About the Plane Fit
The plane fit parameter is used to determine the 'goodness of fit'
of the particular
plane
under consideration. The plane fit is the square root of the first
eigenvalue (i.e., the standard deviation of the residuals for the
fitted points). The plane fit value represents the variance of the
residuals of the fitted plane. This value is used to determine if
the fitted plane is a good fit where planes with values above the
plane fit value would not be classified. The plane fit value is linear
and the default value for this parameter is appropriate for most cases.
Effects of Increasing or Decreasing the Plane Fit
- Increasing Value: Increasing the plane fit value will result
in more points being classified. Higher plane fit values will
classify more points because the points under consideration are
allowed more variation in respect to the orthogonal distance to
the fitted plane resulting in more vegetation patches being classified.
In addition, objects of interest (e.g., buildings with rough roofs)
with rough surfaces might be classified by increasing the plane
fit value.
- Decreasing Value: Decreasing the plane fit value will result
in less points being classified. Lower plane fit values will classify
less points because the points under consideration are allowed
less variation in respect to the orthogonal distance to the fitted
plane resulting in less vegetation patches being classified. In
addition, fewer objects of interest (e.g., buildings with rough
surfaces) with rough surfaces are classified by decreasing the
plane fit value.
