eigenimages: Eigenimage

In emanuelhuber/RGPR: Ground-penetrating radar (GPR) data visualisation, processing and delineation

Eigenimage

Description

Decompose the GPR data (radargram) using singular value decomposition (SVD) and return the reconstructed data for the selected singular values (eigenvalues). This method is sometimes refered to in the litterature as the Karhunen-Loeve (KL) transformation or the eigenimage decomposition.

Usage

## S4 method for signature 'GPR'
eigenimages(x, center = TRUE, scale = FALSE, track = TRUE)

Arguments

x	An object of the class GPR
center	Logical or numeric. If TRUE, centering is done by subtracting the layer means (omitting NA's), and if FALSE, no centering is done. If center is a numeric vector with length equal to the nlayers(x), then each layer of x has the corresponding value from center subtracted from it.
scale	Logical or numeric. If TRUE, scaling is done by dividing the (centered) layers of x by their standard deviations if center is TRUE, and the root mean square otherwise. If scale is FALSE, no scaling is done. If scale is a numeric vector with length equal to nlayers(x), each layer of x is divided by the corresponding value. Scaling is done after centering.

Value

An object of the class GPR.

References

• Textbook: Sacchi (2002) Statistical and Transform Methods in Geophysical Signal Processing

Examples

 
data(frenkeLine00)
x <- frenkeLine00
x1 <- eigenimage(x)
plot(x)
plot(x1[ , , 1])

emanuelhuber/RGPR documentation built on May 13, 2024, 9:31 p.m.