Recognizing body poses using multilinear analysis and semi-supervised learning

Authors:
Bo Peng;Gang Qian;Yunqian Ma
Affiliations:
School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85287-8709, USA;School of Arts, Media and Engineering and School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85287-8709, USA;Honeywell Labs, 1985 Douglas Drive North, Golden Valley, MN 55422, USA
Venue:
Pattern Recognition Letters
Year:
2009

Citing 32
Cited 3

An alternating least squares algorithms for PARAFAC2 and three-way DEDICOM

Computational Statistics & Data Analysis
A survey of computer vision-based human motion capture

Computer Vision and Image Understanding - Modeling people toward vision-based underatanding of a person's shape, appearance, and movement
Virtual Stage: A Location-Based Karaoke System

IEEE MultiMedia
Human Body Model Acquisition and Tracking Using Voxel Data

International Journal of Computer Vision
Multilinear Analysis of Image Ensembles: TensorFaces

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Vision-Based Gesture Recognition: A Review

GW '99 Proceedings of the International Gesture Workshop on Gesture-Based Communication in Human-Computer Interaction
Motion segmentation and pose recognition with motion history gradients

Machine Vision and Applications - Special issue: IEEE WACV
Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selection

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Learning-based hand sign recognition using SHOSLIF-M

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Ghost: A Human Body Part Labeling System Using Silhouettes

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
Gesture Recognition via Pose Classification

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Inference of Human Postures by Classification of 3D Human Body Shape

AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
TensorTextures: multilinear image-based rendering

ACM SIGGRAPH 2004 Papers
Automatic Sign Language Analysis: A Survey and the Future beyond Lexical Meaning

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face transfer with multilinear models

ACM SIGGRAPH 2005 Papers
Clustering on the Unit Hypersphere using von Mises-Fisher Distributions

The Journal of Machine Learning Research
Posture and Gesture Recognition using 3D Body Shapes Decomposition

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
EyesWeb: Toward Gesture and Affect Recognition in Interactive Dance and Music Systems

Computer Music Journal
Dance Posture Recognition Using Wide-baseline Orthogonal Stereo Cameras

FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Inference with the Universum

ICML '06 Proceedings of the 23rd international conference on Machine learning
3D People Tracking with Gaussian Process Dynamical Models

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Applying 3D human model in a posture recognition system

Pattern Recognition Letters
A survey of advances in vision-based human motion capture and analysis

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Tracking human motion and actions for interactive robots

Proceedings of the ACM/IEEE international conference on Human-robot interaction
Learning from Data: Concepts, Theory, and Methods

Learning from Data: Concepts, Theory, and Methods
Robust visual tracking of articulated human motion

Robust visual tracking of articulated human motion
Monocular 3D tracking of articulated human motion in silhouette and pose manifolds

Journal on Image and Video Processing - Anthropocentric Video Analysis: Tools and Applications
Inferring 3D body pose from silhouettes using activity manifold learning

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
3-D hand posture recognition by training contour variation

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion capture

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Viewpoint insensitive posture representation for action recognition

AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects
Monocular tracking of 3d human motion with a coordinated mixture of factor analyzers

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II

Human pose recognition using chamfer distance in reduced background edge for human-robot interaction

ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part II
Multifactor feature extraction for human movement recognition

Computer Vision and Image Understanding
Pattern classification and clustering: A review of partially supervised learning approaches

Pattern Recognition Letters

Quantified Score

Hi-index	0.10

Visualization

Abstract

This paper presents an approach to full-body human pose recognition using features extracted from stereo silhouettes via multilinear analysis in a semi-supervised learning framework. Inputs to the proposed approach are pairs of silhouette images obtained from wide baseline binocular cameras. Through multilinear analysis, low dimensional view-invariant pose coefficient vectors can be extracted from these stereo silhouette pairs. Taking these pose coefficient vectors as features, a recently proposed state-of-the-art semi-supervised learning method, Universum, is adopted for pose recognition. Experiment results obtained using real image data showed the efficacy of the proposed approach.