Question

我在视频旋转的某个地方有一个视频......我不知道角度和移动的方向。我试着用：

function [ output_args ] = aaa( filename )
hVideoSrc = vision.VideoFileReader(filename, 'ImageColorSpace', 'Intensity');

imgA = step(hVideoSrc); % Read first frame into imgA
imgB = step(hVideoSrc); % Read second frame into imgB

figure; imshowpair(imgA, imgB, 'montage');
title(['Frame A', repmat(' ',[1 70]), 'Frame B']);
figure; imshowpair(imgA,imgB,'ColorChannels','red-cyan');
title('Color composite (frame A = red, frame B = cyan)');
ptThresh = 0.1;
pointsA = detectFASTFeatures(imgA, 'MinContrast', ptThresh);
pointsB = detectFASTFeatures(imgB, 'MinContrast', ptThresh);

% Display corners found in images A and B.
figure; imshow(imgA); hold on;
plot(pointsA);
title('Corners in A');

figure; imshow(imgB); hold on;
plot(pointsB);
title('Corners in B');
% Extract FREAK descriptors for the corners
[featuresA, pointsA] = extractFeatures(imgA, pointsA);
[featuresB, pointsB] = extractFeatures(imgB, pointsB);
indexPairs = matchFeatures(featuresA, featuresB);
pointsA = pointsA(indexPairs(:, 1), :);
pointsB = pointsB(indexPairs(:, 2), :);
figure; showMatchedFeatures(imgA, imgB, pointsA, pointsB);
legend('A', 'B');
[tform, pointsBm, pointsAm] = estimateGeometricTransform(...
    pointsB, pointsA, 'affine');
imgBp = imwarp(imgB, tform, 'OutputView', imref2d(size(imgB)));
pointsBmp = transformPointsForward(tform, pointsBm.Location);
figure;
showMatchedFeatures(imgA, imgBp, pointsAm, pointsBmp);
legend('A', 'B');
% Extract scale and rotation part sub-matrix.
H = tform.T;
R = H(1:2,1:2);
% Compute theta from mean of two possible arctangents
theta = mean([atan2(R(2),R(1)) atan2(-R(3),R(4))]);
% Compute scale from mean of two stable mean calculations
scale = mean(R([1 4])/cos(theta));
% Translation remains the same:
translation = H(3, 1:2);
% Reconstitute new s-R-t transform:
HsRt = [[scale*[cos(theta) -sin(theta); sin(theta) cos(theta)]; ...
  translation], [0 0 1]'];
tformsRT = affine2d(HsRt);

imgBold = imwarp(imgB, tform, 'OutputView', imref2d(size(imgB)));
imgBsRt = imwarp(imgB, tformsRT, 'OutputView', imref2d(size(imgB)));

figure(2), clf;
imshowpair(imgBold,imgBsRt,'ColorChannels','red-cyan'), axis image;
title('Color composite of affine and s-R-t transform outputs');
% Reset the video source to the beginning of the file.
reset(hVideoSrc);

hVPlayer = vision.VideoPlayer; % Create video viewer

% Process all frames in the video
movMean = step(hVideoSrc);
imgB = movMean;
imgBp = imgB;
correctedMean = imgBp;
ii = 2;
Hcumulative = eye(3);
while ~isDone(hVideoSrc) && ii < 10
    % Read in new frame
    imgA = imgB; % z^-1
    imgAp = imgBp; % z^-1
    imgB = step(hVideoSrc);
    movMean = movMean + imgB;

    % Estimate transform from frame A to frame B, and fit as an s-R-t
    H = cvexEstStabilizationTform(imgA,imgB);
    HsRt = cvexTformToSRT(H);
    Hcumulative = HsRt * Hcumulative;
    imgBp = imwarp(imgB,affine2d(Hcumulative),'OutputView',imref2d(size(imgB)));

    % Display as color composite with last corrected frame
    step(hVPlayer, imfuse(imgAp,imgBp,'ColorChannels','red-cyan'));
    correctedMean = correctedMean + imgBp;

    ii = ii+1;
end
correctedMean = correctedMean/(ii-2);
movMean = movMean/(ii-2);

% Here you call the release method on the objects to close any open files
% and release memory.
release(hVideoSrc);
release(hVPlayer);
figure; imshowpair(movMean, correctedMean, 'montage');
title(['Raw input mean', repmat(' ',[1 50]), 'Corrected sequence mean']);


end

来自这里的代码 http://www.mathworks.com/help/vision/examples/video-stabilization-using-point-feature-matching.html，但是MatLab无法识别功能 detectFASTFeatures

有人可以帮帮我吗？也许某人有其他功能可以找到这一点。

Answer 1

它似乎只是计算机视觉工具箱中的一个功能，它只附带MATLAB r2014a：

http://www.mathworks.com/help/vision/ref/detectfastfeatures.html

Answer 2

如果你有一个旧版本的MATLAB with Computer Vision System Toolbox，你可以使用vision.CornerDetector对象。

使用MATLAB进行视频稳定

2 个答案: