Introduction

This paper addresses the problem of recovering 3D human pose from a single monocular image, using a discriminative bag-of-words approach. In previous work, the visual words are learned by unsupervised clustering algorithms. They capture the most common patterns and are good features for coarse-grain recognition tasks like object classification. But for those tasks which deal with subtle differences such as pose estimation, such representation may lack the needed discriminative power. In this paper, we propose to jointly learn the visual words and the pose regressors in a supervised manner. More specifically, we learn an individual distance metric for each visual word to optimize the pose estimation performance. The learned metrics rescale the visual words to suppress unimportant dimensions such as those corresponding to background. Another contribution is that we design an Appearance and Position Context (APC) local descriptor that achieves both selectivity and invariance while requiring no background subtraction. We test our approach on both a quasi-synthetic dataset and a real dataset (HumanEva) to verify its effectiveness. Our approach also achieves fast computational speed thanks to the integral histograms used in APC descriptor extraction and fast inference of pose regressors.

Experimental Results

We constructed a quasi-synthetic human database with large variations, by animating computer graphic human avatars using real motion data and placing the synthetic images on real backgrounds.
Sample videos: without background, with background We also test our algorithm on the HumanEva dataset. Here are some sample videos together with the estimated pose represented as the outline of a cylinder-based human model superimposed onto the original images. We visualize the estimated pose on cameras: C1, C2, and C3, and the ground truth on camera C1 only.
1. Walking (video).
2. Boxing (video).
3. Jogging (video).