pohybových výrazů a opakování akcí jsou řešeny využitím editační vzdálenosti a její adaptace. Tato …moreAbstract:
The thesis improves the technique for representing short motions called motion words. We present a new quantization technique called composite motion word by dividing the skeleton into non-overlapping body parts. The problems of inefficient indexing of motion word sequences and action repetitions are addressed by employing edit distance and its adaptation. These advancements achieve a classification …more
Language used: English
Date on which the thesis was submitted / produced: 16. 5. 2023
Identifier:
https://is.muni.cz/th/sojsh/
Thesis defence
- Date of defence: 19. 6. 2023
- Supervisor: doc. RNDr. Vlastislav Dohnal, Ph.D.
- Reader: doc. RNDr. Jan Sedmidubský, Ph.D.
Citation record
Full text of thesis
Contents of on-line thesis archive
Published in Theses:- světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatikyMasaryk University
Faculty of InformaticsMaster programme / field:
Computer systems, communication and security / Software systems
Theses on a related topic
-
Movement-Based Sentiment Classification in Human Interactions
Maroš Dubíny -
Triplet-loss Learning for Classification of 3D Human Motion Data
Barbora Kompišová -
Action Recognition, Annotation, and Searching in Motion Data
Petr Eliáš -
Efficient Implementation of Dynamic Time Warping for Motion Data
Matěj Hamala -
Folk-Dance Learning Using Human Motion Data Analysis
Iris Kico -
Triplet-loss Learning for Classification of 3D Human Motion Data
Barbora Kompišová -
Similarity-based Matching of Fast and Slow Motions using Motion Words
Matěj Bagar -
Efficient Implementation of Dynamic Time Warping for Motion Data
Matěj Hamala