pcorr3d: Phase Correlation of Images

Description

Input two images (matrices) and perform phase correlation by multiplication in the frequency domain. Return the maximum phase correlation value, its associated shift vector (x and y), and the phase correlation matrix.

Usage

pcorr3d(img1,img2)

Arguments

img1

Image (matrix) 1

img2

Image (matrix) 2 with same dimensions of img1

Value

List whose values correspond to:

max.shifts

Vector of length two whose values are the x and y indices associated with the highest phase correlation value. Note these values are shifted according to the zero frequency which changes depending on the dimensions of img1 and/or img2.

max.corr

Highest normalized phase correlation value in the correlation matrix

corr.mat

Normalized phase correlation matrix

Details

Phase correlation calculated in the frequency domain as a multiplication. The dimensions of img1 and img2 must match. If pcorr3d is used to apply a match filter, it is logical to input the image to be searched over as img1 and the match filter as img2. Similarly, if tracking relative motion between images, it is logical to input the first image at time t=n as img1 and the second image at time t=n+1 as img2, otherwise motions will backwards.

Examples

Run this code

# NOT RUN {
#################
### Example 1 ###
#################
## track movement between images

## load in the images
data(tux1,tux2)

## now find the shift vector by using the phase correlation function 
shifts <- pcorr3d(tux1,tux2)

## ---- Plotting Example 1  ----- ##

split.screen(c(1,2))
screen(1)
image(1:nrow(tux1),1:ncol(tux1),tux1,col=gray.colors(200))

## define an example arrow starting and end points based on the shift found
x0 = nrow(tux1)/2
y0 = ncol(tux1)/2
x1 = x0 + shifts$max.shifts[1]
y1 = y0 + shifts$max.shifts[2]

## add arrows indicating how the image shifted
arrows(x0,y0,x1,y1)

## add a point where the arrow is
points(nrow(tux1)/2+shifts$max.shifts[1],ncol(tux1)/2+shifts$max.shifts[2],pch=21,bg='green')

screen(2)
image(1:nrow(tux2),1:ncol(tux2),tux2,col=gray.colors(200))
points(nrow(tux1)/2+shifts$max.shifts[1],ncol(tux1)/2+shifts$max.shifts[2],pch=21,bg='green')

## close the screen
close.screen(all.screens=TRUE)

# }