Hand posture recognition and tracking based on Bag-of-Words for human robot interaction

Author

Chuang, Yuelong ; Chen, Ling ; Zhao, Gangqiang ; Chen, Gencai

Author_Institution

Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China

fYear

2011

fDate

9-13 May 2011

Firstpage

538

Lastpage

543

Abstract

Hand posture is a natural and effective interaction between human and robot. In this paper, we use monocular camera as input device, and an improved Bag-of-Words (BoW) method is proposed to detect and recognize hand posture based on a new descriptor ARPD (Appearance and Relative Position Descriptor) and spectral embedding clustering algorithm. To track hand motion rapidly and accurately, we have designed a new framework based on improved BoW and CAMSHIFT algorithm. The thorough evaluation of our algorithm is presented to show its usefulness.

Keywords

cameras; human-robot interaction; image motion analysis; pattern clustering; pose estimation; robot vision; CAMSHIFT algorithm; appearance and relative position descriptor; bag-of-words; hand motion tracking; hand posture recognition; hand posture tracking; human robot interaction; monocular camera; spectral embedding clustering algorithm; Algorithm design and analysis; Classification algorithms; Clustering algorithms; Histograms; Target tracking; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation (ICRA), 2011 IEEE International Conference on

Conference_Location

Shanghai

ISSN

1050-4729

Print_ISBN

978-1-61284-386-5

Type

conf

DOI

10.1109/ICRA.2011.5979767

Filename

5979767