Dedan Kimathi University,5th year project.Automatic Traffic Data Collection and Analysis Using Optical Camera and Sensor Image Recognition

Automated traffic data collection Algorithm,Godwin Micheni 5th Year,Civil Engineering, DeKUT

% PART A
%linking camera with rasperry pi
%creating a camera board object
clear rpi;
rpi= raspi();
cam = cameraboard(rpi,'Resolution','640x480');
%PART B
% code to start the camera and to capture image
Clear all
Close all
clc
%camera integration
webcam list
ans ='webcam 1';
     'webcam 2';
cam= webcam(2);
%from the given list webcam is choosen
button=input('would you like to open the camera?(y\n)!','s');
if strcmp(button,'v')
disp(button)
end
%on pressing the v button the camera and sensor are actuated to take photo
im = snapshot(cam);
preview (cam);
%PART C
%image filtering
I= imread('im');
BW = imread('im');
mask = BW(1:256,1:256);
f = @(x) imadjust(x,[],[],0.3);
img1 = roifilt2(I,mask,f);
figure,imshow(img1)
imwrite(img1,'C:\Users\GODWIN\Desktop\Project\1.jpg');
%PART D
%calling comparitory images in the database
L = list_files(path_fn);
% get information about given path_fn
L = dir (path_fn);
% ... ignore . and ..
L = L(3: length (L));
% ... turn into a cell array
L = struct2cell(L);
% ... and only keep the filenames .
L = L(1,:);
fn (X,y:width,height) = read_images(path_fn)
% get files for a given path
folder = list_files(path_fn);
% initialize the empty return values
X=[];
y=[];
width=0;
height=0;
% start counting with class index 1
classIdx = 1;
% for each file ...
for i=1: length (folder)
subject = folder{i};
% ... get files in this subdir
images = list_files([path_fn , filesep , subject]);
% ... ignore a file or empty folder
if ( length(images) == 0)
continue;
end
% ... for each image
for j=1: length (images)
% ... get the absolute path
filename = [path_fn , filesep , subject , filesep , images{j}];
% ... read the image
T = double(imread(filename));
% ... get the image information
[height width channels] = size (T);
% ... and grayscale if it ' s a color image
if (channels == 3)
T = 0.2989 * T(:,:,1) + 0.5870* T(:,:,2) + 0.1140 * T(:,:,3);
end
% ... reshape into a row vector and append to data matrix
X = [X; reshape (T,1,width*height)];
% ... append the corresponding class to the class vector
y = [y, classIdx];
end
% ... increase the class index
classIdx = classIdx + 1;
end
% ... for - each folder .
fn [W, mu] = pca(X, y, k)
[n,d] = size (X);
mu = mean (X);
Xm = X - repmat(mu, rows(X), 1);
if (n>d)
C = Xm'*Xm;
[W,D] = eig (C);
% sort eigenvalues and eigenvectors
[D, i] = sort ( diag (D), ' descend ' );
W = W(:,i);
% keep k components
W = W(:,1:k);
else
C = 'Xm*Xm ';
% C = cov ( Xm ') ;
[W,D] = eig (C);
% multiply with data matrix
W = Xm'*W;
% normalize eigenvectors
for i=1:n
W(:,i) = W(:,i)/ norm (W(:,i));
end
% sort eigenvalues and eigenvectors
[D, i] = sort ( diag (D), ' descend ' );
W = W(:,i);
% keep k components
W = W(:,1:k);
end
fn Y = project(W, X, mu)
if ( nargin <3)
Y = X*W;
else
Y = (X-repmat(mu, rows(X), 1))*W;
end
fn X = reconstruct(W, Y, mu)
if ( nargin <3)
X = Y * W';
else
X = Y * W' + repmat(mu, rows(Y), 1);
end
% load function files from subfolders aswell
addpath (genpath ( ' . ' ));
% read images
[X,y,w,h] = read_images('C:\Users\GODWIN\Desktop\Project\vehicle_database');
% n - number of samples
% d - dimensionality
[n,d] = size (X);
% perform a full pca
[W,mu] = pca(X,y,n);
fn X = normalize(X, l, h)
minX = min (X(:));
maxX = max (X(:));
% % Normalize to [0...1].
X = X - minX;
X = X ./ (maxX - minX);
% % Scale to [ low ... high ].
X = X .* (h-l);
X = X + l;
fn Y = toGrayscale(X, width , height)
Y = normalize(X, 0, 255);
if ( nargin ==3)
Y = reshape (Y, height , width);
end
Y = uint8(Y);
% plot eigenvehicles
figure ; hold on;
title ( ' Eigenvehicles ( AT & T Vehicledatabase ) ' );
for i=1: min (16,n)
subplot (4,4,i);
eigenface_i = toGrayscale(W(:,i), w, h);
imshow(eigenface_i);
colormap ( jet (256));
title ( sprintf ( ' Eigenvehicle #% i ' , i));
end
% plot eigenvehicles reconstruction
steps = 10:20: min (n,320);
Q = X(1,:); % first image to reconstruct
figure ; hold on;
title ( ' Reconstruction ( AT & T Vehicledatabase ) ' );
for i=1: min (16, length (steps))
subplot (4,4,i);
numEvs = steps(i);
P = project(W(:,1:numEvs), X(1,:), mu);
R = reconstruct(W(:,1:numEvs),P,mu);
comp = toGrayscale(R, w, h);
imshow(comp);
title ( sprintf ( ' % i Eigenvectors ' , numEvs));
end
fn [W, mu] = lda(X,y,k)
% dimension of observation
[n,d] = size (X);
% number of classes
labels = unique(y);
C = length (labels);
% allocate scatter matrices
Sw = zeros (d,d);
Sb = zeros (d,d);
% total mean
mu = mean (X);
% calculate scatter matrices
for i = 1:C
Xi = X( find (y == labels(i)) ,:);
% samples for current class
n = rows(Xi);
mu_i = mean (Xi);
% mean vector for current class
Xi = Xi - repmat(mu_i , n, 1);
Sw = Sw + Xi*Xi;
Sb = Sb + n * (mui - mu)*(mui - mu);
end
% solve general eigenvalue problem
[W, D] = eig (Sb, Sw);
% sort eigenvectors
[D, i] = sort ( diag (D), ' descend ' );
W = W(:,i);
% keep at most ( c -1) eigenvectors
W = W(:,1:k);
fn [W, mu] = fishervehicles(X,y,k)
% number of samples
N = rows(X);
% number of classes
labels = unique(y);
c = length (labels);
if ( nargin < 3)
k = c-1;
end
k = min (k,(c-1));
% get ( N - c ) principal components
[Wpca , mu] = pca(X, y, (N-c));
[Wlda , mu_lda] = lda(project(Wpca , X, mu), y, k);
W = Wpca*Wlda;
% load function files from subfolders aswell
addpath (genpath ( ' . ' ));
% for plotting
db_name = ' lorry vehicledatabase ' ;
% read images
[X,y,w,h] = read_images( 'C:\Users\GODWIN\Desktop\Project\vehicledatabase' );
% n - number of samples
% d - dimensionality
[n,d] = size (X);
% get the unique classes
c = unique(y);
% compute the fishervehicles
[W,mu] = fisherfaces(X,y);
% plot fishervehicle
figure ; hold on;
title ( sprintf ( ' Fishervehicle % s ' , db_name));
for i=1: min (16, length (c) -1)
subplot (4,4,i);
fishervehicle_i = toGrayscale(W(:,i), w, h);
imshow(fishervehicle_i);
colormap ( jet (256));
title ( sprintf ( ' Fishervehicle #% i ' , i));
end
steps = 1: min (16, length (c) -1);
Q = X(1,:); % first image to reconstruct
figure ; hold on;
title ( sprintf ( ' Fishervehicle Reconstruction % s ' , db_name));
for i=1: min (16, length (steps))
subplot (4,4,i);
numEv = steps(i);
P = project(W(:,numEv), X(1,:), mu);
R = reconstruct(W(:,numEv),P,mu);
comp = toGrayscale(R, w, h);
imshow(comp);
title ( sprintf ( ' Fishervehicle #% i ' , numEv));
end
ELSEIF strcmp(button,'n')
disp(button)
disp('obtain traffic analysis output in the spreadsheet')

Valid object handles must be supplied
==end

%Published with MATLAB® 7.12

Nice, clean, well written code. Good work.

Thank you

Add spacing after every commented line .

Thank you for your comment @kenju254.I am working on that now.

@chenigodwin Could you add a Whitespace after each comment .

This is awesome, I'm looking forward to seeing the output of the code

Thank you guys,am looking into your recommendations.