A Non-parametric Bayesian Network Prior of Human Pose

Having a sensible prior of human pose is a vital ingredient for many computer vision applications, including tracking and pose estimation. While the application of global non-parametric approaches and parametric models has led to some success, finding the right balance in terms of flexibility and tractability, as well as estimating model parameters from data has turned out to be challenging. In this work, we introduce a sparse Bayesian network model of human pose that is non-parametric with respect to the estimation of both its graph structure and its local distributions. We describe an efficient sampling scheme for our model and show its tractability for the computation of exact log-likelihoods. We empirically validate our approach on the Human 3.6M dataset and demonstrate superior performance to global models and parametric networks. We further illustrate our model's ability to represent and compose poses not present in the training set (compositionality) and describe a speed-accuracy trade-off that allows real-time scoring of poses.

[1]  Neil D. Lawrence,et al.  Gaussian Process Latent Variable Models for Human Pose Estimation , 2007, MLMI.

[2]  Michael Isard,et al.  Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief Propagation , 2011, International Journal of Computer Vision.

[3]  Marco Grzegorczyk,et al.  Nonparametric Bayesian Networks , 2011 .

[4]  David W. Scott,et al.  Multivariate Density Estimation: Theory, Practice, and Visualization , 1992, Wiley Series in Probability and Statistics.

[5]  Mun Wai Lee,et al.  Human Upper Body Pose Estimation in Static Images , 2004, ECCV.

[6]  Cristian Sminchisescu,et al.  Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  David J. Fleet,et al.  3D People Tracking with Gaussian Process Dynamical Models , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[8]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[9]  Sanjeev R. Kulkarni,et al.  Universal Estimation of Information Measures for Analog Sources , 2009, Found. Trends Commun. Inf. Theory.

[10]  David J. Fleet,et al.  Dynamical binary latent variable models for 3D human pose tracking , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Jitendra Malik,et al.  Tracking people with twists and exponential maps , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[12]  Larry S. Davis,et al.  Efficient Kernel Density Estimation Using the Fast Gauss Transform with Applications to Color Modeling and Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  M. N. Goria,et al.  A new class of random vector entropy estimators and its applications in testing statistical hypotheses , 2005 .

[14]  D. W. Scott,et al.  Multivariate Density Estimation, Theory, Practice and Visualization , 1992 .

[15]  Miguel Á. Carreira-Perpiñán,et al.  People Tracking with the Laplacian Eigenmaps Latent Variable Model , 2007, NIPS.

[16]  Andrew W. Moore,et al.  Nonparametric Density Estimation: Toward Computational Tractability , 2003, SDM.

[17]  Neil D. Lawrence,et al.  Gaussian Process Latent Variable Models for Visualisation of High Dimensional Data , 2003, NIPS.

[18]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[19]  Daniel P. Huttenlocher,et al.  Beyond trees: common-factor models for 2D human pose recovery , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[20]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[21]  David Barber,et al.  Bayesian reasoning and machine learning , 2012 .

[22]  Bodo Rosenhahn,et al.  Nonparametric Density Estimation for Human Pose Tracking , 2006, DAGM-Symposium.

[23]  Fei-Fei Li,et al.  Modeling mutual context of object and human pose in human-object interaction activities , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[24]  Larry S. Davis,et al.  Improved fast gauss transform and efficient kernel density estimation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[25]  Søren Hauberg,et al.  Gaussian-Like Spatial Priors for Articulated Tracking , 2010, ECCV.

[26]  R. K. Shyamasundar,et al.  Introduction to algorithms , 1996 .

[27]  Zoubin Ghahramani,et al.  Sparse Gaussian Processes using Pseudo-inputs , 2005, NIPS.

[28]  Nir Friedman,et al.  Probabilistic Graphical Models , 2009, Data-Driven Computational Neuroscience.