Rotation and scale invariant posture recognition using Microsoft Kinect skeletal tracking feature
conference contribution
posted on 2012-12-01, 00:00authored bySamiul Monir, Sabirat Rubya, Hasan Ferdous
Human posture identification for motion controlling applications is becoming more of a challenge. We present a posture classification system using skeletal-tracking feature of Microsoft Kinect sensor. Posture recovery is carried out by detecting the human body joints, its position, and orientation at the same time. Angular representation of the skeleton data makes the system very robust and avoids problems related to human body occlusions and motion ambiguities. The implemented system is tested on a class of relatively common postures comprising hundreds of human pose instances by different people, where our classifier shows an average accuracy of 94.9%, 96.7% and 96.9% for linear, exponential and priority based matching systems respectively.
History
Pagination
404-409
Location
Kochi, India
Start date
2012-11-27
End date
2012-11-29
ISSN
2164-7143
eISSN
2164-7151
ISBN-13
9781467351188
Language
eng
Publication classification
E1.1 Full written paper - refereed
Copyright notice
2012, IEEE
Title of proceedings
ISDA 2012 : Proceedings of the 12th International Conference on Intelligent Systems Design and Applications
Event
ISDA - Intelligent Systems Design and Applications. International Conference (12th : 2012 : Kochi, India)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)