Improving HessianFactor documentation

release/4.3a0
Richard Roberts 2011-09-04 15:34:28 +00:00
parent 154f730b70
commit 4d24f2af80
1 changed files with 10 additions and 3 deletions

View File

@ -52,9 +52,16 @@ namespace gtsam {
/**
* A general quadratic factor of the form
* f(x) = x'Hx + hx + c
* and stores the matrix H, the vector h, and the constant term c. This factor
* is one of the factors that can be in a GaussianFactorGraph. It may
* be returned from NonlinearFactor::linearize(), but is also
* and stores the matrix H, the vector h, and the constant term c.
*
* When H is positive semidefinite, this factor represents a Gaussian,
* in which case H is the information
* matrix \Lambda, which is the inverse of the covariance matrix \Sigma,
* h is the information vector \eta = \Lambda \mu, and c is the error
* at the mean, when x = \mu.
*
* This factor is one of the factors that can be in a GaussianFactorGraph.
* It may be returned from NonlinearFactor::linearize(), but is also
* used internally to store the Hessian during Cholesky elimination.
*
* This can represent a quadratic factor with characteristics that cannot be