How to get the minimum mode image and a plot, using pixel values of all the frames of the video in the given program?

That is, to get the image background of the site, so that i would be able to subtract the original frame to the mode frame and get the number of vehicles passing through?

The code is as follows:

nframes = trafficVid.NumberOfFrames;
I = read(trafficVid, 1);
taggedCars = zeros([size(I,1) size(I,2) 3 nframes], class(I));

for k = 1 : nframes
    singleFrame = read(trafficVid, k);

      % Convert to grayscale to do morphological processing.
      I = rgb2gray(singleFrame);

      % Remove dark cars.
      noDarkCars = imextendedmax(I, darkCarValue);

      % Remove lane markings and other non-disk shaped structures.
      noSmallStructures = imopen(noDarkCars, sedisk);

      % Remove small structures.
      noSmallStructures = bwareaopen(noSmallStructures, 150);

      % Get the area and centroid of each remaining object in the frame. The
      % object with the largest area is the light-colored car.  Create a copy
      % of the original frame and tag the car by changing the centroid pixel
      % value to red.
      taggedCars(:,:,:,k) = singleFrame;

      stats = regionprops(noSmallStructures, {'Centroid','Area'});
      if ~isempty([stats.Area])
          areaArray = [stats.Area];
          [junk,idx] = max(areaArray);
          c = stats(idx).Centroid;
          c = floor(fliplr(c));
          width = 2;
          row = c(1)-width:c(1)+width;
          col = c(2)-width:c(2)+width;
          taggedCars(row,col,1,k) = 255;
          taggedCars(row,col,2,k) = 0;
          taggedCars(row,col,3,k) = 0;
      end
  end

Answer 1

[Walter Roberson]

before your "for" loop, add

minimg = inf(size(I));
for k = 1 : nframes
  singleFrame = read(trafficVid, k);
  minimg = min(minimg, singleFrame);
end

now minimg contains the minimum of all of the RGB components.

Note: the minimum RGB components for any given pixel will not necessarily be the darkest value. It will also not necessarily be the "background". Consider that if pedestrian wearing a black jacket walks through the scene, then the black may become the minimum ever found at the locations traveled through, but it would not be the background.

Answer 2

[Image Analyst]

The mode frame sounds like a good idea, though it seems like people usually use Gaussian Mixture Models to get background from video. See http://www.mathworks.com/help/vision/examples/detecting-cars-using-gaussian-mixture-models.html?prodcode=VP&language=en

[ramya ullagaddimath]

Sir/Ma'am, Thank you so much for the above link, it was a life-saver. Is there any extension that I could add, so as to make this code read both the cars and motorcycles too? Give me a separate list of the total number of cars, motorcycles, trucks and other classification of the vehicles in a given traffic video?

Thank you.

[Image Analyst]

Personally, I don't know because I don't have that toolbox and haven't used that code, but I would think you could do that.