Conditional Random People: Tracking Humans with CRFs and Grid Filters

Authors:
Leonid Taycher;David Demirdjian;Trevor Darrell;Gregory Shakhnarovich
Affiliations:
Massachusetts Institute of Technology;Massachusetts Institute of Technology;Massachusetts Institute of Technology;Brown University,Providence
Venue:
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Year:
2006

Citing 0
Cited 12

A survey of advances in vision-based human motion capture and analysis

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Vision-based human motion analysis: An overview

Computer Vision and Image Understanding
Fast nonparametric belief propagation for real-time stereo articulated body tracking

Computer Vision and Image Understanding
3D voxel based online human pose estimation via robust and efficient hashing

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
A Study on Smoothing for Particle-Filtered 3D Human Body Tracking

International Journal of Computer Vision
Occlusion modeling by tracking multiple objects

Proceedings of the 29th DAGM conference on Pattern recognition
Kinematic self retargeting: A framework for human pose estimation

Computer Vision and Image Understanding
Graphical framework for action recognition using temporally dense STIPs

WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Discriminative semi-supervised learning of dynamical systems for motion estimation

Pattern Recognition
A large margin framework for single camera offline tracking with hybrid cues

Computer Vision and Image Understanding
Coupled Action Recognition and Pose Estimation from Multiple Views

International Journal of Computer Vision
Sketched symbol recognition using Latent-Dynamic Conditional Random Fields and distance-based clustering

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a state-space tracking approach based on a Conditional Random Field (CRF) model, where the observation potentials are learned from data. We find functions that embed both state and observation into a space where similarity corresponds to L1 distance, and define an observation potential based on distance in this space. This potential is extremely fast to compute and in conjunction with a grid-filtering framework can be used to reduce a continuous state estimation problem to a discrete one. We show how a state temporal prior in the grid-filter can be computed in a manner similar to a sparse HMM, resulting in real-time system performance. The resulting system is used for human pose tracking in video sequences.