Find the moving circle position between two images

Hey,

I was trying to write a code that evaluate the position vector of a circle with using two pictures. For example, in the first picture circle is on the (8,8) and in the second picture it will be (11,13). How can i calculate the position vector with using same size potographs?

Actually my goal is compare different at least 4 or five pictures which they captured to position of a circle. If i can understand two i think i can apply for all.

Thank you for your time.

Note: I will use colour dedection to find circle. Example :The circle will be green and the background will be all white.

Answer 1

[Image Analyst]

You can use image analysis, expecially the Color Thresholder app on the Apps tab of the tool ribbon.

Also see my Image Processing Tutorial in my File Exchange:

Image Analyst's File Exchange

If you have any more questions, then attach your images and code to read them in with the paperclip icon after you read this:

TUTORIAL: How to ask a question (on Answers) and get a fast answer

[Doga Selcuk]

i checked but there is nothing to here for me. Here is an example javascript for what i wanna do inmatlab:

https://github.com/oreHGA/Speed-Detector/blob/master/MotionDetection.java#L33

[Image Analyst]

Where did you check? I mean certainly you need to have images so it you checked your drive(s) and can't find your images, then there is nothing to do.

If you have images, then you can use segmentation methods on it, such as one or more of the ones in my file exchange or from code you export from the Color Thresholder app.

See attached demo where I track a green Sharpie marker. See if that helps.

Again, I can't offer more customized help unless you attach your images.

Or you could try imfindcircles

[Doga Selcuk]

Thanks a lot. I will try to upload images ASAP.

Answer 2

[Image Analyst]

Try this:

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 16;

%===============================================================================
% Get the name of the background image the user wants to use.
baseFileName = 'coloredchips.png';
folder = pwd;
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

%=======================================================================================
% Read in demo image.
rgbImage = imread(fullFileName);
% Get the dimensions of the image.
[rows, columns, numberOfColorChannels] = size(rgbImage)
% Display image.
subplot(2, 2, 1);
imshow(rgbImage, []);
impixelinfo;
axis on;
caption = sprintf('Original RGB Image\n%s', baseFileName);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
% Set up figure properties:
% Enlarge figure to full screen.
g = gcf;
g.WindowState = "maximized";
% Get rid of tool bar and pulldown menus that are along top of figure.
% set(gcf, 'Toolbar', 'none', 'Menu', 'none');
% Give a name to the title bar.
set(gcf, 'Name', 'Demo by ImageAnalyst', 'NumberTitle', 'Off')
drawnow;

%=======================================================================================
% Threshold the image to create a mask
[mask, maskedRGBImage] = createMask(rgbImage);
% Fill holes
mask = imfill(mask, 'holes');
% Display the mask image.
subplot(2, 2, 2);
imshow(mask, []);
impixelinfo;
axis('on', 'image');
title('Mask Image', 'FontSize', fontSize); 
drawnow;

%=======================================================================================
% Plot the borders of all the blobs in the overlay above the original background image 
% using the coordinates returned by bwboundaries().
% bwboundaries() returns a cell array, where each cell contains the row/column coordinates for an object in the image.
% Here is where we actually get the boundaries for each blob.
boundaries = bwboundaries(mask);
% boundaries is a cell array - one cell for each blob.
% In each cell is an N-by-2 list of coordinates in a (row, column) format.  Note: NOT (x,y).
% Column 1 is rows, or y.    Column 2 is columns, or x.
numberOfBoundaries = size(boundaries, 1); % Count the boundaries so we can use it in our for loop
% Here is where we actually plot the boundaries of each blob in the overlay.
subplot(2, 2, 3);
imshow(rgbImage);
hold on; % Don't let boundaries blow away the displayed image.
for k = 1 : numberOfBoundaries
    thisBoundary = boundaries{k}; % Get boundary for this specific blob.
    x = thisBoundary(:,2); % Column 2 is the columns, which is x.
    y = thisBoundary(:,1); % Column 1 is the rows, which is y.
    plot(x, y, 'r-', 'LineWidth', 2); % Plot boundary in red.
end
hold off;
caption = sprintf('Original image with %d detected green blobs', numberOfBoundaries); 
title(caption, 'FontSize', fontSize); 
axis('on', 'image'); % Make sure image is not artificially stretched because of screen's aspect ratio.

%=======================================================================================
% Find the centroid of the green blobs.
props = regionprops(mask, 'Centroid');
xyCentroids = vertcat(props.Centroid)
xCentroid = xyCentroids(:, 1);
yCentroid = xyCentroids(:, 2);

%=======================================================================================
% Plot a big red cross over the centroids.
hold on;
plot(xCentroid, yCentroid, 'r+', 'LineWidth', 2, 'MarkerSize', 30);
message = sprintf('Done!')
uiwait(helpdlg(message));

%=======================================================================================
function [BW,maskedRGBImage] = createMask(RGB)
%createMask  Threshold RGB image using auto-generated code from colorThresholder app.
%  [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
%  auto-generated code from the colorThresholder app. The colorspace and
%  range for each channel of the colorspace were set within the app. The
%  segmentation mask is returned in BW, and a composite of the mask and
%  original RGB images is returned in maskedRGBImage.
% Auto-generated by colorThresholder app on 10-Oct-2022
%------------------------------------------------------
% Convert RGB image to chosen color space
I = rgb2hsv(RGB);
% Define thresholds for channel 1 based on histogram settings
channel1Min = 0.303;
channel1Max = 0.528;
% Define thresholds for channel 2 based on histogram settings
channel2Min = 0.446;
channel2Max = 1.000;
% Define thresholds for channel 3 based on histogram settings
channel3Min = 0.292;
channel3Max = 1.000;
% Create mask based on chosen histogram thresholds
sliderBW = (I(:,:,1) >= channel1Min ) & (I(:,:,1) <= channel1Max) & ...
    (I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
    (I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);
BW = sliderBW;
% Initialize output masked image based on input image.
maskedRGBImage = RGB;
% Set background pixels where BW is false to zero.
maskedRGBImage(repmat(~BW,[1 1 3])) = 0;
end

[Doga Selcuk]

Pictures

First of all, thank you for all your answers. I will try to explain my subject with the help of two basic pictures that i attached.

Firstly, we have let's say 20 green points. we captured at this moment where they placed together with small distances between each them. Then in the second one due to the time and assume they are moving, we have another picture that shows their movement. And my aim is to dedect of each green points as you did, however i want to store their initial location and for each green points calculate their last location and find a position vectors of each one. For this i guess i need a object tracker or something else but i don't know how can i do that and i'm waiting for your answer. Sorry for unlimited questions

Note: since they are two pictures how can algorithm will understand and do not confuse every green points i don't know. Should we use video instead?

[Image Analyst]

Not seeing the two images you attached. Where did you attach them?

If you're tracking multiple points, which can cross paths and enter and leave the field of view, it can get to be very difficult. The Computer Vision Toolbox has tracking capabilities so I suggest you check it out.

[Doga Selcuk]

Sorry about that. I uploaded that again.

Should i use video for tracking or matlab has any algortihm that analyzes those pictures and understand their movements ?

And another point in the first comment that you gave has a video type and could i work with it for multiple tracking analyzing ? I'm so confused

[Image Analyst]

What are those things and why are they moving? And why do you need to track them?

Detecting green blobs is one thing but tracking them is a more difficult problem. Sure, try the tracking software in MATLAB.

Tracking can work with a stream of video frames or a sequence of separate still image files.

[Doga Selcuk]

Those are for just the understand the tracking mechanism. Actually my aim is with using the same Test1 design i mean wind tunnel test. As you can see there are streamlines due to the flow. Now what if we put the styrofoam foam circles which they have neglicible weight and have like 0.5 mm diameter. They will also have a movement and they will create similar streamlines too. if i know the time and have the video or captures i don't know yet, i can find their position vector using a MATLAB algorithm and i can find their velocity with respect to time and position.

Due to the idea is complicated and i have no wind tunnel i just want to try something more easier for me otherwise i probably won't be able to do that.

I think tracking is more suitable but when i discuss with somebody they told me capture two images and substract the frames and should use colour dedection. I think it may be a problem to understand the different but looks exactly the same circles motions without confusing between two frames because which one is which one but i will search more&more. Thank you

Test1: https://www.youtube.com/watch?v=Png0fnG0b_U if the Test1 button won't open.

[Image Analyst]

For our complicated tracking needs, we use Noldus software:

https://www.noldus.com/

Ask them if your windtunnel situation could use their software.

Or else I'm sure there are wind tunnel software programs commercially available, so why write your own?

[Doga Selcuk]

I will, thank you.

I just want to use Matlab software and actually im a seniour student so another point is it's kinda challenge for me to do with matlab but as i said there are limited examples in matlab as i see. I think you're right