code to detection the cars this code not counting cars properly How do i make it count correct ?

clc
clear all
MV = imread('cars1.jpg'); %To read image
MV1 = imread('backgnd.jpg');
A = double(rgb2gray(MV));%convert to gray
B= double(rgb2gray(MV1));%convert 2nd image to gray
[height, width] = size(A); %image size?
h1 = figure(1);
 %Foreground Detection
 thresh=11;
 fr_diff = abs(A-B);
 for j = 1:width
 for k = 1:height
 if (fr_diff(k,j)>thresh)
 fg(k,j) = A(k,j);
 else
 fg(k,j) = 0;
 end
 end
 end
 subplot(2,2,1) , imagesc(MV), title (['Orignal Frame']);
 subplot(2,2,2) , imshow(mat2gray(A)), title ('converted Frame');
 subplot(2,2,3) , imshow(mat2gray(B)), title ('BACKGND Frame ');
36;
 sd=imadjust(fg);% adjust the image intensity values to the color map
 level=graythresh(sd);
 m=imnoise(sd,'gaussian',0,0.025);% apply Gaussian noise
 k=wiener2(m,[5,5]);%filtering using Weiner filter
 bw=im2bw(k,level);
 bw2=imfill(bw,'holes');
 bw3 = bwareaopen(bw2,5000);
 labeled = bwlabel(bw3,8);
 cc=bwconncomp(bw3);
 Densityoftraffic = cc.NumObjects/(size(bw3,1)*size(bw3,2));
 blobMeasurements = regionprops(labeled,'all');
numberofcars = size(blobMeasurements, 1);
 subplot(2,2,4) , imagesc(labeled), title (['Foreground']);
 hold off;
 disp(numberofcars);% display number of cars
 disp(Densityoftraffic);%display number of vehicles

Answer 1

[KSSV]

It looks like the dimensions of image A, B are not same. So while subtracting you are getting the error.

You need to resize them into same dimensions using imresize.

A = double(rgb2gray(MV));%convert to gray
B= double(rgb2gray(MV1));%convert 2nd image to gray
[m1,n1,p1] = size(A) ; 
[m2,n2,p2] = size(B) ;

m = max(m1,m2) ;
n = max(n1,n2) ;

A = imresize(A,[m n]) ;
B = imresize(B, [m n]) ; 

[Jeje Ahmad]

can you help me the code does not count correct ; what is the value i will change to count correct ?

please

@KSSV

[KSSV]

Attach your image....I cannot promsie you the solution...but will give a try.

[Jeje Ahmad]

[Jeje Ahmad]

[Jeje Ahmad]

this is image

thank you

[Jeje Ahmad]

@KSSV

[KSSV]

Have you seen this?

https://in.mathworks.com/matlabcentral/answers/338296-cars-detection-in-image

https://in.mathworks.com/matlabcentral/answers/85192-how-to-detect-and-count-vehicle-patterns-in-a-image

[Jeje Ahmad]

yes i see it but not work good with me

[Jeje Ahmad]

Can you help me about code to count and detect the cars?

@KSSV

Answer 2

[Image Analyst]

Here, try this:

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 = 18;
fprintf('Beginning to run %s.m ...\n', mfilename);

% excel = actxserver('excel.application');
% filename = 'C:\Users\hayworth.ms\OneDrive - Procter and Gamble\Not Shared\Mark Hayworth Personal Files\Personal Documents\Financial Statements\Assets\ASSETS.xlsm';
% workbook = excel.Workbooks.Open(filename, [], true, [], 'images');
% excel.Visible = true;

MV = imread('cars1.png'); % To read image
MV1 = imread('backgnd.png');
carsImage = double(rgb2gray(MV));% convert to gray
[rows, columns, numColors] = size(carsImage)
backgroundImage = double(rgb2gray(MV1));%convert 2nd image to gray
[rowsb, columnsb, numColorsb] = size(backgroundImage)

% If the background image is not the same size as the test image, resize the test image.
if rows ~= rowsb || columns ~= columnsb
	message = sprintf('Cars = %dx%d, background = %dx%d.\nI will resize the cars image.', rows, columns, rowsb, columnsb);
	uiwait(helpdlg(message));
	carsImage = imresize(carsImage, [rowsb, columnsb]);
	[rows, columns, numColors] = size(carsImage)
end

% Display images.
subplot(2, 3, 1);
imshow(MV);
impixelinfo;
title('Cars1 image', 'FontSize', fontSize);
subplot(2, 3, 2);
imshow(MV1);
impixelinfo;
title('Background image', 'FontSize', fontSize);

h1 = figure(1);
%Foreground Detection
thresh=11;
fr_diff = imabsdiff(carsImage, backgroundImage);
subplot(2, 3, 3);
imshow(fr_diff, []);
impixelinfo;
title('Difference image', 'FontSize', fontSize);

% Take the histogram.
subplot(2, 3, 4);
histogram(fr_diff, 128);
% Put a line where the threshold is
xline(thresh, 'LineWidth', 2);
grid on;
title('Histogram of Difference Image', 'FontSize', fontSize);

% Threshold to create a binary image (mask)
mask = fr_diff > thresh;
subplot(2, 3, 5);
imshow(mask);
title('Thresholded image', 'FontSize', fontSize);

But rather than resizing, which doesn't allow for a perfect subtraction as you can see, you should really investigate why your frames are different sizes than your background image. And not only are they different sizes, but the cameras seem to be pointed in different directions so the field of view is not the same between the two cameras.

[Jeje Ahmad]

i try it but give error

Undefined function or variable 'xline'.

Error in new (line 47)

xline(thresh, 'LineWidth', 2);

[Jeje Ahmad]

and the threshold image it did not appear

@Image Analyst

[Image Analyst]

You have an old version. Try replacing xline with line:

line([thresh, thresh], ylim, 'LineWidth', 2);

[Jeje Ahmad]

i try it and the code run code

but can i ask you

the code does not give the number of cars an image?

[Image Analyst]

Correct. I did not do that part for you. Do you have a video? There is a demo in the Computer Vision Toolbox that does car counting.

https://www.mathworks.com/products/computer-vision.html#object-tracking

[Jeje Ahmad]

i dont have i video but i will see this demo

thank you so much

[Jeje Ahmad]

i open this toolbox and try to count cars but give not correctr

hoe i can add function to the code to counting cars?

@Image Analyst

[Jeje Ahmad]

@Image Analyst

[Jeje Ahmad]

can you answer me

pleaes

[Image Analyst]

I see you've already accepted an answer. Did it not really work? If not, unaccept it and maybe others will know it's not solved and open your post.

Like I said, you need to find out why your background is not the same size as your image, and why the camera does not have the same field of view (angle and field width) so that you can get better subtraction. Then you can just remove clutter with bwareaopen(), bwareafilt(), imclearborder(), imfill(), etc. and then call bwlabel to get the count.

Or you can simply get the Computer Vision Toolbox which has a car counting program already in it.

[Jeje Ahmad]

I see this toolbox but give my so error for the code

i just need a fuction added to the previous code to counting a cars?

@Image Analyst

[Image Analyst]

From your response, I can see you haven't yet read this: TUTORIAL: How to ask a question (on Answers) and get a fast answer so read that first.

I see you've already accepted an answer. Did it not really work? If not, unaccept it and maybe others will know it's not solved and open your post.

Like I said, AGAIN you need to find out why your background is not the same size as your image, and why the camera does not have the same field of view (angle and field width) so that you can get better subtraction. Why won't you answer the one, main question that is the source of all your problems?

Here is a little bit more:

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 = 18;
fprintf('Beginning to run %s.m ...\n', mfilename);

% excel = actxserver('excel.application');
% filename = 'C:\Users\hayworth.ms\OneDrive - Procter and Gamble\Not Shared\Mark Hayworth Personal Files\Personal Documents\Financial Statements\Assets\ASSETS.xlsm';
% workbook = excel.Workbooks.Open(filename, [], true, [], 'images');
% excel.Visible = true;

MV = imread('cars1.png'); % To read image
MV1 = imread('backgnd.png');
carsImage = double(rgb2gray(MV));% convert to gray
[rows, columns, numColors] = size(carsImage)
backgroundImage = double(rgb2gray(MV1));%convert 2nd image to gray
[rowsb, columnsb, numColorsb] = size(backgroundImage)

% If the background image is not the same size as the test image, resize the test image.
if rows ~= rowsb || columns ~= columnsb
	message = sprintf('Cars = %dx%d, background = %dx%d.\nI will resize the cars image.', rows, columns, rowsb, columnsb);
	uiwait(helpdlg(message));
	carsImage = imresize(carsImage, [rowsb, columnsb]);
	[rows, columns, numColors] = size(carsImage)
end

% Display images.
subplot(2, 3, 1);
imshow(MV);
impixelinfo;
title('Cars1 image', 'FontSize', fontSize);
subplot(2, 3, 2);
imshow(MV1);
impixelinfo;
title('Background image', 'FontSize', fontSize);

h1 = figure(1);
%Foreground Detection
thresh=11;
fr_diff = imabsdiff(carsImage, backgroundImage);
subplot(2, 3, 3);
imshow(fr_diff, []);
impixelinfo;
title('Difference image', 'FontSize', fontSize);

% Take the histogram.
subplot(2, 3, 4);
histogram(fr_diff, 128);
% Put a line where the threshold is
xline(thresh, 'LineWidth', 2);
grid on;
title('Histogram of Difference Image', 'FontSize', fontSize);

% Threshold to create a binary image (mask)
mask = fr_diff > thresh;
subplot(2, 3, 5);
imshow(mask);
title('Thresholded image', 'FontSize', fontSize);

% Filter out spurious blobs
mask = imfill(mask, 'holes');
mask = imclearborder(mask);
props = regionprops(mask, 'Area');
allAreas = sort([props.Area], 'descend')
mask = bwareafilt(mask, [100, inf]);
subplot(2, 3, 6);
imshow(mask);
title('Final Mask', 'FontSize', fontSize);

g = gcf;
g.WindowState = 'maximized';

fprintf('Done running %s.m ...\n', mfilename);

It still doesn't work great, again because you refuse to answer the questions about why the test image and the background don't correspond.

[Jeje Ahmad]

Error in new1 (line 75)

g.WindowState = 'maximized';

Give me this error?

[Image Analyst]

It shouldn't. That should work for every version of MATLAB since R2014b. For some reason you blew right past the version that you were supposed to enter when you posted your question but since that is a version that is over 6 years old, I assume you have R2020b and it should work. So the only other reason it wouldn't work with R2014b or later is if you didn't have the g=gcf line of code in there.

Regardless, it's just optional code to maximize the figure window and you can take it out if you want and the figure will show up "normalized" (non-full screen).

[Jeje Ahmad]

i will take the picture it is the same size

but i want a function to added to count the number of cars

can you help me

please

[Image Analyst]

Call bwlabel()

[labeledImage, numberOfCars] = bwlabel(binaryImage);

[Jeje Ahmad]

thank you sooo much

[Jeje Ahmad]

hi i am using this function but give me error

how i can correct this error

@Image Analyst

[Jeje Ahmad]

Undefined function or variable 'Call'.

Error in new1 (line 78)

Call bwlabel()

[Image Analyst]

Notice that I did not use the word "Call" which is not part of MATLAB syntax. I had this:

[labeledImage, numberOfCars] = bwlabel(binaryImage);

See? No "Call".

[Jeje Ahmad]

yes i see

but give me this error

Undefined function or variable 'binaryImage'.

Error in new (line 69)

[labeledImage, numberOfCars] = bwlabel(binaryImage);

[Jeje Ahmad]

i try this function but still give me this error

@Image Analyst

[Image Analyst]

Jeje, I'm sure you've figured this out by now, but when people give you code they make up variable names that you might not have. You have to replace them with the actual variable names you used. For example, maybe you named your binary image "mask" or "BW" or "BW1" or something else. Replace binaryImage with the actual name of the binary image you used.

[Jeje Ahmad]

you mean this one of this named:

MV = imread('cars1.png'); % To read image

MV1 = imread('backgnd.png');

or mask?

[Jeje Ahmad]

[Jeje Ahmad]

i am repalce but not give me the number of cars?

[Image Analyst]

It counts the blobs, regardless of what they represent. You have to do better segmentation to make it count only the cars and nothing else. The Computer Vision Toolbox has car tracking capability. I don't. So look there for a solution.

[Jeje Ahmad]

@Image Analyst

hi i am use the code to detect in video but the number of cars not give me how i can count the cars in video

foregroundDetector = vision.ForegroundDetector('NumGaussians', 3, ...

'NumTrainingFrames', 100);

videoReader = VideoReader('video.mp4');

for i = 1:200

frame = readFrame(videoReader); % read the next video frame

foreground = step(foregroundDetector, frame);

end

figure; imshow(frame); title('Video Frame');

figure; imshow(foreground); title('Foreground');

se = strel('square', 3);

filteredForeground = imopen(foreground, se);

figure; imshow(filteredForeground); title('Clean Foreground');

blobAnalysis = vision.BlobAnalysis('BoundingBoxOutputPort', true, ...

'AreaOutputPort', false, 'CentroidOutputPort', false, ...

'MinimumBlobArea', 1500);

bbox = step(blobAnalysis, filteredForeground);

result = insertShape(frame, 'Rectangle', bbox, 'Color', 'green');

numCars = size(bbox, 1);

result = insertText(result, [10 10], numCars, 'BoxOpacity', 1, ...

'FontSize', 14);

figure; imshow(result); title('Detected Cars');

videoPlayer = vision.VideoPlayer('Name', 'Detected Cars');

videoPlayer.Position(3:4) = [650,400]; % window size: [width, height]

se = strel('square', 3); % morphological filter for noise removal

while hasFrame(videoReader)

frame = readFrame(videoReader); % read the next video frame

% Detect the foreground in the current video frame

foreground = step(foregroundDetector, frame);

% Use morphological opening to remove noise in the foreground

filteredForeground = imopen(foreground, se);

% Detect the connected components with the specified minimum area, and

% compute their bounding boxes

bbox = step(blobAnalysis, filteredForeground);

% Draw bounding boxes around the detected cars

result = insertShape(frame, 'Rectangle', bbox, 'Color', 'green');

% Display the number of cars found in the video frame

numCars = size(bbox, 1);

result = insertText(result, [10 10], numCars, 'BoxOpacity', 1, ...

'FontSize', 14);

step(videoPlayer, result); % display the results

end

release(videoReader); % close the video file