Extract color map from a video ?
4 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Hi,
I try to follow this steps that I see in Matlab conference: https://www.mathworks.com/content/dam/mathworks/mathworks-dot-com/company/events/conferences/matlab-conference-australia/2017/proceedings/detecting-moving-objects-in-aerial-imagery-captured-from-unmanned-aerial-vehicles.pdf
And there I try to extract some points from a video using "detectSURFFeatures", for this case I use rgb2gray. But after all process, I get a modified image, named with '481x641xsingle' proprieties, but to use "foreground = step(foregroundDetector, videoFrame);" I need to transform it in '480x640x3xsingle', but I can't extract the color map from the video. How can I do that?
there is my code:
v = vision.VideoFileReader('C:\Users\rafae\Desktop\DRONE desafio street car.mp4');
%%Create Video Player
videoPlayer = vision.VideoPlayer;
fgPlayer = vision.VideoPlayer;
%%Create Foreground Detector (Background Subtraction)
foregroundDetector = vision.ForegroundDetector('NumGaussians', 3,'NumTrainingFrames', 50);
for i = 1:30
vidFrame = step(v);
I2 = rgb2gray(vidFrame);
point2 = detectSURFFeatures(I2);
[features2,valid_points2] = extractFeatures(I2,point2);
if(rem(i,2)==0)
if(rem(i,2)==0)
vidFrame = step(v);
I1=rgb2gray(vidFrame);
point1=detectSURFFeatures(I1);
[features1,valid_points1] = extractFeatures(I1,point1);
% imshow(I1); hold on;
% plot(point1.selectStrongest(10));
else
vidFrame = step(v);
I2=rgb2gray(vidFrame);
point2=detectSURFFeatures(I2);
[features2,valid_points2] = extractFeatures(I2,point2);
% imshow(I2); hold on;
% plot(point2.selectStrongest(10));
end
indexPairs = matchFeatures(features1,features2);
matchedPoints1 = valid_points1(indexPairs(:,1),:);
matchedPoints2 = valid_points2(indexPairs(:,2),:);
%figure; showMatchedFeatures(I1,I2,matchedPoints1,matchedPoints2);
pointTracker = vision.PointTracker;
movingPoints = matchedPoints2.Location;
fixedPoints = matchedPoints1.Location;
tform = fitgeotrans(movingPoints,fixedPoints,'projective');
B = imwarp(I2,tform);
%frameDifferences = diff(framesWithWhiteBlobs);
ind2gray
videoFrame = step(B); %here is my error
else
videoFrame = step(v);
end
foreground = step(foregroundDetector,videoFrame);
end
0 Kommentare
Antworten (0)
Siehe auch
Kategorien
Mehr zu Convert Image Type finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!