Estimating Human Body Pose from a Single Image via the Specialized Mappings Architecture

Date
2000-06-10
DOI
Authors
Rosales, Romer
Sclaroff, Stan
Version
OA Version
Citation
Rosales, Romer; Sclaroff, Stan. "Estimating Human Body Pose from a Single Image via the Specialized Mappings Architecture", Technical Report BUCS-2000-015, Computer Science Department, Boston University, June 10, 2000. [Available from: http://hdl.handle.net/2144/1809]
Abstract
A non-linear supervised learning architecture, the Specialized Mapping Architecture (SMA) and its application to articulated body pose reconstruction from single monocular images is described. The architecture is formed by a number of specialized mapping functions, each of them with the purpose of mapping certain portions (connected or not) of the input space, and a feedback matching process. A probabilistic model for the architecture is described along with a mechanism for learning its parameters. The learning problem is approached using a maximum likelihood estimation framework; we present Expectation Maximization (EM) algorithms for two different instances of the likelihood probability. Performance is characterized by estimating human body postures from low level visual features, showing promising results.
Description
License