[Computer Vision] Size of colored Object detected with my algorithm

Hi @ all!

I make a code that detects and tracks colored objects. It works quite fine! Anyway I need also to calculate and to store the size of the detected objects for post elaboration (like area, perimeter etc etc) and unfortunately I don't know how to do that! Can someone help me?

There is my code:

      redThresh = 0.8; % Threshold for red component of color detection
    greenThresh = 0.4; % Threshold for green component of color detection
    blueThresh = 0.4; % Threshold for blue component of color detection

    vidDevice = imaq.VideoDevice('winvideo', 1, 'YUY2_640x480', ... % Acquire input video stream
                        'ROI', [1 1 640 480], ...
                        'ReturnedColorSpace', 'rgb');
    vidInfo = imaqhwinfo(vidDevice); % Acquire input video property
    hblob = vision.BlobAnalysis('AreaOutputPort', true, ... % Set blob analysis handling
                                    'CentroidOutputPort', true, ... 
                                    'BoundingBoxOutputPort', true', ...
                                    'MinimumBlobArea', 400, ...
                                    'MaximumCount', 50);
    hshapeinsWhiteBox = vision.ShapeInserter('BorderColor', 'Custom', ...
                                            'CustomBorderColor', [1 0 0]); % Set white box handling
    htextins = vision.TextInserter('Text', 'Number of Colored Object(s): %2d', ... % Set text for number of blobs
                                        'Location',  [7 2], ...
                                        'Color', [1 1 1], ... // white color
                                        'Font', 'Courier New', ...
                                        'FontSize', 12);
    htextinsCent = vision.TextInserter('Text', '+      X:%6.2f,  Y:%6.2f', ... % set text for centroid
                                        'LocationSource', 'Input port', ...
                                        'Color', [0 0 0], ... // black color
                                        'FontSize', 12);
    hVideoIn = vision.VideoPlayer('Name', 'Final Video', ... % Output video player
                                    'Position', [100 100 vidInfo.MaxWidth+20 vidInfo.MaxHeight+30]);
    nFrame = 0; % Frame number initialization
    nFrameMax = 1000;  % Max frame number to acquire
    k = 1;

    %%Processing Loop
    while(nFrame < nFrameMax)
        rgbFrame = step(vidDevice); % Acquire single frame
        rgbFrame = flipdim(rgbFrame,2); % obtain the mirror image for displaying
        redFrame = rgbFrame(:,:,1);  % Red component of RGB Frame
        greenFrame = rgbFrame(:,:,2);  % Green component of RGB Frame
        blueFrame = rgbFrame(:,:,3);  % Blue component of RGB Frame

        % Loop of Detection based on Thresholds previously defined
        for i = 1:480
            for j = 1:640
                if redFrame(i,j) >= redThresh
                    redFrameThres(i,j) = 1;
                else redFrameThres(i,j) = 0;
                end

                if greenFrame(i,j) <= greenThresh
                    greenFrameThres(i,j) = 1;
                else greenFrameThres(i,j) = 0;
                end

                if blueFrame(i,j) <= blueThresh
                    blueFrameThres(i,j) = 1;
                else blueFrameThres(i,j) = 0;
                end
            end
        end

        binFrame = redFrameThres & greenFrameThres & blueFrameThres; % get the common region
        binFrameMatrix(:,:,k) = binFrame; % Storage of binFrame

        [AREA, CENTROID, BBOX] = step(hblob, binFrame); % Get the area, centroids and bounding boxes of the blobs

        rgbFrame(1:15,1:215,:) = 0; % put a black region on the output stream
        vidIn = step(hshapeinsWhiteBox, rgbFrame, bbox); % Insert the white box
        for object = 1:1:length(bbox(:,1)) % Write the corresponding centroids
            vidIn = step(htextinsCent, vidIn, [centroid(object,1) centroid(object,2)], [centroid(object,1)-6 centroid(object,2)-9]); 
        end
        vidIn = step(htextins, vidIn, uint8(length(bbox(:,1)))); % Count the number of blobs
        step(hVideoIn, vidIn); % Output video stream
        nFrame = nFrame+1;
        k = k+1;
    end
    %%Clearing Memory
    release(hVideoIn); % Release all memory and buffer used
    release(vidDevice);
    clear all;
    clc;

[JENNIFER JACOB]

how did u find the exact threshold values for these colors?

[Image Analyst]

Jennifer, see the Color Thresholder on the Apps tab of the tool ribbon. Or else see my File Exchange for color segmentation demos.

Answer 1

[Iain]

have a look at regionprops.