Question

我从两个视频中提取了SIFT功能以进行匹配。我需要将每个第二个视频功能与存储在第一个视频的一系列功能中的功能进行比较。我在设置代码时遇到了问题，因此当我收到通信时，我可以获得存在该功能的帧。我能怎么做？谁能告诉我一个代码示例？

这是我的代码：

obj = VideoReader('video2.avi');
lastFrame = read(obj, inf);
numFrames = obj.NumberOfFrames;

%estrazione frame e sift
for k = 1 : 3 % numFrames / 5
    disp(['Processing frame #', num2str(k)]);
    this_frame = read(obj, k * 5); % leggi solo un fotogramma ogni 5 per velocizzarle la cosa
    this_frame = imresize(this_frame, 0.5); % rimpiccioliamolo per questioni di efficienza!
    I = single(rgb2gray(this_frame)) ;
    [f,d] = vl_sift(I);  % estrazione feature

    features{k} = f;     % salviamo le feautre e i relativi descrittori in delle celle
    descriptors{k} = d;
end
save('feature_input', 'features');
save('descrittori_input', 'descriptors');

%%% un esempio di come ripescare i dati...
pippo = load('feature_input');
newfeat = pippo.features;
pippo = load('descrittori_input');
newdesc = pippo.descriptors;

for k = 1 : 3
    disp(['Le feature del fotogramma', num2str(k), ' sono: ']);
    f = cell2mat( newfeat(k) );
    f(:, 1:10) % ne mostriamo solo un pezzetto... le posizioni delle prime 10 features
end


obj2 = VideoReader('video2u.avi');
lastFrame = read(obj2, inf);
numFrames = obj2.NumberOfFrames;



%estrazione frame e sift video2
for k2 = 1 : 3 % numFrames / 5
    disp(['Processing frame #', num2str(k2)]);
    this_frame2 = read(obj2, k2 * 5); % leggi solo un fotogramma ogni 5 per velocizzarle la cosa
    this_frame2 = imresize(this_frame2, 0.5); % rimpiccioliamolo per questioni di efficienza!
    K = single(rgb2gray(this_frame2)) ;
    [f2,d2] = vl_sift(K);  % estrazione feature

    features2{k2} = f2;     % salviamo le feautre e i relativi descrittori in delle celle
    descriptors2{k2} = d2;
end




save('feature2_input', 'features2');
save('descrittori2_input', 'descriptors2');

%%% un esempio di come ripescare i dati...
pippo2 = load('feature2_input');
newfeat2 = pippo2.features2;
pippo2 = load('descrittori2_input');
newdesc2 = pippo2.descriptors2;

for k2 = 1 : 3
    disp(['Le feature del fotogramma', num2str(k2), ' sono: ']);
    f2 = cell2mat( newfeat2(k2) );
    f2(:, 1:10) % ne mostriamo solo un pezzetto... le posizioni delle prime 10 features


end


[matches, scores] = vl_ubcmatch(d, d2, 1.5) ;

% sift points plot

    subplot(1,2,1);
    imshow(uint8(I));
    hold on;
    plot(f(1,matches(1,:)),f(2,matches(1,:)),'b*');


    subplot(1,2,2);
    imshow(uint8(K));
    hold on;
    plot(f2(1,matches(2,:)),f2(2,matches(2,:)),'r*');


    figure;

     %-------------  

 % RANSAC

X1 = f(1:2,matches(1,:)) ; X1(3,:) = 1 ;
X2 = f2(1:2,matches(2,:)) ; X2(3,:) = 1 ;


numMatches = size(matches,2) ;

for t = 1:100
  % estimate homograpyh
  subset = vl_colsubset(1:numMatches, 4) ;
  A = [] ;
  for i = subset
    A = cat(1, A, kron(X1(:,i)', vl_hat(X2(:,i)))) ;
  end


  [U,S,V] = svd(A) ;


H{t} = reshape(V(:,9),3,3) ;

  % score homography
  X2_ = H{t} * X1 ;
  du = X2_(1,:)./X2_(3,:) - X2(1,:)./X2(3,:) ;
  dv = X2_(2,:)./X2_(3,:) - X2(2,:)./X2(3,:) ;
  ok{t} = (du.*du + dv.*dv) < 6*6 ;
  score(t) = sum(ok{t}) ;
end



[score, best] = max(score) ;
H = H{best};
ok = ok{best};


% sift feature matching 

   dh1 = max(size(K,1)-size(I,1),0) ;
   dh2 = max(size(I,1)-size(K,1),0) ;


subplot(2,1,1) ;
imagesc([padarray(I,dh1,'post') padarray(K,dh2,'post')]) ;
 colormap (gray);
o = size(I,2) ;
line([f(1,matches(1,:));f2(1,matches(2,:))+o], ...
     [f(2,matches(1,:));f2(2,matches(2,:))]) ;


axis image off ;

subplot(2,1,2) ;
imagesc([padarray(I,dh1,'post') padarray(K,dh2,'post')]) ;
 colormap (gray);
o = size(I,2) ;
line([f(1,matches(1,ok));f2(1,matches(2,ok))+o], ...
     [f(2,matches(1,ok));f2(2,matches(2,ok))]) ;
title(sprintf('%d (%.2f%%) inliner matches out of %d', ...
              sum(ok), ...
              100*sum(ok)/numMatches, ...
              numMatches)) ;
axis image off ;

drawnow ;

end

Answer 1

您正在使用[matches, scores] = vl_ubcmatch(d, d2, 1.5) ;进行匹配。 d仅包含最新帧的描述符。你应该做点什么：

for nFrames=1:3
   [matches{nFrames}, scores{nFrames}] = vl_ubcmatch(descriptors{nFrames}, descriptors2{nFrames}, 1.5);
end

从这里开始，您应该可以获得帧之间的匹配。

找到两个视频之间匹配的SIFT功能

1 个答案: