Human Motion – Understanding, Modeling, Capture and Animation: Second Workshop, Human Motion 2007, Rio de Janeiro, Brazil, October 20, 2007. Proceedings

Edilson de Aguiar, Christian Theobalt, Carsten Stoll, Hans-Peter Seidel (auth.), Ahmed Elgammal, Bodo Rosenhahn, Reinhard Klette (eds.)3540757023, 9783540757023

This LNCS volume contains the papers presented at the second Workshop on Human Motion Understanding, Modeling, Capture and Animation, which took place on October 20th, 2007, accompanying the 11th IEEE International C- ference on Computer Vision in Rio de Janeiro, Brazil. In total, 38 papers were submitted to this workshop,of which 22 papers were accepted. We were careful to ensure a high standard of quality when selecting the papers. All submissions were double-blind reviewed by at least two experts. Out of the 22 accepted papers, 10 were selected for oral presentation and 12 for posters. We thank the authors of the accepted papers for taking the reviewers’ comments into account in the ?nal published versions of their papers. We thank all of the authors who submitted their work, and we trust that the reviewers’ comments have been of value for their research activities. The accepted papers re?ect the state of the art in the ?eld and cover various topicsrelatedto humanmotiontrackingandanalysis.Thepapersinthisvolume have been classi?ed into three categories based on the topics they cover: human motion capture and pose estimation, body and limb tracking and segmentation, and activity recognition.

---

Table of contents :
Front Matter….Pages –
Marker-Less 3D Feature Tracking for Mesh-Based Human Motion Capture….Pages 1-15
Boosted Multiple Deformable Trees for Parsing Human Poses….Pages 16-27
Gradient-Enhanced Particle Filter for Vision-Based Motion Capture….Pages 28-41
Multi-activity Tracking in LLE Body Pose Space….Pages 42-57
Exploiting Spatio-temporal Constraints for Robust 2D Pose Tracking….Pages 58-73
Efficient Upper Body Pose Estimation from a Single Image or a Sequence….Pages 74-87
Real-Time and Markerless 3D Human Motion Capture Using Multiple Views….Pages 88-103
Modeling Human Locomotion with Topologically Constrained Latent Variable Models….Pages 104-118
Silhouette Based Generic Model Adaptation for Marker-Less Motion Capturing….Pages 119-135
3D Hand Tracking in a Stochastic Approximation Setting….Pages 136-151
Nonparametric Density Estimation with Adaptive, Anisotropic Kernels for Human Motion Tracking….Pages 152-165
Multi Person Tracking Within Crowded Scenes….Pages 166-179
Joint Appearance and Deformable Shape for Nonparametric Segmentation….Pages 180-195
Robust Spectral 3D-Bodypart Segmentation Along Time….Pages 196-211
Articulated Object Registration Using Simulated Physical Force/Moment for 3D Human Motion Tracking….Pages 212-224
An Ease-of-Use Stereo-Based Particle Filter for Tracking Under Occlusion….Pages 225-239
Semi-Latent Dirichlet Allocation: A Hierarchical Model for Human Action Recognition….Pages 240-254
Recognizing Activities with Multiple Cues….Pages 255-270
Human Action Recognition Using Distribution of Oriented Rectangular Patches….Pages 271-284
Human Motion Recognition Using Isomap and Dynamic Time Warping….Pages 285-298
Behavior Histograms for Action Recognition and Human Detection….Pages 299-312
Learning Actions Using Robust String Kernels….Pages 313-327
Back Matter….Pages –