Neural-network-based real-time human body posture estimation

Kazuhiko Takahashi, Tetsuya Uemura, Jun Ohya

Research output: Chapter in Book/Report/Conference proceedingChapter

3 Citations (Scopus)

Abstract

This paper proposes a real-time human body posture estimation method using ANNs. The network is composed of three ANNs and a decision logic unit. The ANNs' input is the result of a function analysis on a human silhouette's contour extracted from camera images and the ANNs' output indicates the feature points' positions on the contour. The decision logic unit synthesizes each of the ANNs' output vectors and then the 2D coordinates of the human body's feature points are calculated. The proposed method is implemented on a personal computer and runs in real-time (17-20 frames/sec). Experimental results confirm both the feasibility and the effectiveness of the proposed method for estimating human body postures.

Original languageEnglish
Title of host publicationNeural Networks for Signal Processing - Proceedings of the IEEE Workshop
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages477-486
Number of pages10
Volume2
Publication statusPublished - 2000
Externally publishedYes
Event10th IEEE Workshop on Neural Network for Signal Processing (NNSP2000) - Sydney, Australia
Duration: 2000 Dec 112000 Dec 13

Other

Other10th IEEE Workshop on Neural Network for Signal Processing (NNSP2000)
CitySydney, Australia
Period00/12/1100/12/13

Fingerprint

Personal computers
Cameras
Neural networks

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Takahashi, K., Uemura, T., & Ohya, J. (2000). Neural-network-based real-time human body posture estimation. In Neural Networks for Signal Processing - Proceedings of the IEEE Workshop (Vol. 2, pp. 477-486). Piscataway, NJ, United States: IEEE.

Neural-network-based real-time human body posture estimation. / Takahashi, Kazuhiko; Uemura, Tetsuya; Ohya, Jun.

Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. Vol. 2 Piscataway, NJ, United States : IEEE, 2000. p. 477-486.

Research output: Chapter in Book/Report/Conference proceedingChapter

Takahashi, K, Uemura, T & Ohya, J 2000, Neural-network-based real-time human body posture estimation. in Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. vol. 2, IEEE, Piscataway, NJ, United States, pp. 477-486, 10th IEEE Workshop on Neural Network for Signal Processing (NNSP2000), Sydney, Australia, 00/12/11.
Takahashi K, Uemura T, Ohya J. Neural-network-based real-time human body posture estimation. In Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. Vol. 2. Piscataway, NJ, United States: IEEE. 2000. p. 477-486
Takahashi, Kazuhiko ; Uemura, Tetsuya ; Ohya, Jun. / Neural-network-based real-time human body posture estimation. Neural Networks for Signal Processing - Proceedings of the IEEE Workshop. Vol. 2 Piscataway, NJ, United States : IEEE, 2000. pp. 477-486
@inbook{696455c30cbf46418c75afb7b5086a68,
title = "Neural-network-based real-time human body posture estimation",
abstract = "This paper proposes a real-time human body posture estimation method using ANNs. The network is composed of three ANNs and a decision logic unit. The ANNs' input is the result of a function analysis on a human silhouette's contour extracted from camera images and the ANNs' output indicates the feature points' positions on the contour. The decision logic unit synthesizes each of the ANNs' output vectors and then the 2D coordinates of the human body's feature points are calculated. The proposed method is implemented on a personal computer and runs in real-time (17-20 frames/sec). Experimental results confirm both the feasibility and the effectiveness of the proposed method for estimating human body postures.",
author = "Kazuhiko Takahashi and Tetsuya Uemura and Jun Ohya",
year = "2000",
language = "English",
volume = "2",
pages = "477--486",
booktitle = "Neural Networks for Signal Processing - Proceedings of the IEEE Workshop",
publisher = "IEEE",

}

TY - CHAP

T1 - Neural-network-based real-time human body posture estimation

AU - Takahashi, Kazuhiko

AU - Uemura, Tetsuya

AU - Ohya, Jun

PY - 2000

Y1 - 2000

N2 - This paper proposes a real-time human body posture estimation method using ANNs. The network is composed of three ANNs and a decision logic unit. The ANNs' input is the result of a function analysis on a human silhouette's contour extracted from camera images and the ANNs' output indicates the feature points' positions on the contour. The decision logic unit synthesizes each of the ANNs' output vectors and then the 2D coordinates of the human body's feature points are calculated. The proposed method is implemented on a personal computer and runs in real-time (17-20 frames/sec). Experimental results confirm both the feasibility and the effectiveness of the proposed method for estimating human body postures.

AB - This paper proposes a real-time human body posture estimation method using ANNs. The network is composed of three ANNs and a decision logic unit. The ANNs' input is the result of a function analysis on a human silhouette's contour extracted from camera images and the ANNs' output indicates the feature points' positions on the contour. The decision logic unit synthesizes each of the ANNs' output vectors and then the 2D coordinates of the human body's feature points are calculated. The proposed method is implemented on a personal computer and runs in real-time (17-20 frames/sec). Experimental results confirm both the feasibility and the effectiveness of the proposed method for estimating human body postures.

UR - http://www.scopus.com/inward/record.url?scp=0034514025&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034514025&partnerID=8YFLogxK

M3 - Chapter

VL - 2

SP - 477

EP - 486

BT - Neural Networks for Signal Processing - Proceedings of the IEEE Workshop

PB - IEEE

CY - Piscataway, NJ, United States

ER -