3D HUMAN POSTURE ESTIMATION BASED ON LINEAR REGRESSION OF HOG FEATURES FROM MONOCULAR IMAGES

Katsunori Onishi (Japan), Tetsuya Takiguchi (Japan) and Yasuo Ariki (Japan)

Received July 9, 2009

Abstract

In this paper, we propose a method to estimate the 3D human posture from monocular image without using the markers. A 3D human body is expressed by a multi-joint model, and a set of the joint angles describes a posture. The proposed method estimates the posture using Histograms of Oriented Gradients (HOG) feature vectors that can express the shape of the object in the input image obtained from monocular camera. In addition, the feature dimension of the background region is reduced for reliability by principal component analysis (PCA) computed at every block of HOG. The joint angles in Human multi-joint model are estimated by linear regression analysis applied to its feature vector extracted from the input image. As a result of comparison experiment with the Shape Contexts features, the RMS error was reduced by about 5.35 degrees.

Keywords and phrases: posture estimation, histograms of oriented gradients, principal analysis, linear regression.