質問

How to use matlab vision.ForegroundDetector with webcam instead of input video file.

hsrc = vision.VideoFileReader('viptraffic.avi','ImageColorSpace','Intensity','VideoOutputDataType','uint8');
hfg = vision.ForegroundDetector(...
       'NumTrainingFrames', 5, ... % 5 because of short video
       'InitialVariance', 30*30); % initial standard deviation of 30
hblob = vision.BlobAnalysis(...
       'CentroidOutputPort', false, 'AreaOutputPort', false, ...
       'BoundingBoxOutputPort', true, ...
       'MinimumBlobAreaSource', 'Property', 'MinimumBlobArea', 250);
hsi = vision.ShapeInserter('BorderColor','White');

hsnk = vision.VideoPlayer();
while ~isDone(hsrc)
     frame  = step(hsrc);
     fgMask = step(hfg, frame);
     bbox   = step(hblob, fgMask);
     out    = step(hsi, frame, bbox); % draw bounding boxes around cars
     step(hsnk, out); % view results in the video player
end
release(hsnk);
release(hsrc);
役に立ちましたか?

解決

If you have access to the Image Acquisition Toolbox, you could replace the first line with:

hsrc = imaq.VideoDevice('winvideo', 1, 'MJPG_640x480', ...
    'ReturnedColorSpace','grayscale', 'ReturnedDataType','uint8');

You will need to adjust the parameters according to the supported formats by your webcam. Just consult the documentation of the imaq.VideoDevice function.

Also replace the loop test by just while true since the video feed is always not done :)

ライセンス: CC-BY-SA帰属
所属していません StackOverflow
scroll top