MDIC '01 Proceedings of the Second International Workshop on Multimedia Databases and Image Communication
Learning silhouette features for control of human motion
ACM Transactions on Graphics (TOG)
Nonlinear manifold learning for dynamic shape and dynamic appearance
Computer Vision and Image Understanding
A 3D Shape Descriptor for Human Pose Recovery
AMDO '08 Proceedings of the 5th international conference on Articulated Motion and Deformable Objects
Real-Time Body Pose Recognition Using 2D or 3D Haarlets
International Journal of Computer Vision
VideoMocap: modeling physically realistic human motion from monocular video sequences
ACM SIGGRAPH 2010 papers
View independent human body pose estimation from a single perspective image
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
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
Homeomorphic manifold analysis: learning decomposable generative models for human motion analysis
WDV'05/WDV'06/ICCV'05/ECCV'06 Proceedings of the 2005/2006 international conference on Dynamical vision
Estimating 3d human body pose from stereo image sequences
GW'05 Proceedings of the 6th international conference on Gesture in Human-Computer Interaction and Simulation
Reconstruction of 3d human body pose for gait recognition
ICB'06 Proceedings of the 2006 international conference on Advances in Biometrics
Reconstruction of 3d human body pose based on top-down learning
ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part I
Reconstructing 3d human pose from 2d image landmarks
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
| Hi-index | 0.00 |
We present an approach for recovering articulated body pose from single monocular images using the Specialized Mappings Architecture (SMA), a nonlinear supervised learning architecture. SMAs consist of several specialized forward (input to output space) mapping functions and a feedback matching function, estimated automatically from data. Each of these forward functions maps certain areas (possibly disconnected) of the input space onto the output space. A probabilistic model for the architecture is first formalized along with a mechanism for learning its parameters. The learning problem is approached using a maximum likelihood estimation framework; we present expectation maximization (EM) algorithms for several different choices of the likelihood function. The performance of the presented solutions under these different likelihood functions is compared in the task of estimating human body posture from low-level visual features obtained from a single image, showing promising results.