Gesture Recognition with 3D Sensors using Hidden Markov Models and Clustering

Autor:	Tobias Steinmetzer, Carlos M. Travieso, Barbara Priwitzer, Ingrid Bonninger, Simon Piatraschk
Rok vydání:	2019
Předmět:	Jaccard index Computer science business.industry Pattern recognition computer.file_format Small set Data conversion Gesture recognition Metric (mathematics) Artificial intelligence Hidden Markov model business Cluster analysis computer Gesture
Zdroj:	IWOBI
Popis:	We propose a method for recognizing dynamic gestures using a 3D sensor. New aspects of the developed system include problem-adapted data conversion and compression as well as automatic detection of different variants of the same gesture via clustering with a suitable metric inspired by Jaccard metric. The combination of Hidden Markov Models and clustering leads to robust detection of different executions based on a small set of training data. We achieved an increase of 5% recognition rate compared to regular Hidden Markov Models. The system has been used for human-machine interaction and might serve as an assistive system in physiotherapy and neurological or orthopedic diagnosis.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::8daa6ee17eba44eabe908d6d9945287a https://doi.org/10.1109/iwobi47054.2019.9114513 Zobrazit plný text záznamu