single-jc.php

JACIII Vol.14 No.6 pp. 638-644
doi: 10.20965/jaciii.2010.p0638
(2010)

Paper:

Posture Estimation of Human Body Based on Connection Relations of 3D Ellipsoidal Models

Mitsuhiro Hayase* and Susumu Shimada**

*Graduate School of Computer and Cognitive Science, Chukyo University, 101 Tokodachi, Kaizu-cho, Toyota, Aichi 470-0393, Japan

**School of Information Science and Technology, Chukyo University, 101 Tokodachi, Kaizu-cho, Toyota, Aichi 470-0393, Japan

Received:
January 23, 2010
Accepted:
July 15, 2010
Published:
September 20, 2010
Keywords:
posture estimation, 2D appearance models, 3D models, connection relations, model-based vision
Abstract

We propose new method of estimating human body posture from connection relations of threedimensional (3D) ellipsoidal models. First, 3D ellipsoidal models with enlargement and reduction transformations are constructed. Next, two-dimensional (2D) appearance models are constructed from 2D projected images of the 3D model. The appearance models are related to each other by employing a network data structure. They are then matched with an image of the body made from actual thermal images. By using the connection relations between the head and body, the head and the body can be recognized. Differences between individuals can be simply treated by using different sized parts. Moreover, this method can be applied also to recognition of arms and legs.

Cite this article as:
Mitsuhiro Hayase and Susumu Shimada, “Posture Estimation of Human Body Based on Connection Relations of 3D Ellipsoidal Models,” J. Adv. Comput. Intell. Intell. Inform., Vol.14, No.6, pp. 638-644, 2010.
Data files:
References
  1. [1] Ministry of Internal Affairs and Communications – Statistics Bureau, Director-General for Policy Planning (Statistical Standards) & Statistical Research and Training Institute,
    http://www.stat.go.jp/english/index.htm.
  2. [2] H. Jiang, Z. N. Li, and M. S. Drew, “Human Posture Recognition with Convex Programming,” Proc. IEEE Conf. on Multimedia and Expo (ICME 2005), 2005.
  3. [3] A. Fathi and G. Mori, “Human Pose Estimation using Motion Exemplars,” IEEE Int. Conf. on Computer Vision (ICCV 2007), 2007.
  4. [4] Y. Wang and G. Mori, “Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation,” European Conf. on Computer Vision (ECCV 2008), 2008.
  5. [5] A. Sakaguchi, Y. Yano, and S. Okuma, “A Study on Markerless Posture Estimation based on Constructing Detected Body Parts,” Joint 4th Int. Conf. on Soft Computing and Intelligent Systems and 9th Int. Symposium on Advanced Intelligent Systems (SCIS & ISIS 2008), pp. 1681-1686, 2008.
  6. [6] S. Shimada, “Diagrammatic Reasoning with Time-Space Model,” IPSJ SIG Notes. ICS, Vol.95, No.48, pp. 45-50, 1995 (in Japanese).
  7. [7] M. Hayase and S. Shimada, “A Posture Estimation of a Human Body by 2-D projected images of a 3-D Model,” Proc. of the IEICE General Conf., Vol.2007, No.2, p. 187, 2007 (in Japanese).
  8. [8] M. Hayase and S. Shimada, “Posture Estimation of a Human Body from Thermal Images of 2D Appearnce Models of 3D Ellipsoidal Model,” J. of Advanced Computational Intelligence and Intelligent Informatics (JACIII), Vol.13, No.3, pp. 172-177, 2009.
  9. [9] T. Kanade, “Computer Vision and AI : Their Relation and Non-Relation,” J. of Japanese Soc. for Artifical Intelligence, Vol.18, No.3, pp. 328-335, 2003 (in Japanese).

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Sep. 19, 2021