Conditional Random People: Tracking Humans with CRFs and Grid Filters
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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 2005
- Accession Number
- ADA466726
Entities
People
- David Demirdjian
- Gregory Shakhnarovich
- Leonid Taycher
- Trevor Darrell
Organizations
- Massachusetts Institute of Technology