性能 – 有效计算光流参数 – MATLAB

我正在实现光流上 Horn & Schunck paper的偏导数方程.然而,即使对于相对较小的图像(320×568),也需要令人沮丧的长时间(~30-40秒)才能完成.我假设这是由于320 x 568 = 181760循环迭代,但我无法找到一种更有效的方法来做到这一点(缺少MEX文件).

有没有办法将其转化为更高效的MATLAB操作(也许是卷积)？我可以弄清楚如何做它作为它的卷积而不是Ix和Iy.我也考虑过矩阵移位,但这只适用于它,据我所知.

有没有其他人遇到这个问题并找到了解决方案？

我的代码如下：

function [Ix, Iy, It] = getFlowParams(img1, img2)

% Make sure image dimensions match up
assert(size(img1, 1) == size(img2, 1) && size(img1, 2) == size(img2, 2), ...
    'Images must be the same size');
assert(size(img1, 3) == 1, 'Images must be grayscale');

% Dimensions of original image
[rows, cols] = size(img1);
Ix = zeros(numel(img1), 1);
Iy = zeros(numel(img1), 1);
It = zeros(numel(img1), 1);

% Pad images to handle edge cases
img1 = padarray(img1, [1,1], 'post');
img2 = padarray(img2, [1,1], 'post');

% Concatenate i-th image with i-th + 1 image
imgs = cat(3, img1, img2);

% Calculate energy for each pixel
for i = 1 : rows
    for j = 1 : cols
        cube = imgs(i:i+1, j:j+1, :);
        Ix(sub2ind([rows, cols], i, j)) = mean(mean(cube(:, 2, :) - cube(:, 1, :)));
        Iy(sub2ind([rows, cols], i, j)) = mean(mean(cube(2, :, :) - cube(1, :, :)));
        It(sub2ind([rows, cols], i, j)) = mean(mean(cube(:, :, 2) - cube(:, :, 1)));
    end
end

2D convolution是这里的方式,正如在问题中预测的那样取代那些重均值/平均值的计算.此外,这些迭代差异可以由 MATLAB’s diff取代.因此,结合所有这些,矢量化实施将是 –

%// Pad images to handle edge cases
img1 = padarray(img1, [1,1], 'post');
img2 = padarray(img2, [1,1], 'post');

%// Store size parameters for later usage
[m,n] = size(img1);

%// Differentiation along dim-2 on input imgs for Ix calculations
df1 = diff(img1,[],2)
df2 = diff(img2,[],2)

%// 2D Convolution to simulate average calculations & reshape to col vector
Ixvals = (conv2(df1,ones(2,1),'same') + conv2(df2,ones(2,1),'same'))./4;
Ixout = reshape(Ixvals(1:m-1,:),[],1);

%// Differentiation along dim-1 on input imgs for Iy calculations
df1 = diff(img1,[],1)
df2 = diff(img2,[],1)

%// 2D Convolution to simulate average calculations & reshape to col vector
Iyvals = (conv2(df1,ones(1,2),'same') + conv2(df2,ones(1,2),'same'))./4
Iyout = reshape(Iyvals(:,1:n-1),[],1);

%// It just needs elementwise diffentiation between input imgs.
%// 2D convolution to simulate mean calculations & reshape to col vector
Itvals = conv2(img2-img1,ones(2,2),'same')./4
Itout = reshape(Itvals(1:m-1,1:n-1),[],1)

这种矢量化实现的好处是：

>内存效率：不会在第三维上连接会导致内存开销.再次,性能方面,它将是一个好处,因为我们不需要索引到这样的重型阵列.
>循环代码中的迭代差异被diff的差异所取代,所以这应该是另一个改进.>那些昂贵的平均计算被非常快速的卷积计算所取代,这应该是主要的改进部分.