Enhanced Mixtures of Part Model for Human Pose Estimation

TL;DR

This paper introduces an enhanced mixture of parts model for human pose estimation that incorporates additional input cues like human silhouettes and gradient features, improving 2D detection and enabling 3D pose prediction.

Contribution

It extends the mixture of parts model by integrating silhouette and gradient cues, addressing double counting issues and facilitating 3D pose estimation from 2D detections.

Findings

Improved 2D body part detection on HumanEva dataset.

Successful 3D pose estimation from 2D detections using Gaussian process regression.

Framework adaptable to various input features.

Abstract

Mixture of parts model has been successfully applied to 2D human pose estimation problem either as explicitly trained body part model or as latent variables for the whole human body model. Mixture of parts model usually utilize tree structure for representing relations between body parts. Tree structures facilitate training and referencing of the model but could not deal with double counting problems, which hinder its applications in 3D pose estimation. While most of work targeted to solve these problems tend to modify the tree models or the optimization target. We incorporate other cues from input features. For example, in surveillance environments, human silhouettes can be extracted relative easily although not flawlessly. In this condition, we can combine extracted human blobs with histogram of gradient feature, which is commonly used in mixture of parts model for training body part templates. The method can be easily extend to other candidate features under our generalized framework. We show 2D body part detection results on a public available dataset: HumanEva dataset. Furthermore, a 2D to 3D pose estimator is trained with Gaussian process regression model and 2D body part detections from the proposed method is fed to the estimator, thus 3D poses are predictable given new 2D body part detections. We also show results of 3D pose estimation on HumanEva dataset.