In this paper we present a simple 3D gesture recognizer based on trajectory matching, showing its good performances in classification and retrieval of command gestures based on single hand trajectories. We demonstrate that further simplifications in porting the classic "1 dollar" algorithm approach from the 2D to the 3D gesture recognition and retrieval problems can result in very high classification accuracy and retrieval scores even on datasets with a large number of different gestures executed by different users. Furthermore, recognition can be good even with heavily subsampled path traces and with incomplete gestures.

A 3 Cent Recognizer: Simple and effective retrieval and classification of mid-air gestures from single 3D traces

CARCANGIU, ALESSANDRO;SPANO, LUCIO DAVIDE;
2017-01-01

Abstract

In this paper we present a simple 3D gesture recognizer based on trajectory matching, showing its good performances in classification and retrieval of command gestures based on single hand trajectories. We demonstrate that further simplifications in porting the classic "1 dollar" algorithm approach from the 2D to the 3D gesture recognition and retrieval problems can result in very high classification accuracy and retrieval scores even on datasets with a large number of different gestures executed by different users. Furthermore, recognition can be good even with heavily subsampled path traces and with incomplete gestures.
2017
978-3-03868-048-2
File in questo prodotto:
File Dimensione Formato  
STAG_2017_paper_5.pdf

Solo gestori archivio

Tipologia: versione pre-print
Dimensione 717.97 kB
Formato Adobe PDF
717.97 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/225696
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? ND
social impact