Body Height Estimation System Based on Binocular Vision

Authors

  • Guangyi Yang School of Electronic Information, Wuhan University, Wuhan, China https://orcid.org/0000-0002-1580-0188
  • Deshi Li School of Electronic Information, Wuhan University, Wuhan, China
  • Guobao Ru School of Electronic Information, Wuhan University, Wuhan, China
  • Jiahua Cao School of Electronic Information, Wuhan University, Wuhan, China
  • Weizheng Jin School of Electronic Information, Wuhan University, Wuhan, China

DOI:

https://doi.org/10.3991/ijoe.v14i04.8400

Keywords:

binocular vision, height measurement, human body, Gaussian mixture model, feature matching

Abstract


In this paper, we propose a novel approach to estimate body height from video sequences based on binocular stereo vision. Firstly, we built a parallel binocular stereo vision device and detected the foreground by using Gaussian mixture model. After shadow elimination, we proposed the contour screening algorithm to obtain the human foreground and the top point in the foreground image. Then, we detected SURF feature points in the binocular images and screened them for 3 times to calculate the disparity of the head. After that, the height of human bodies can be estimated with the calibration parameters of binocular cameras. The experimental results demonstrate that the proposed method has higher measurement accuracy and spends less time which proves the effectiveness of the method.

Downloads

Published

2018-04-26

How to Cite

Yang, G., Li, D., Ru, G., Cao, J., & Jin, W. (2018). Body Height Estimation System Based on Binocular Vision. International Journal of Online and Biomedical Engineering (iJOE), 14(04), pp. 177–192. https://doi.org/10.3991/ijoe.v14i04.8400

Issue

Section

Papers