Latent structured models for human pose estimation
- 1 November 2011
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2220-2227
- https://doi.org/10.1109/iccv.2011.6126500
Abstract
We present an approach for automatic 3D human pose reconstruction from monocular images, based on a discriminative formulation with latent segmentation inputs. We advanced the field of structured prediction and human pose reconstruction on several fronts. First, by working with a pool of figure-ground segment hypotheses, the prediction problem is formulated in terms of combined learning and inference over segment hypotheses and 3D human articular configurations. Beside constructing tractable formulations for the combined segment selection and pose estimation problem, we propose new augmented kernels that can better encode complex dependencies between output variables. Furthermore, we provide primal linear re-formulations based on Fourier kernel approximations, in order to scale-up the non-linear latent structured prediction methodology. The proposed models are shown to be competitive in the HumanEva benchmark and are also illustrated in a clip collected from a Hollywood movie, where the model can infer human poses from monocular images captured in complex environments.Keywords
This publication has 13 references indexed in Scilit:
- Object recognition as ranking holistic figure-ground hypothesesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Efficient additive kernels via explicit feature mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Structural SVM for visual localization and continuous state estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Pose search: Retrieving people using their posePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- People-tracking-by-detection and people-detection-by-trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- BM³E : Discriminative Density Propagation for Visual TrackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- A general regression technique for learning transductionsPublished by Association for Computing Machinery (ACM) ,2005
- Priors for people tracking from small training setsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Generative modeling for continuous non-linearly embedded visual inferencePublished by Association for Computing Machinery (ACM) ,2004