Calculate Car speed from a video stream

3 vues (au cours des 30 derniers jours)
Chadi St
Chadi St le 11 Jan 2019
Hi , i'm trying to calculate an estimation of the car speed using the following code , However it gives me the same speed for every car:
foregroundDetector = vision.ForegroundDetector('NumGaussians', 3, ...
'NumTrainingFrames', 50);
V=VideoReader('visiontraffic.avi');
videoReader = vision.VideoFileReader('visiontraffic.avi');
for i = 1:150
frame = step(videoReader); % read the next video frame
foreground = step(foregroundDetector, frame);
end
imwrite(frame,'D:\referenceimage.jpg','jpg');
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
referenceimage=imread('D:\referenceimage.jpg');
X=zeros(2,121);
Y=zeros(2,121);
Z=zeros;
while ~isDone(videoReader)
frame = step(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);
%-----------------------SPEED ---------------------------%
frame2=((im2double(frame))-(im2double(referenceimage)));
frame1=im2bw(frame2,0.1);
[Labelimage]=bwlabeln(frame1);
stats=regionprops(Labelimage,'basic');
BB=stats.BoundingBox;
i=2; %fblasst for
X(i)=BB(1);
Y(i)=BB(2);
Dist=((X(i)-X(i-1))^2+(Y(i)-Y(i-1))^2)^(1/2);
Z(i)=Dist;
M=median(Z);
%disp(M);
%clc;
%disp('speed=')
Speed=((M)*(120/8))/(4);
%disp(Speed);
%SPEED = M ???????????
i = i + 1;
SE = strel('disk',6);
frame3=imclose(frame1,SE);
step(videoReader);
pause(0.05);
%if(i==121) end; ??
%-----------------------SPEED ---------------------------%
% Detect the connected components with the specified minimum area, and
% compute their bounding boxes
blobAnalysis = vision.BlobAnalysis('BoundingBoxOutputPort', true, ...
'AreaOutputPort', true, 'CentroidOutputPort', true, ...
'MinimumBlobArea', 150);
%bbox = step(blobAnalysis, filteredForeground);
[areas, centroids, 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
%ICI
%disp(centroids); //show...
%disp(size(centroids));//show....
numCars = size(bbox, 1); %cars ...
numCars_str = ['car number:', num2str(size(bbox, 1))];
speed_str = [num2str(Speed),'KM/h'];
result = insertText(result,[10,10],numCars_str, 'BoxOpacity', 1, ...
'FontSize', 14);
for i=1:size(bbox, 1)
result = insertText(result,[centroids(i,1),centroids(i,2)], speed_str, 'BoxOpacity', 1, ...
'FontSize', 20);
end;
step(videoPlayer, result); % display the results
end;
release(videoReader); % close the video file
  2 commentaires
Ameni chetouane
Ameni chetouane le 6 Sep 2019
I have the same error, could you please help me
AKASH KUMAR SWAIN
AKASH KUMAR SWAIN le 4 Sep 2022
this code is detecting multiple objects falsely
please help me with this

Connectez-vous pour commenter.

Réponses (1)

Sandhiya CSE
Sandhiya CSE le 15 Mai 2020
Can someone send the input video for this code

Catégories

En savoir plus sur Tracking and Motion Estimation dans Help Center et File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by