Learning effective human pose estimation from inaccurate annotation
- 1 June 2011
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1465-1472
- https://doi.org/10.1109/cvpr.2011.5995318
Abstract
The task of 2-D articulated human pose estimation in natural images is extremely challenging due to the high level of variation in human appearance. These variations arise from different clothing, anatomy, imaging conditions and the large number of poses it is possible for a human body to take. Recent work has shown state-of-the-art results by partitioning the pose space and using strong nonlinear classifiers such that the pose dependence and multi-modal nature of body part appearance can be captured. We propose to extend these methods to handle much larger quantities of training data, an order of magnitude larger than current datasets, and show how to utilize Amazon Mechanical Turk and a latent annotation update scheme to achieve high quality annotations at low cost. We demonstrate a significant increase in pose estimation accuracy, while simultaneously reducing computational expense by a factor of 10, and contribute a dataset of 10,000 highly articulated poses.Keywords
This publication has 16 references indexed in Scilit:
- Clustered Pose and Nonlinear Appearance Models for Human Pose EstimationPublished by British Machine Vision Association and Society for Pattern Recognition ,2010
- Combining discriminative appearance and segmentation cues for articulated human pose estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A discriminatively trained, multiscale, deformable part modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Progressive search space reduction for human pose estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Utility data annotation with Amazon Mechanical TurkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007
- Training Deformable Models for LocalizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Mixtures of trees for object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Strike a Pose: Tracking People by Finding Stylized PosesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Efficient matching of pictorial structuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002