Sciweavers

128 search results - page 14 / 26
» Motion Segmentation from Feature Trajectories with Missing D...
Sort
View
SI3D
2006
ACM
15 years 11 months ago
Human motion estimation from a reduced marker set
Motion capture data from human subjects exhibits considerable redundancy. In this paper, we propose novel methods for exploiting this redundancy. In particular, we set out to find...
Guodong Liu, Jingdan Zhang, Wei Wang 0010, Leonard...
CVPR
2010
IEEE
16 years 1 months ago
Chaotic Invariants of Lagrangian Particle Trajectories for Anomaly Detection in Crowded Scenes
A novel method for crowd flow modeling and anomaly detection is proposed for both coherent and incoherent scenes. The novelty is revealed in three aspects. First, it is a unique ut...
Shandong Wu, Brian E. Moore, and Mubarak Shah
JMM2
2006
110views more  JMM2 2006»
15 years 5 months ago
Two-Stage PCA Extracts Spatiotemporal Features for Gait Recognition
We propose a technique for gait recognition from motion capture data based on two successive stages of principal component analysis (PCA) on kinematic data. The first stage of PCA ...
Sandhitsu R. Das, Robert C. Wilson, Maciej T. Laza...
CGF
2008
148views more  CGF 2008»
15 years 5 months ago
Automatic Registration for Articulated Shapes
We present an unsupervised algorithm for aligning a pair of shapes in the presence of significant articulated motion and missing data, while assuming no knowledge of a template, u...
Will Chang, Matthias Zwicker
BMVC
2002
15 years 8 months ago
Low Density Feature Point Matching for Articulated Pose Identification
We describe a general algorithm for identifying an arbitrary pose of an articulated subject with low density feature points. The algorithm aims to establish a one-to-one correspon...
Horst Holstein, Baihua Li