3D Human Pose Estimation from Monocular Image Sequences
Translated title
Author
Term
4. term
Publication year
2012
Submitted on
2012-05-31
Abstract
Automatic 3D reconstruction of human poses from monocular images is a challenging and popular topic in the computer vision community, which provides a wide range of applications in multiple areas. Solutions for 3D pose estimation involve various learning approaches, such as Support Vector Machines and Gaussian processes, but many encounter difficulties in cluttered scenarios and require additional input data, such as silhouettes, or controlled camera settings. The project outlined consists of a framework that is capable of estimating the 3D pose of a person from monocular image sequences without requiring background information and which is robust to camera variations. The framework models the inherent non-linearity found in human motion as it benefits from flexible learning approaches, including a highly customizable 2D detector and a Gaussian process regressor trained on specific action motions. Results on the HumanEva benchmark show that the system outperforms previous works obtaining a 70% decrease in average estimation error on identical datasets. Detailed settings for experiments, test results and performance measures on 3D pose estimation are provided.
Documents