Real-time estimation of human body postures using Kalman filter

Kazuhiko Takahashi, Tatsumi Sakaguchi, Jun Ohya

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

10 Citations (Scopus)

Abstract

This paper presents a hybrid estimation method of human body postures from CCD camera images. In the hybrid estimation method, the feature points of the human body (top of the head, tips of the hands, and feet, and elbow joints) are obtained from the results of heuristic contour analyses of human silhouettes or those of a time subtraction image depending on the reliability of the silhouette information. A dynamic compensation is then carried out by tracking all feature points using the AR model in order to obtain their optimal position and to overcome self-occlusion problems. The AR model's parameters are estimated through on-line processing by the Kalman filter. The proposed method is implemented on a personal computer and the process runs in real-time. Experimental results show high estimation accuracy and the feasibility of the proposed method.

Original languageEnglish
Title of host publicationRobot and Human Communication - Proceedings of the IEEE International Workshop
Pages189-194
Number of pages6
Publication statusPublished - 1999
Externally publishedYes
Event8th IEEE International Workshop on Robot and Human Communication RO-MAN '99 - Pisa
Duration: 1999 Sep 271999 Sep 29

Other

Other8th IEEE International Workshop on Robot and Human Communication RO-MAN '99
CityPisa
Period99/9/2799/9/29

    Fingerprint

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software

Cite this

Takahashi, K., Sakaguchi, T., & Ohya, J. (1999). Real-time estimation of human body postures using Kalman filter. In Robot and Human Communication - Proceedings of the IEEE International Workshop (pp. 189-194)