A Bayesian Framework for Sparse Representation-Based 3-D Human Pose Estimation

@article{BabagholamiMohamadabadi2014ABF,
  title={A Bayesian Framework for Sparse Representation-Based 3-D Human Pose Estimation},
  author={Behnam Babagholami-Mohamadabadi and Amin Jourabloo and Ali Zarghami and Shohreh Kasaei},
  journal={IEEE Signal Processing Letters},
  year={2014},
  volume={21},
  pages={297-300}
}
A Bayesian framework for 3-D human pose estimation from monocular images based on sparse representation (SR) is introduced. Our probabilistic approach aims at simultaneously learning two overcomplete dictionaries (one for the visual input space and the other for the pose space) with a shared sparse representation. Existing SR-based pose estimation approaches only offer a point estimation of the dictionary and the sparse codes. Therefore, they might be unreliable when the number of training… Expand
A New Sparse Representation Algorithm for 3D Human Pose Estimation
TLDR
A new framework based on sparse representation for 3D human pose estimation which uses both the labeled and unlabeled data is proposed which can exploit the information of the pose space to improve the pose estimation accuracy. Expand
Human Pose Estimation from Monocular Images: A Comprehensive Survey
TLDR
A comprehensive survey of human pose estimation from monocular images is carried out including milestone works and recent advancements and splits the problem into several modules: feature extraction and description, human body models, and modeling methods. Expand
A CSF-Based CNR Approach for Small-Size Image Sequences
TLDR
A column space fitting (CSF) based consensus of non-rigid (CNR) reconstruction approach is proposed to deal with the 3D structure estimation problem for small-size image sequences. Expand
Integral Knowledge Distillation for Multi-Person Pose Estimation
TLDR
A novel compact and lightweight framework to train more efficient estimators using knowledge distillation, which can achieve competitive performance with the most state-of-the-art methods and consume only $\text{35}\%$ model parameters and GFLOPs of the authors' baseline (SimpleBaseline-ResNet-50) on the COCO dataset. Expand
VST3D-Net:Video-Based Spatio-Temporal Network for 3D Shape Reconstruction from a Video
TLDR
The proposed Video-based Spatio-Temporal 3D Network (VST3D-Net), which is a novel learning approach of viewpoint-invariant 3D shape reconstruction from monocular video, can outperform the state-of the art approaches both in accuracy and efficiency. Expand
Temporally stable monocular 3D human pose estimation for tunable body language generation
Realistic body language generation for social robots and animated characters is an extremely challenging problem that has only been attacked recently. The source of the difficulty is both findingExpand
Covariance-Free Sparse Bayesian Learning
TLDR
A new SBL inference algorithm that avoids explicit computation of the covariance matrix, thereby saving significant time and space and enabling SBL to tractably tackle high-dimensional signal recovery problems, such as deconvolution of calcium imaging data and multi-contrast reconstruction of magnetic resonance images. Expand
Learning Multimodal Structures in Computer Vision
TLDR
The goal is to extract a discriminative representation of the multimodal data that leads to easily finding its essential characteristics in the subsequent analysis step, e.g., regression and classification, in a decomposition coefficient vector that is favorable towards the maximal discriminatory power. Expand
Reconstructing Three-Dimensional Human Poses: A Combined Approach of Iterative Calculation on Skeleton Model and Conformal Geometric Algebra
TLDR
A new approach for 3D human pose construction based on the iterative calculation of a skeleton model and conformal geometric algebra and high-performance conformalgeometric algebra in relation to rotation transformations in order to improve the adjustment of the postures of the human limbs. Expand
Extremity Extraction Based on Curvature with Skeleton Filtering and the Ability of Recognizing of Hidden Features Human Pose Representation
TLDR
Experimental results demonstrate the privileged performance of the proposed algorithm to extract the extremities and so the human posture against the best reported works. Expand
...
1
2
...

References

SHOWING 1-10 OF 12 REFERENCES
Robust 3D human pose estimation via dual dictionaries learning
  • Hao Ji, Fei Su
  • Computer Science
  • Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)
  • 2012
TLDR
A new dual dictionaries learning (DDL) method is proposed for robust 3D human pose estimation that aims at simultaneously constructing two overcomplete dictionaries with a shared sparse representation (SSR) regularization with respect to every data sample. Expand
Estimating Human Pose from Occluded Images
TLDR
Experimental results on synthetic and real data sets bear out the theory that with sparse representation 3D human pose can be robustly estimated when humans are partially or heavily occluded in the scenes. Expand
3D human pose recovery from image by efficient visual feature selection
TLDR
A new examplar-based approach to recover 3D human poses from monocular images by using sparse representation to retrieve the pose candidates, where the measured visual feature is expressed as a sparse linear combination of the examplars in the database. Expand
Recovering 3D human pose from monocular images
  • A. Agarwal, B. Triggs
  • Mathematics, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2006
TLDR
A learning-based method for recovering 3D human body pose from single images and monocular image sequences, embedded in a novel regressive tracking framework, using dynamics from the previous state estimate together with a learned regression value to disambiguate the pose. Expand
3D Human Pose Reconstruction Using Millions of Exemplars
  • Hao Jiang
  • Computer Science
  • 2010 20th International Conference on Pattern Recognition
  • 2010
TLDR
This work proposes a novel exemplar based method to estimate 3D human poses from single images by using only the joint correspondences, which implicitly squares the size of the exemplar database and enables us to reconstruct unconstrained poses efficiently. Expand
Human Pose Tracking in Monocular Sequence Using Multilevel Structured Models
  • M. Lee, R. Nevatia
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2009
TLDR
Experimental results on several realistic indoor video sequences show that the proposed three-stage approach with multi-level state representation that enables a hierarchical estimation of 3D body poses is able to track multiple persons during complex movement including sitting and turning movements with self and inter-occlusion. Expand
Monocular 3D pose estimation and tracking by detection
TLDR
A three-stage process building on a number of recent advances to recover 3D human pose from monocular image sequences and demonstrates state-of-the-art performance on the HumanEva II benchmark, and shows the applicability of the approach to articulated 3D tracking in realistic street conditions. Expand
Inferring 3D body pose from silhouettes using activity manifold learning
  • A. Elgammal, Chan-Su Lee
  • Computer Science
  • Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
TLDR
This work aims to infer 3D body pose directly from human silhouettes by explicitly learning view-based representations of activity manifolds as well as learning mapping functions between such central representations and both the visual input space and the 3DBody pose space. Expand
Twin Gaussian Processes for Structured Prediction
We describe twin Gaussian processes (TGP), a generic structured prediction method that uses Gaussian process (GP) priors on both covariates and responses, both multivariate, and estimates outputs byExpand
Fast sparse representation with prototypes
  • Jia-Bin Huang, Ming-Hsuan Yang
  • Mathematics, Computer Science
  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
TLDR
This work proposes an algorithm that exploits the fact that signals in most problems can be modeled by a small set of prototypes and shows that the l\-norm minimization problem can be reduced to a much smaller problem, thereby gaining significant speed-ups with much less memory requirements. Expand
...
1
2
...