Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images

We address the problem of estimating human body pose from a single image with cluttered background. We train multiple local linear regressors for estimating the 3D pose from a feature vector of gradient orientation histograms. Each linear regressor is capable of selecting relevant components of the feature vector depending on pose by training it on a pose cluster which is a subset of the training samples with similar pose. For discriminating the pose clusters, we use kernel Support Vector Machines (SVM) with pose-dependent feature selection. We achieve feature selection for kernel SVMs by estimating scale parameters of RBF kernel through minimization of the radius/margin bound, which is an upper bound of the expected generalization error, with efficient gradient descent. Human detection is also possible with these SVMs. Quantitative experiments show the effectiveness of pose-dependent feature selection to both human detection and pose estimation.

[1]  David F. Shanno,et al.  Remark on “Algorithm 500: Minimization of Unconstrained Multivariate Functions [E4]” , 1980, TOMS.

[2]  Alex Pentland,et al.  Pfinder: real-time tracking of the human body , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[3]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[4]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[5]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[6]  Alexander J. Smola,et al.  Advances in Large Margin Classifiers , 2000 .

[7]  Tomaso A. Poggio,et al.  Image representations for object detection using kernel classifiers , 2000 .

[8]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[9]  S. Sathiya Keerthi,et al.  Efficient tuning of SVM hyperparameters using radius/margin bound and iterative algorithms , 2002, IEEE Trans. Neural Networks.

[10]  Trevor Darrell,et al.  Fast pose estimation with parameter-sensitive hashing , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[11]  Paul A. Viola,et al.  Detecting Pedestrians Using Patterns of Motion and Appearance , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[12]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[13]  Luc Van Gool,et al.  A Hierarchical System for Recognition, Tracking and Pose Estimation , 2004, MLMI.

[14]  Dimitris N. Metaxas,et al.  Learning to Reconstruct 3 D Human Motion from Bayesian Mixtures of Experts . A Probabilistic Discriminative Approach , 2004 .

[15]  Rin-ichiro Taniguchi,et al.  Real-time human motion sensing based on vision-based inverse kinematics for interactive applications , 2004, ICPR 2004.

[16]  Sidharth Bhatia,et al.  Tracking loose-limbed people , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[17]  Cordelia Schmid,et al.  Human Detection Based on a Probabilistic Assembly of Robust Part Detectors , 2004, ECCV.

[18]  Charles A. Micchelli,et al.  On Learning Vector-Valued Functions , 2005, Neural Computation.

[19]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[20]  Ankur Agarwal,et al.  Monocular Human Motion Capture with a Mixture of Regressors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[21]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[22]  Michael J. Black,et al.  Predicting 3D People from 2D Pictures , 2006, AMDO.

[23]  Mei-Chen Yeh,et al.  Fast Human Detection Using a Cascade of Histograms of Oriented Gradients , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[24]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion , 2006 .

[25]  Björn Stenger,et al.  Multivariate Relevance Vector Machines for Tracking , 2006, ECCV.

[26]  Ankur Agarwal,et al.  Recovering 3D human pose from monocular images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Ankur Agarwal,et al.  A Local Basis Representation for Estimating Human Pose from Cluttered Images , 2006, ACCV.

[28]  Ronald Poppe,et al.  Evaluating Example-based Pose Estimation: Experiments on the HumanEva Sets , 2007 .

[29]  Stefano Soatto,et al.  Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Björn Stenger,et al.  A Video Motion Capture System for Interactive Games , 2007, MVA.

[31]  E. Rückert.  Detecting Pedestrians by Learning Shapelet Features , 2007 .

[32]  Andrei Popescu-Belis,et al.  Machine Learning for Multimodal Interaction , 4th International Workshop, MLMI 2007, Brno, Czech Republic, June 28-30, 2007, Revised Selected Papers , 2008, MLMI.