UXDE dot Net

Chroma Based Road Tracking System Matlab Code

By -

For More Matlab Projects Visit last Posted Matlab Project Traffic Sign Recognition Using Matlab . 

Introduction 

  • Our Objective is to Detect Road tract using road edges especially when road signs or marking are not available.
  • Input is video.avi format first frames are extracted and then Chroma based segmentation is applied.
  • Figure Below Shown the Project model we have to implement this project according the Below Block Set.

 

Chroma Based Road Tracking

Scenarios when both edges of road are visible

  • First algorithm search for the detection of left and right edges of the road.
  • This is done by simply analyzing video frames and when there’s change in color behavior algorithm search for edges by drawing lines on road starting from the center and in the same way lines move towards the edges as shown in the figure below
  • Lines started from Initial Lines Pair and then lines are Expanding and finally when there is Convergence edges are found

 

 

road tracking

road tracking

 

Algorithm Result

Now the following image below shows result of above procedure.

Algorithm Detected Edges of Road Shown by Pink and Yellow Lines 

 

track recognized

When There’s No Road 

No Road

Results when only one side of road is visible

vipunmarkedroad_05

Result When Both Sides of Road Edges are Visible 

arrow shown road tracking

 

Templates 

Following images were used for concatenation

 

Used to Show Road is Left 

Left Arrow

 

Used to Show Road is Right Diagonal 

 

arrow2

Used to Show Road is Right 

 

arrow3

Used to Show Road is Left Diagonal 

 

arrow4

Used to Show Road Straight  

 

arrow5

Used to Show There’s No Road 

cross

Matlab Implementation

function road
arrow1=imread(‘arrow1.jpg’); arrow1=imresize(arrow1,[50 50]);
arrow2=imread(‘arrow2.jpg’); arrow2=imresize(arrow2,[50 50]);
arrow3=imread(‘arrow3.jpg’); arrow3=imresize(arrow3,[50 50]);
arrow4=imread(‘arrow4.jpg’); arrow4=imresize(arrow4,[50 50]);
arrow5=imread(‘arrow5.jpg’); arrow5=imresize(arrow5,[50 50]);
cross=imread(‘cross.jpg’);      cross  =imresize(cross,[50 50]);
readerobj = mmreader(‘roadtest.avi’);
Frames = read(readerobj);
vidFrames = read(readerobj);
numFrames = get(readerobj, ‘numberOfFrames’);

r = readerobj.Height;
c = readerobj.Width;

for k = 1 : numFrames-1

mov(k).cdata = vidFrames(:,:,:,k);
a=mov(k).cdata;
z=mov(k).cdata;
for i=1:r
for j=1:c
if(a(i,j,1)>100&&a(i,j,2)>120&&a(i,j,3)>110&&a(i,j,1)<255&&a(i,j,2)<255&&a(i,j,3)<255) if(a(i,j,1)>120&&a(i,j,2)>190&&a(i,j,3)>120&&a(i,j,1)<160&&a(i,j,2)<255&&a(i,j,3)<150) z(i,j,1)=255; z(i,j,2)=255; z(i,j,3)=255; else z(i,j,1)=0; z(i,j,2)=0; z(i,j,3)=0; end else z(i,j,1)=255; z(i,j,2)=255; z(i,j,3)=255; end end end z=z(:,:,1); check=0; if(z(r,c/2)==0&&z(r-2,c/2)==0) for i=1:1:r-10 if(z(i,1)&&z(i+1,1)&&z(i+2,1)&&z(i+4,1)&&z(i+5,1)==255&&z(i+10,1)==255) x=i; end if(z(i,c)&&z(i+1,c)&&z(i+2,c)&&z(i+4,c)&&z(i+5,c)==255&&z(i+10,c)==255) y=i; end end if(x>=160&&y>=160)
if(x==y||x==y+2)
a(120:169,120:169,:)=arrow3;
check=1;
elseif(x<y) a(120:169,120:169,:)=arrow4; check=1; elseif(x>y)
a(120:169,120:169,:)=arrow2;
check=1;
end

end
if(check==0)
a(120:169,120:169,:)=arrow5;
end
else
a(120:169,120:169,:)=cross;
end
mov(k).cdata=a;
vidFrames(:,:,:,k)=mov(k).cdata;
end
implay(Frames);
implay(vidFrames);

How To See Output 

Just play these two input and output videos to see output.

Turn Left

Source Code

Like , share this post on Facebook , Twitter by using left moving Social Sharing block and follow us on Facebook Page , Twitter and do comment and enter your email. After you have done you will automatically get source code in your mail. Note : This will be auto generated mail you can’t get until you follow above method.

 

Farheen Bibi

You can find Farheen on , and .

23 Comments to Chroma Based Road Tracking System Matlab Code

  1. this is so cool, can’t wait to get my hands on this. look forward to studying more of this! this is the answer to tonnes of my questions!

  2. I was wondering if you have a implementation of chroma based color similarity , i am doin a project on the following paper and have completed the whole code except for the color similarity part , the paper i am refrerring to is “www.ijcaonline.org/volume15/number2/pxc3872565.pdf”. can u help me out with the color part , i can mail u the rest of the code if u need

Leave a Reply