警告：将非浮点数据转换为单个

Question

我一直在研究特征提取和对极几何。但是，我经常遇到以下错误：

Warning: Converting non-floating point data to single. In pdist2 (line 219) In extractFeaturesU (line 93)

返回警告消息的代码行是：

[distance, position] = sort(pdist2(double(repmat(featuresA, size(xPoints, 1))), featuresB), 2, 'ascend');

下面显示了包含上述行的代码部分。

%% extract features
corresponding = [];
rightBound = size(sharpImageB, 2);
xPoints = 3 : 3 : rightBound - 3;
for index = 1 : size(realWantedPoints, 2) 
    %extract features from wanted points
    disp('extracting features from wanted points...');   
    if strcmp(desc, 'hog')
        [featuresA, pointsA] = extractHOGFeatures(sharpImageA, realWantedPoints(:, index)', ...
        'CellSize', [8 8], 'BlockSize', [2 2], 'NumBins', 9, 'UseSignedOrientation', true);
    elseif strcmp(desc, 'block')
        [featuresA, pointsA] = extractFeatures(sharpImageA, realWantedPoints(:, index)', ...
        'Method', 'Block', 'BlockSize', 21, 'Upright', true);
    elseif strcmp(desc, 'surf')
        [featuresA, pointsA] = extractFeatures(sharpImageA, realWantedPoints(:, index)', ...
        'Method', 'SURF', 'SURFSize', 64, 'Upright', true);
    end

    % generate epipolar line points
    liner = star([1 0 0]) * [realWantedPoints(:, index); 1];
    yPoints = -(liner(3) + (liner(1) * xPoints)) / liner(2);
    matrixB = [xPoints', yPoints'];

    % extract features from epipolar line points
    disp('extracting features from epipolar line points...');   
    if strcmp('hog', desc)
        [featuresB, pointsB] = extractHOGFeatures(sharpImageB, matrixB, ...
        'CellSize', [8 8], 'BlockSize', [2 2], 'NumBins', 9, 'UseSignedOrientation', true);
    elseif strcmp('block', desc)
        [featuresB, pointsB] = extractFeatures(sharpImageB, matrixB, ...
        'Method', 'Block', 'BlockSize', 21, 'Upright', true);
    elseif strcmp('surf', desc)
        [featuresB, pointsB] = extractFeatures(greyB, matrixB, ...
        'Method', 'SURF', 'SURFSize', 64, 'Upright', true);
    end

    % calculate similarity
    [distance, position] = sort(pdist2(double(repmat(featuresA, size(xPoints, 1))), featuresB), 2, 'ascend');
    corresponding = [corresponding; pointsB(position(1), :)];
end

xB = corresponding(:, 1);
yB = corresponding(:, 2);

Answer 1

我可以通过对两个变量调用 pdist2 来生成该错误：一个是 double 类型，另一个是 single 类型。例如

x = ones(5,1,'single');
y = ones(5,1,'double');
pdist2(x,y);

我猜你的 featuresB 变量是单精度浮点数，因此与你给 pdist2 的第一个参数的类型不匹配（它是双精度的，因为你明确地转换了它）。

警告：将非浮点数据转换为单个

Warning: Converting non-floating point data to single

matlab

feature-extraction

computer-vision