Learning Appearance Manifolds from Video

Rahimi, Asgar Bradaran; Darrell, Trevor; Recht, Ben

doi:10.1109/cvpr.2005.204

Cited by 58 publications

(40 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To learn pose models a key problem concerns the highly nonlinear space of human poses. Accordingly, methods for nonlinear dimensionality reduction have been popular [21,[31][32][33][34].…”

Section: Related Workmentioning

confidence: 99%

Temporal motion models for monocular and multiview 3D human body tracking

Urtasun

Fleet

Fua

2006

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…To learn pose models a key problem concerns the highly nonlinear space of human poses. Accordingly, methods for nonlinear dimensionality reduction have been popular [21,[31][32][33][34].…”

Section: Related Workmentioning

confidence: 99%

Temporal motion models for monocular and multiview 3D human body tracking

Urtasun

Fleet

Fua

2006

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…To cope with the high dimensionality of kinematic models and the relative sparsity of available training data, a major theme of recent research on people tracking has been dimensionality reduction (Elgammal and Lee 2004;Rahimi et al 2005;Sminchisescu and Jepson 2004;Urtasun et al 2005Urtasun et al , 2006. It is thought that low-dimensional models are less likely to over-fit the training data and will therefore generalize better.…”

Section: Related Workmentioning

confidence: 99%

Physics-Based Person Tracking Using the Anthropomorphic Walker

2009

View full text Add to dashboard Cite

We introduce a physics-based model for 3D person tracking. Based on a biomechanical characterization of lower-body dynamics, the model captures important physical properties of bipedal locomotion such as balance and ground contact. The model generalizes naturally to variations in style due to changes in speed, step-length, and mass, and avoids common problems (such as footskate) that arise with existing trackers. The dynamics comprise a two degreeof-freedom representation of human locomotion with inelastic ground contact. A stochastic controller generates impulsive forces during the toe-off stage of walking, and springlike forces between the legs. A higher-dimensional kinematic body model is conditioned on the underlying dynamics. The combined model is used to track walking people in video, including examples with turning, occlusion, and varying gait. We also report quantitative monocular and binocular tracking results with the HumanEva dataset.

show abstract

“…A major theme of recent tracking methods is dimensionality reduction for learning low-dimensional models and dynamical systems from data [8,23,27,30,31]. In this paper, we employ a hand-designed low-dimensional representation based on models from the biomechanics literature.…”

Section: Related Workmentioning

confidence: 99%

Physics-Based Person Tracking Using Simplified Lower-Body Dynamics

Brubaker

Fleet

Hertzmann

2007

2007 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

We introduce a physics-based model for 3D person tracking. Based on a biomechanical characterization of lower-body dynamics, the model captures important physical properties of bipedal locomotion such as balance and ground contact, generalizes naturally to variations in style due to changes in speed, step-length, and mass, and avoids common problems such as footskate that arise with existing trackers. The model dynamics comprises a two degree-offreedom representation of human locomotion with inelastic ground contact. A stochastic controller generates impulsive forces during the toe-off stage of walking and spring-like forces between the legs. A higher-dimensional kinematic observation model is then conditioned on the underlying dynamics. We use the model for tracking walking people from video, including examples with turning, occlusion, and varying gait.

show abstract

Learning Appearance Manifolds from Video

Cited by 58 publications

References 8 publications

Temporal motion models for monocular and multiview 3D human body tracking

Temporal motion models for monocular and multiview 3D human body tracking

Physics-Based Person Tracking Using the Anthropomorphic Walker

Physics-Based Person Tracking Using Simplified Lower-Body Dynamics

Contact Info

Product

Resources

About