Model-Based Estimation of 3D Human Motion

By Ioannis A. Kakadiaris, Dimitris N. Metaxas. 2000

201 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “[141] Key Segment Mining BoW Lowlv Dict X X X Kakadiaris and Metaxas [142] Physics Based Model Conc Lowlv Hand X Nie et al.”
Pedestrian detection and tracking with night vision (2005, methodology): “[17], [18], spatial–temporal silhouette analysis of human parts with a three-dimensional (3-D) model [20], periodicity and self-similarity analysis [9], annealed particle filtering for articulated pedestrian [11], and probabilistic modeling of pose and motion, as well as maximum a posteriori detecti”
A Physics-Based Model Prior for Object-Oriented MDPs (2014, methodology): “It arises in vision for model-based tracking (Kakadiaris & Metaxas, 2000; Duff et al., 2010), and in graphics for data-driven tuning of simulation parameters e.g. for cloth simulation (Bhat et al., 2003), rigid-body motion (Bhat et al., 2002), and even humanoid motion (Liu et al., 2005).”
Recovering 3D human body configurations using shape contexts (2006, unknown): “Kakadiaris and Metaxas [9] use multiple cameras and match occluding contours with projections from a deformable 3D model.”
Multi-view 3D Human Pose Estimation in Complex Environment (2011, methodology): “given a reasonably accurate 3D human model and an initial 3D pose, predict the pose at the next time step using a particular dynamical and observation model (Balan and Black 2006; Brubaker et al. 2010; Deutscher and Reid 2005; Drummond and Cipolla 2001; Fossati et al. 2009; Gavrila and Davis 1996; H”
Estimating Human Body Configurations Using Shape Context Matching (2002, unknown): “Kakadiaris and Metaxas[7] use multiple cameras and match occluding contours with projections from a deformable 3D model.”
Detailed Human Shape and Pose from Images (2007, methodology): “Kakadiaris and Metaxas used generic deformable models to estimate 3D human shape from silhouette contours taken from multiple camera views [11] and tracked these shapes over multiple frames [12].”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, background): “Note that, there are other keywords that return relevant publications such as “3D human pose recovery” [5] or “3D human motion tracking” [25].”
Estimating Anthropometry and Pose from a Single Uncalibrated Image (2001, methodology): “Concerning posture estimation and tracking, methods have been presented that use either one [4, 6, 17, 21], or multiple cameras [1, 7, 9, 13, 14, 16 ].”
Vision-based human motion analysis: An overview (2007, methodology): “Image descriptors and matching functions are described in Section 2.2.”