Related
I have this MATLab code to count the number of objects in the image. There are two objects in the image I am choosing (a car and a cyclist). However, the program is returning a wrong output saying there are 0 objects. Can someone find the error in the code? Thanks.
The logic behind the code is:
1. Take two input images are given, one without objects and one with objects.
2. Convert the input images from RGB to Gray scale.
3. Compare the two images and find the difference.
4. Convert the image obtained to binary.
5. In the image, only open the blobs whose area is greater than 4000.
6. Display the count and density.
clc;
MV = imread('car.png'); %To read image
MV1 = imread('backgnd.png');
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 ');
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
An empty image(of a road) with no objects(vehicles) in it
An image of the same road but with 2 objects(car and cyclist) in it
Try This it will help you in an optimize manner
clc
clear all
close all
im1 = imread('image1.png');
im2 = imread('image2.png');
gray1 = double(rgb2gray(im1));
gray2 = double(rgb2gray(im2));
absDif = mat2gray(abs(gray1 - gray2));
figure,imshow(absDif,[])
absDfbw = im2bw(absDif,0.9*graythresh(absDif));
figure,imshow(absDfbw,[])
absDfbw = bwareaopen(absDfbw,25);
absDfbw = imclose(absDfbw,strel('disk',5));
figure,imshow(absDfbw,[])
Results are:
Thank You
pointA=[9.62579 15.7309 3.3291];
pointB=[13.546 25.6869 3.3291];
pointC=[23.502 21.7667 -3.3291];
pointD=[19.5818 11.8107 -3.3291];
points=[pointA' pointB' pointC' pointD'];
fill3(points(1,:),points(2,:),points(3,:),'r')
grid on
alpha(0.3)
This code will show a filled plane(Cant add images yet T.T)
Now here is my problem. On a spreadsheet, I have x,y,z coordinates of thousands of points. The 4 consecutive points form a plane like the one shown. How do I make a code such that for every 4 consecutive points, it makes a filled plane.
Basically, if I have 400 points, I want the code to plot 100 planes.
Assuming your data are a matrix, m = (400,3)
m = rand(400,3);
for i = 1:length(m);
m2 = m'; % Transpose
end
Create a 3-D matrix in which 'j' represents each set of points:
m3=[];
%Not the most elegant way to cycle through every four points but it works!
z = 0:(length(m2)/4); z1 = (z*4)+1; z1 = z1(:,1:length(z)-1);
for j = 1:length(z1);
m3(:,:,j) = m2(:,z1(j):(z1(j)+3));
end
'j' now has a total length = 100 - representing the amount planes;
fill3(m3(1,:,1),m3(2,:,1),m3(3,:,1),'r');
% Cycle through planes- make a new figure for each plane;
for j = 1:length(z1);
fill3(m3(1,:,j),m3(2,:,j),m3(3,:,j),'r');
end
clear all, close all, clc
pointA=rand(99,1);
pointB=rand(99,1);
pointC=rand(99,1);
pointD=rand(99,1);
pointAmat = reshape(pointA,3,1,[]);
pointBmat = reshape(pointB,3,1,[]);
pointCmat = reshape(pointC,3,1,[]);
pointDmat = reshape(pointD,3,1,[]);
points=[pointAmat pointBmat pointCmat pointDmat];
for i = 1:size(points,3)
fill3(points(1,:,i),points(2,:,i),points(3,:,i),'r')
hold all
end
grid on
alpha(0.3)
Hope this helps.
I'm making an image processing project and I have stuck in one the project's steps. Here is the situation;
This is my mask:
and I want to detect the maximum-sized rectangle that can fit into this mask like this.
I'm using MATLAB for my project. Do you know any fast way to accomplish this aim. Any code sample, approach or technique would be great.
EDIT 1 : The two algorithms below are works with lot's of the cases. But both of them give wrong results in some difficult cases. I'am using both of them in my project.
This approach starts with the entire image and shrinks each border in turn pixel-by-pixel until it finds an acceptable rectangle.
It takes ~0.02 seconds to run on the example image, so it's reasonably fast.
EDIT: I should clarify that this isn't meant to be a universal solution. This algorithm relies on the rectangle being centered and having roughly the same aspect ratio as the image itself. However, in the cases where it is appropriate, it is fast. #DanielHsH offered a solution which they claim works in all cases.
The code:
clear; clc;
tic;
%% // read image
imrgb= imread('box.png');
im = im2bw(rgb2gray(imrgb)); %// binarize image
im = 1-im; %// convert "empty" regions to 0 intensity
[rows,cols] = size(im);
%% // set up initial parameters
ULrow = 1; %// upper-left row (param #1)
ULcol = 1; %// upper-left column (param #2)
BRrow = rows; %// bottom-right row (param #3)
BRcol = cols; %// bottom-right column (param #4)
parameters = 1:4; %// parameters left to be updated
pidx = 0; %// index of parameter currently being updated
%% // shrink region until acceptable
while ~isempty(parameters); %// update until all parameters reach bounds
%// 1. update parameter number
pidx = pidx+1;
pidx = mod( pidx-1, length(parameters) ) + 1;
p = parameters(pidx); %// current parameter number
%// 2. update current parameter
if p==1; ULrow = ULrow+1; end;
if p==2; ULcol = ULcol+1; end;
if p==3; BRrow = BRrow-1; end;
if p==4; BRcol = BRcol-1; end;
%// 3. grab newest part of region (row or column)
if p==1; region = im(ULrow,ULcol:BRcol); end;
if p==2; region = im(ULrow:BRrow,ULcol); end;
if p==3; region = im(BRrow,ULcol:BRcol); end;
if p==4; region = im(ULrow:BRrow,BRcol); end;
%// 4. if the new region has only zeros, stop shrinking the current parameter
if isempty(find(region,1))
parameters(pidx) = [];
end
end
toc;
params = [ULrow ULcol BRrow BRcol]
area = (BRrow-ULrow)*(BRcol-ULcol)
The results for this image:
Elapsed time is 0.027032 seconds.
params =
10 25 457 471
area =
199362
Code to visualize results:
imrgb(params(1):params(3),params(2):params(4),1) = 0;
imrgb(params(1):params(3),params(2):params(4),2) = 255;
imrgb(params(1):params(3),params(2):params(4),3) = 255;
imshow(imrgb);
Another example image:
Here is a correct answer.
You must use dynamic programming! Other methods of direct calculation (like cutting 1 pixel from each edge) might produce sub-optimal results. My method guarantees that it selects the largest possible rectangle that fits in the mask. I assume that the mask has 1 big convex white blob of any shape with black background around it.
I wrote 2 methods. findRect() which finds the best possible square (starting on x,y with length l). The second method LargestInscribedImage() is an example of how to find any rectangle (of any aspect ratio). The trick is to resize the mask image, find a square and resize it back.
In my example the method finds the larges rectangle that can be fit in the mask having the same aspect ration as the mask image. For example if the mask image is of size 100x200 pixels than the algorithm will find the largest rectangle having aspect ratio 1:2.
% ----------------------------------------------------------
function LargestInscribedImage()
% ----------------------------------------------------------
close all
im = double(imread('aa.bmp')); % Balck and white image of your mask
im = im(:,:,1); % If it is colored RGB take only one of the channels
b = imresize(im,[size(im,1) size(im,1)]); Make the mask square by resizing it by its aspect ratio.
SC = 1; % Put 2..4 to scale down the image an speed up the algorithm
[x1,y1,l1] = findRect(b,SC); % Lunch the dyn prog algorithm
[x2,y2,l2] = findRect(rot90(b),SC); % rotate the image by 90deg and solve
% Rotate back: x2,y2 according to rot90
tmp = x2;
x2 = size(im,1)/SC-y2-l2;
y2 = tmp;
% Select the best solution of the above (for the original image and for the rotated by 90degrees
if (l1>=l2)
corn = sqCorn(x1,y1,l1);
else
corn = sqCorn(x2,y2,l2);
end
b = imresize(b,1/SC);
figure;imshow(b>0); hold on;
plot(corn(1,:),corn(2,:),'O')
corn = corn*SC;
corn(1,:) = corn(1,:)*size(im,2)/size(im,1);
figure;imshow(im); hold on;
plot(corn(1,:),corn(2,:),'O')
end
function corn = sqCorn(x,y,l)
corn = [x,y;x,y+l;x+l,y;x+l,y+l]';
end
% ----------------------------------------------------------
function [x,y,l] = findRect(b,SC)
b = imresize(b,1/SC);
res = zeros(size(b,1),size(b,2),3);
% initialize first col
for i = 1:1:size(b,1)
if (b(i,1) > 0)
res(i,1,:) = [i,1,0];
end
end
% initialize first row
for i = 1:1:size(b,2)
if (b(1,i) > 0)
res(1,i,:) = [1,i,0];
end
end
% DynProg
for i = 2:1:size(b,1)
for j = 2:1:size(b,2)
isWhite = b(i,j) > 0;
if (~isWhite)
res(i,j,:)=res(i-1,j-1,:); % copy
else
if (b(i-1,j-1)>0) % continuous line
lineBeg = [res(i-1,j-1,1),res(i-1,j-1,2)];
lineLenght = res(i-1,j-1,3);
if ((b(lineBeg(1),j)>0)&&(b(i,lineBeg(2))>0)) % if second diag is good
res(i,j,:) = [lineBeg,lineLenght+1];
else
res(i,j,:)=res(i-1,j-1,:); % copy since line has ended
end
else
res(i,j,:) = [i,j,0]; % Line start
end
end
end
end
% check last col
[maxValCol,WhereCol] = max(res(:,end,3));
% check last row
[maxValRow,WhereRow] = max(res(end,:,3));
% Find max
x= 0; y = 0; l = 0;
if (maxValCol>maxValRow)
y = res(WhereCol,end,1);
x = res(WhereCol,end,2);
l = maxValCol;
else
y = res(end,WhereRow,1);
x = res(end,WhereRow,2);
l = maxValRow;
end
corn = [x,y;x,y+l;x+l,y;x+l,y+l]';
% figure;imshow(b>0); hold on;
% plot(corn(1,:),corn(2,:),'O')
return;
end
The black boundaries in your image are curved and not closed. For example, in the top right corner, the black boundaries won't meet and form a closed contour. Therefore, a simple strategy in one of my comments will not work.
I am now providing you with a skeleton of a code which you can play with and add conditions as per your need. My idea is as follows:
To find left-side x-coordinate of the rectangle, first count the white pixels each column of the image contains:
%I assume that the image has already been converted to binary.
whitePixels=sum(img,1);
Then find the rate of change:
diffWhitePixels=diff(whitePixels);
If you see the bar plot of diffWhitePixels then you will observe various large entries (which indicate that the white region is still not in a straight line, and it is not a proper place to put the rectangles left vertical edge). Small entries (in your image, less than 5) indicate you can put the rectangle edge there.
You can do similar things to determine right, top and bottom edge positions of the rectangles.
Discussion:
First of all, the problem is ill-posed in my opinion. What do you mean by maximum-sized rectangle? Is it maximum area or length of side? In all possible cases, I don't think above method can get the correct answer. I can think of two or three cases right now where above method would fail, but it will at least give you the right answer on images similar to the given image, provided you adjust the values.
You can put some constraints once you know how your images are going to look. For example, if the black boundary curves inside, you can say that you don't want a column such as [0;0;...0;1;1;...0;0;...;0;1;1;...;1] i.e. zeros surrounded by ones. Another constraint could be how many black pixels do you want to allow? You can also crop the image till to remove extra black pixels. In your image, you can crop the image (programmatically) from the left and the bottom edge. Cropping an image is probably necessary, and definitely the better thing to do.
I'm making an image processing project and I have stuck in one the project's steps. Here is the situation;
This is my mask:
and I want to detect the maximum-sized rectangle that can fit into this mask like this.
I'm using MATLAB for my project. Do you know any fast way to accomplish this aim. Any code sample, approach or technique would be great.
EDIT 1 : The two algorithms below are works with lot's of the cases. But both of them give wrong results in some difficult cases. I'am using both of them in my project.
This approach starts with the entire image and shrinks each border in turn pixel-by-pixel until it finds an acceptable rectangle.
It takes ~0.02 seconds to run on the example image, so it's reasonably fast.
EDIT: I should clarify that this isn't meant to be a universal solution. This algorithm relies on the rectangle being centered and having roughly the same aspect ratio as the image itself. However, in the cases where it is appropriate, it is fast. #DanielHsH offered a solution which they claim works in all cases.
The code:
clear; clc;
tic;
%% // read image
imrgb= imread('box.png');
im = im2bw(rgb2gray(imrgb)); %// binarize image
im = 1-im; %// convert "empty" regions to 0 intensity
[rows,cols] = size(im);
%% // set up initial parameters
ULrow = 1; %// upper-left row (param #1)
ULcol = 1; %// upper-left column (param #2)
BRrow = rows; %// bottom-right row (param #3)
BRcol = cols; %// bottom-right column (param #4)
parameters = 1:4; %// parameters left to be updated
pidx = 0; %// index of parameter currently being updated
%% // shrink region until acceptable
while ~isempty(parameters); %// update until all parameters reach bounds
%// 1. update parameter number
pidx = pidx+1;
pidx = mod( pidx-1, length(parameters) ) + 1;
p = parameters(pidx); %// current parameter number
%// 2. update current parameter
if p==1; ULrow = ULrow+1; end;
if p==2; ULcol = ULcol+1; end;
if p==3; BRrow = BRrow-1; end;
if p==4; BRcol = BRcol-1; end;
%// 3. grab newest part of region (row or column)
if p==1; region = im(ULrow,ULcol:BRcol); end;
if p==2; region = im(ULrow:BRrow,ULcol); end;
if p==3; region = im(BRrow,ULcol:BRcol); end;
if p==4; region = im(ULrow:BRrow,BRcol); end;
%// 4. if the new region has only zeros, stop shrinking the current parameter
if isempty(find(region,1))
parameters(pidx) = [];
end
end
toc;
params = [ULrow ULcol BRrow BRcol]
area = (BRrow-ULrow)*(BRcol-ULcol)
The results for this image:
Elapsed time is 0.027032 seconds.
params =
10 25 457 471
area =
199362
Code to visualize results:
imrgb(params(1):params(3),params(2):params(4),1) = 0;
imrgb(params(1):params(3),params(2):params(4),2) = 255;
imrgb(params(1):params(3),params(2):params(4),3) = 255;
imshow(imrgb);
Another example image:
Here is a correct answer.
You must use dynamic programming! Other methods of direct calculation (like cutting 1 pixel from each edge) might produce sub-optimal results. My method guarantees that it selects the largest possible rectangle that fits in the mask. I assume that the mask has 1 big convex white blob of any shape with black background around it.
I wrote 2 methods. findRect() which finds the best possible square (starting on x,y with length l). The second method LargestInscribedImage() is an example of how to find any rectangle (of any aspect ratio). The trick is to resize the mask image, find a square and resize it back.
In my example the method finds the larges rectangle that can be fit in the mask having the same aspect ration as the mask image. For example if the mask image is of size 100x200 pixels than the algorithm will find the largest rectangle having aspect ratio 1:2.
% ----------------------------------------------------------
function LargestInscribedImage()
% ----------------------------------------------------------
close all
im = double(imread('aa.bmp')); % Balck and white image of your mask
im = im(:,:,1); % If it is colored RGB take only one of the channels
b = imresize(im,[size(im,1) size(im,1)]); Make the mask square by resizing it by its aspect ratio.
SC = 1; % Put 2..4 to scale down the image an speed up the algorithm
[x1,y1,l1] = findRect(b,SC); % Lunch the dyn prog algorithm
[x2,y2,l2] = findRect(rot90(b),SC); % rotate the image by 90deg and solve
% Rotate back: x2,y2 according to rot90
tmp = x2;
x2 = size(im,1)/SC-y2-l2;
y2 = tmp;
% Select the best solution of the above (for the original image and for the rotated by 90degrees
if (l1>=l2)
corn = sqCorn(x1,y1,l1);
else
corn = sqCorn(x2,y2,l2);
end
b = imresize(b,1/SC);
figure;imshow(b>0); hold on;
plot(corn(1,:),corn(2,:),'O')
corn = corn*SC;
corn(1,:) = corn(1,:)*size(im,2)/size(im,1);
figure;imshow(im); hold on;
plot(corn(1,:),corn(2,:),'O')
end
function corn = sqCorn(x,y,l)
corn = [x,y;x,y+l;x+l,y;x+l,y+l]';
end
% ----------------------------------------------------------
function [x,y,l] = findRect(b,SC)
b = imresize(b,1/SC);
res = zeros(size(b,1),size(b,2),3);
% initialize first col
for i = 1:1:size(b,1)
if (b(i,1) > 0)
res(i,1,:) = [i,1,0];
end
end
% initialize first row
for i = 1:1:size(b,2)
if (b(1,i) > 0)
res(1,i,:) = [1,i,0];
end
end
% DynProg
for i = 2:1:size(b,1)
for j = 2:1:size(b,2)
isWhite = b(i,j) > 0;
if (~isWhite)
res(i,j,:)=res(i-1,j-1,:); % copy
else
if (b(i-1,j-1)>0) % continuous line
lineBeg = [res(i-1,j-1,1),res(i-1,j-1,2)];
lineLenght = res(i-1,j-1,3);
if ((b(lineBeg(1),j)>0)&&(b(i,lineBeg(2))>0)) % if second diag is good
res(i,j,:) = [lineBeg,lineLenght+1];
else
res(i,j,:)=res(i-1,j-1,:); % copy since line has ended
end
else
res(i,j,:) = [i,j,0]; % Line start
end
end
end
end
% check last col
[maxValCol,WhereCol] = max(res(:,end,3));
% check last row
[maxValRow,WhereRow] = max(res(end,:,3));
% Find max
x= 0; y = 0; l = 0;
if (maxValCol>maxValRow)
y = res(WhereCol,end,1);
x = res(WhereCol,end,2);
l = maxValCol;
else
y = res(end,WhereRow,1);
x = res(end,WhereRow,2);
l = maxValRow;
end
corn = [x,y;x,y+l;x+l,y;x+l,y+l]';
% figure;imshow(b>0); hold on;
% plot(corn(1,:),corn(2,:),'O')
return;
end
The black boundaries in your image are curved and not closed. For example, in the top right corner, the black boundaries won't meet and form a closed contour. Therefore, a simple strategy in one of my comments will not work.
I am now providing you with a skeleton of a code which you can play with and add conditions as per your need. My idea is as follows:
To find left-side x-coordinate of the rectangle, first count the white pixels each column of the image contains:
%I assume that the image has already been converted to binary.
whitePixels=sum(img,1);
Then find the rate of change:
diffWhitePixels=diff(whitePixels);
If you see the bar plot of diffWhitePixels then you will observe various large entries (which indicate that the white region is still not in a straight line, and it is not a proper place to put the rectangles left vertical edge). Small entries (in your image, less than 5) indicate you can put the rectangle edge there.
You can do similar things to determine right, top and bottom edge positions of the rectangles.
Discussion:
First of all, the problem is ill-posed in my opinion. What do you mean by maximum-sized rectangle? Is it maximum area or length of side? In all possible cases, I don't think above method can get the correct answer. I can think of two or three cases right now where above method would fail, but it will at least give you the right answer on images similar to the given image, provided you adjust the values.
You can put some constraints once you know how your images are going to look. For example, if the black boundary curves inside, you can say that you don't want a column such as [0;0;...0;1;1;...0;0;...;0;1;1;...;1] i.e. zeros surrounded by ones. Another constraint could be how many black pixels do you want to allow? You can also crop the image till to remove extra black pixels. In your image, you can crop the image (programmatically) from the left and the bottom edge. Cropping an image is probably necessary, and definitely the better thing to do.
I have some shapes on an image that i've attempted to label according to their Area using a solution provided to me:
stats = regionprops(BW,'Area')
stats2 = regionprops(BW,'Centroid')
figure,imshow(BW)
for k = 1:numel(stats)
xy = stats2(k).Centroid
if (stats(k).Area>TH)
text(xy(1),xy(2),'L') %// Large Shape
else
text(xy(1),xy(2),'S') %// Small Shape
end
end
But it turns out the shapes are too small for the letters ( which would be too small even if I changed the font), I'm wondering if there's a way to do the thresholding to produce a colour code i.e change the filling of the shapes based on their area?
See if this is inspiring enough for you -
%// Input image. This one is chosen as it is available in MATLAB image library
img = imread('coins.png');
%// Convert to binary image
BW = im2bw(img,0.4); %// 0.4 as binary thresehold worked for this specific image
%// Get area and pixel-list stats
stats = regionprops(BW,'Area');
stats2 = regionprops(BW,'PixelIdxList');
s1 = struct2array(stats);
[v1,v2,v3] = unique(s1);
num_colors = numel(v1);
%// Pixel values per channel for creating color codes
pix_per_ch = linspace(0,255,ceil(power(num_colors,1/3)));
%// Unique 3 color codes
all_color_codes = allcomb(pix_per_ch,pix_per_ch,pix_per_ch);
%// allcomb is a MATLAB File-exchange tool avaiialble at -
%// http://www.mathworks.in/matlabcentral/fileexchange/10064-allcomb
%// Unique 3 color codes for the number of shapes available
color_codes = all_color_codes(randi(size(all_color_codes,1),num_colors,1),:);
%// Sort these uniques colors based on their grayscale intensities
[~,ind]=sort(rgb2gray(uint8(permute(color_codes,[1 3 2]))));
sorted_color_codes = color_codes(ind,:);
%// Pre-allocate for the ouput image
out = uint8(255.*BW(:,:,ones(1,3)));
%// Assign each shape a unique color based on their areas
for k = 1:numel(stats)
ind1 = stats2(k).PixelIdxList;
indx = bsxfun(#plus,ind1,[0:2].*size(img,1)*size(img,2));
color_code = sorted_color_codes(v3(k),:);
color_code_ext = color_code(ones(1,numel(ind1)),:);
out(indx) = color_code_ext;
end
%// Display input, output results
figure,
subplot(211),imshow(img),
title('Input Image')
subplot(212),imshow(out),
title('Output Image (Brighter colors represent larger shapes)')
Output -