How to create a centerline between lines in image?

Hi

I'm trying to convert the image to binary and create a centerline between the two white lines. Can someone please help me?

clc;
clearvars;
close all;
workspace;
grayImage = imread('road.png');
if ndims(grayImage) == 3
    % It's color.  Take the red channel.
    grayImage = grayImage(:, :, 1);
end
figure
imshow(grayImage, []);
impixelinfo;
mask = logical(grayImage > 140 & grayImage < 255);
mask = bwareafilt(mask, 2); % Make sure we have only two lines.
mask = bwskel(mask);
figure
imshow(mask);
labeledImage = bwlabel(mask);
line1 = ismember(labeledImage, 1);
line2 = ismember(labeledImage, 2);
% Get rows and columns of each line.
[r1, c1] = find(line1);
[r2, c2] = find(line2);
for k = 1 : length(r1)
    distances = ((r1(k) + r2) / 2);
    [minDistance, index] = min(distances);
    % Find the midPoint
    midX = mean([c1(k), c2(index)]);
    midY = mean([r1(k), r2(index)]);
    % Burn into mask
    mask(round(midY), round(midX)) = true;
    % Optionally drop a marker there
    hold on;
    plot(midX, midY, 'g.', 'MarkerSize', 10);
end
% Need to add a small amount of noise to x to make the values unique.
midX = midX + 0.001 * rand(size(midX));
midY = midY + 0.001 * rand(size(midY));
% Interpolate x and y to make sure there are no gaps.
kVec = 1 : length(midX);
kFit = linspace(1, kVec(end), 10000);
xFit = interp1(kVec, midX, kFit, 'linear');
yFit = interp1(kVec, midY, kFit, 'linear');
% Remove duplicate values
xy = unique(round([xFit(:), yFit(:)]), "rows");
% Extract individual x and y.
midX = xy(:, 1);
midY = xy(:, 2);
hold on;
plot(midX, midY, 'g.', 'MarkerSize', 10);

Answer 1

[Image Analyst]

Try fitting each lane stripe to a line, then getting the average column for every row. You need to extend the fitted line outside the image so you can get the middle line when only one lane stripe is in the image, like at the bottom of your image.

% Demo by Image Analyst
clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 22;
markerSize = 40;
%--------------------------------------------------------------------------------------------------------
%    READ IN IMAGE
folder = pwd;
baseFileName = 'road.png';
fullFileName = fullfile(folder, baseFileName);
% Check if file exists.
if ~exist(fullFileName, 'file')
    % The file doesn't exist -- didn't find it there in that folder.
    % Check the entire search path (other folders) for the file by stripping off the folder.
    fullFileNameOnSearchPath = baseFileName; % No path this time.
    if ~exist(fullFileNameOnSearchPath, 'file')
        % Still didn't find it.  Alert user.
        errorMessage = sprintf('Error: %s does not exist in the search path folders.', fullFileName);
        uiwait(warndlg(errorMessage));
        return;
    end
end
rgbImage = imread(fullFileName);
% Get the dimensions of the image.
% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.
[rows, columns, numberOfColorChannels] = size(rgbImage)
if numberOfColorChannels > 1
    % It's not really gray scale like we expected - it's color.
    fprintf('It is not really gray scale like we expected - it is color\n');
    % Extract the blue channel.
    grayImage = rgbImage(:, :, 3);
else
    grayImage = rgbImage;
end
%--------------------------------------------------------------------------------------------------------
% Crop away white surrounding frame and other stuff in the screenshot to get the image alone.
grayImage = grayImage(34:752, 83:1362,:);
% Update the dimensions of the image.
% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.
[rows, columns, numberOfColorChannels] = size(grayImage)
%--------------------------------------------------------------------------------------------------------
% Display the image.
subplot(2, 2, 1);
imshow(grayImage);
impixelinfo;
axis('on', 'image');
title('Original Gray Scale Image', 'FontSize', fontSize, 'Interpreter', 'None');
% Maximize window.
g = gcf;
g.WindowState = 'maximized';
drawnow;
% Display histogram.
subplot(2, 2, [2,4]);
histogram(grayImage);
grid on;
drawnow;
title('Histogram of Image', 'FontSize', fontSize, 'Interpreter', 'None');
%--------------------------------------------------------------------------------------------------------
% Binarize the image to get a mask.
lowThreshold = 192;
highThreshold = intmax(class(grayImage)) - 1;
% https://www.mathworks.com/matlabcentral/fileexchange/29372-thresholding-an-image?s_tid=srchtitle
% threshold(lowThreshold, highThreshold, grayImage);
mask = grayImage >= lowThreshold & grayImage <= highThreshold;
% Put red threshold line on histogram so they know where it was thresholded at.
xline(lowThreshold, 'Color', 'r', 'LineWidth', 2)
% Take only the two largest blobs.
mask = bwareafilt(mask, 2);
% Display mask image.
subplot(2, 2, 3);
imshow(mask);
hold on;
impixelinfo;
axis('on', 'image');
drawnow;
title('Mask, a Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');
% Label the two blobs so we can fit a line through wach one, one at a time.
[labeledImage, numBlobs] = bwlabel(mask);
% Fit a line through the left blob
leftLine = ismember(labeledImage, 1);
[leftRows, leftCols] = find(leftLine);
coefficients = polyfit(leftRows, leftCols, 1)
% Make sure xFit is plenty wide enough so that y will span the vertical part of the image.
rowFitLeft = -10 * rows : 10 * rows;
colFitLeft = polyval(coefficients, rowFitLeft);
% Get indexes where y is out of the image
badIndexes = (rowFitLeft < 1) | (rowFitLeft > rows);
colFitLeft(badIndexes) = [];
rowFitLeft(badIndexes) = [];
% Plot line in red over road lane marker.
hold on;
plot(colFitLeft, rowFitLeft, 'r-', 'LineWidth', 3);
% Fit a line through the left blob
rightLine = ismember(labeledImage, 2);
[rightRows, rightCols] = find(rightLine);
coefficients = polyfit(rightRows, rightCols, 1)
rowFitRight = -10 * rows : 10 * rows;
colFitRight = polyval(coefficients, rowFitRight);
% Get indexes where y is out of the image
badIndexes = (rowFitRight < 1) | (rowFitRight > rows);
colFitRight(badIndexes) = [];
rowFitRight(badIndexes) = [];
% Plot line in red over road lane marker.
plot(colFitRight, rowFitRight, 'r-', 'LineWidth', 3);
% Get the middle line as the average of the two x values.
middleLineCols = (colFitLeft + colFitRight) / 2;
% Plot line in red over road lane marker.
plot(middleLineCols, rowFitRight, 'r-', 'LineWidth', 3);

[Dekel Mashiach]

Thank you very much, you solved my problem !

Last question, I want to convert the image to 3D in order to get the depth of the centerline , is it possible to do that?

[Image Analyst]

See this:

https://www.mathworks.com/products/computer-vision.html#camera-calibration

I haven't used it so can't answer questions about it so call the Mathworks if you have questions.

Answer 2

[Image Analyst]

Here are the stps I would try

1. Crop the image to get rid of that white frame.
2. Threshold the image to get the white lines.
3. Call bwareafilt(bw, 2) to take only the 2 largest blobs.
4. Scan down line-by-line using find() to get the first and last white pixel on each line.
5. The center line is the average of the first column and the last column.
6. If you want, you can fit a straight line through the centerline data to remove noise and smooth the line.

[Dekel Mashiach]

I tried according to your steps, but something doesn't work for me, I think the problem is that the lines are not the same length and I do not know how to solve it

[Image Analyst]

I posted something about finding the centerline between two lines of different lengths about a week ago or so. Look for it. I need to get going very soon. I'm traveling over the next 4 days and won't be able to answer until Saturday.

[Dekel Mashiach]

Ok thanks , unfortunately I didn't find. Do I need the sizes of r1 and r2 to be equal to make the mean and find the middle?

[Abdul Hannan Qureshi]

Dear @Dekel Mashiach

@Image Analyst just assisted me few days back almost same topic. here is the link

https://www.mathworks.com/matlabcentral/answers/1708670-center-to-center-distance-between-objects-need-advise

[Dekel Mashiach]

I'm don't understand why the plot is like this

[Image Analyst]

@Abdul Hannan Qureshi that wasn't the post I was thinking of, but thanks. @Dekel Mashiach I just got back from 4 days of traveling. You probably have it solved by now, but if not, write back. I'd probably modify my steps 4-6 above and just fit a line on each side, then get the average x point for each fitted y value.

[Dekel Mashiach]

Unfortunately, I didn't resolve this yet. I would be very happy if you could help me.

Answer 3

[yanqi liu]

yes，sir，which is the target line，may be check this

https://ww2.mathworks.cn/matlabcentral/answers/1712640-how-to-create-centerline-between-to-lines-in-image?s_tid=srchtitle