数字图像和视频处理的基础－第4周运动估计matlab练习题

In this problem you will perform block matching motion estimation between two consecutive video frames. Follow the instructions below to complete this problem. (1) Download the two video frames from  frame_1  and  frame_2 . The frames/images are of height 288 and width 352. (2) Load the frame with file name "frame_1.jpg" into a  288×352  MATLAB array using function "imread", and then convert the array type from 8-bit integer to real number using function "double" or "cast" (note that the range of intensity values after conversion is between 0 and 255). Denote by  I1  the converted MATLAB array. Repeat this step for the frame with file name "frame_2.jpg" and denote the resulting MATLAB array by  I2 . In this problem,  I2  corresponds to the current frame, and  I1  corresponds to the previous frame (i.e., the reference frame). (3) Consider the  32×32  target block in  I2  that has its upper-left corner at  (65,81)  and lower-right corner at  (96,112) . Note this is MATLAB coordinate convention, i.e., the first number between the parenthesis is the row index extending from  1  to  288  and the second number is the column index extending from  1  to  352 . This target block is therefore a  32×32  sub-array of  I2 . (4) Denote the target block by  Btarget . Motion estimation via block matching searches for the  32×32  sub-array of  I1  that is "most similar" to  Btarget . Recall in the video lectures we have introduced various forms of matching criteria, e.g., correlation coefficient, mean-squared-error (MSE), mean-absolute-error (MAE), etc. In this problem, we use MAE as the matching criterion. Given two blocks  B1  and  B2  both of size  M×N , the MAE is defined as  MAE(B1,B2)=1M×N∑Mi=1∑Nj=1|B1(i,j)−B2(i,j)| . To find the block in  I1  that is most similar to  Btarget  in the MAE sense, you will need to scan through all the  32×32  blocks in  I1 , compute the MAE between each of these blocks and  Btarget , and find the one that yields the smallest value of MAE. Note in practice motion search is only performed over a certain region of the reference frame, but for the sake of simplicity, we perform motion search over the entire reference frame  I1  in this problem. When you find the matched block in  I1 , enter the following information: (1) the coordinate of the upper-left corner of the matched block in MATLAB convention. This requires two integer numbers; (2) the corresponding MAE value, which is a floating-point number. Enter the last number to two decimal points. As an example for format of answer, suppose the matched block has upper-left corner located at  (1,1)

, and the corresponding MAE is 10.12, then you should enter 1 1 10.12 (the three numbers are separated by spaces)

clear;
clear all;
clear clc;

I1 = double(imread('frame1.jpg'));
I2 = double(imread('frame2.jpg'));
[height,width] = size(I1);

Btarget = I2(65:96,81:112);

MAE = 1000000;
x = 0;
y = 0;
for i=1:height-31
    for j=1:width-31
        diff = Btarget - I1(i:i+31,j:j+31);
        tsum = sum(sum(abs(diff)));
        if(tsum < MAE)
            x = i;
            y = j;
            MAE = tsum;
        end
    end
end
MAE = MAE/(32*32);