Kinect based body posture detection and recognition system

Pramod Kumar Pisharady, Martin Saerbeck

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

A multi-class human posture detection and recognition algorithm using Kinect based geometric features is presented. The three dimensional skeletal data from the Kinect is converted to a set of angular features. The postures are classified using a support vector machines classifier with polynomial kernel. Detection of posture is done by thresholding the posture probability. The algorithm provided a recognition accuracy of 95.78% when tested using a 10 class dataset containing 6000 posture samples. The precision and recall rates of the detection system are 100% and 98.54% respectively.

Original languageEnglish (US)
Title of host publicationInternational Conference on Graphic and Image Processing, ICGIP 2012
DOIs
StatePublished - Jul 19 2013
Event4th International Conference on Graphic and Image Processing, ICGIP 2012 - Singapore, Singapore
Duration: Oct 6 2012Oct 7 2012

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8768
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

Other4th International Conference on Graphic and Image Processing, ICGIP 2012
CountrySingapore
CitySingapore
Period10/6/1210/7/12

Keywords

  • Angular features
  • Depth camera
  • Human-computer interaction
  • Natural interaction
  • Posture detection
  • Posture recognition

Fingerprint Dive into the research topics of 'Kinect based body posture detection and recognition system'. Together they form a unique fingerprint.

Cite this