Code covered by the BSD License
-
costFuncMAD(currentBlk,refBlk...
Computes the Mean Absolute Difference (MAD) for the given two blocks
-
imgPSNR(imgP, imgComp, n)
Computes motion compensated image's PSNR
-
minCost(costs)
Finds the indices of the cell that holds the minimum cost
-
motionComp(imgI, motionVect, ...
Computes motion compensated image using the given motion vectors
-
motionEst4SS(imgP, imgI, mbSi...
Computes motion vectors using Four Step Search method
-
motionEstARPS(imgP, imgI, mbS...
Computes motion vectors using Adaptive Rood Pattern Search method
-
motionEstDS(imgP, imgI, mbSiz...
Computes motion vectors using Diamond Search method
-
motionEstES(imgP, imgI, mbSiz...
Computes motion vectors using exhaustive search method
-
motionEstNTSS(imgP, imgI, mbS...
Computes motion vectors using *NEW* Three Step Search method
-
motionEstSESTSS(imgP, imgI, m...
Computes motion vectors using Simple and Efficient TSS method
-
motionEstTSS(imgP, imgI, mbSi...
Computes motion vectors using Three Step Search method
-
motionEstAnalysis.m
-
View all files
from
Block Matching Algorithms for Motion Estimation
by Aroh Barjatya
Review of various block matching algorithms used for motion estimation in MPEG coding.
|
| costFuncMAD(currentBlk,refBlk, n) |
% Computes the Mean Absolute Difference (MAD) for the given two blocks
% Input
% currentBlk : The block for which we are finding the MAD
% refBlk : the block w.r.t. which the MAD is being computed
% n : the side of the two square blocks
%
% Output
% cost : The MAD for the two blocks
%
% Written by Aroh Barjatya
function cost = costFuncMAD(currentBlk,refBlk, n)
err = 0;
for i = 1:n
for j = 1:n
err = err + abs((currentBlk(i,j) - refBlk(i,j)));
end
end
cost = err / (n*n);
|
|
Contact us at files@mathworks.com