Resize Frame for Optical Flow

I have problem with changing the resolution of the video file. There is a problem with optical flow if the frame size have been manipulated in any way this gives me error. There are two options either change the resolution of the video at the beginning or somehow how change the frame size in a way that optical flow will work. This is a small prototype for detecting micro-expressions and I will want to add a cascade object to detect nose, mouth and eyes in further development therefore I need solution that will work for individual regions without necessary setting optical flow individually for those regions especially that a bounding box does not have a fixed size and it will displace itself slightly from frame to frame. Here is my code so far, the error is that it is exceeding matrix dimensions.

    close all
    clear
    clc

    %Create a cascade face detector object.
    faceDetector = vision.CascadeObjectDetector();

    %Create video object. Input Video File and set some properties / Read video       frames and audio samples from video file
    vidObj =     vision.VideoFileReader('MEXTest.mp4','ImageColorSpace','Intensity','VideoOutputDataType','uint8');

    %Convert and scale input image to specified output data type (This need to be   changed for future releases of Matlab
    converter = vision.ImageDataTypeConverter;

    %Estimate object velocities
    opticalFlow = vision.OpticalFlow('ReferenceFrameDelay', 1);

    %Form of velocity output
    opticalFlow.OutputValue = 'Horizontal and vertical components in complex form';

    %Draw rectangles, lines, polygons, or circles on an image (This need to be changed for future releases of Matlab
    shapeInserter = vision.ShapeInserter('Shape','Lines','BorderColor','Custom','CustomBorderColor', 255);

    %Play video or display image
    vidPlayer = vision.VideoPlayer('Name','Motion Vector');

    while ~isDone(vidObj);
        %set individual frames
        frame = step(vidObj);

        %resize frame for faster computation
        fraRes = imresize(frame,0.5);

        %set bounding box on the frame
        fbbox = step(faceDetector,fraRes);

        %Annotate truecolor or grayscale image or video stream / set bbox properites
        addfbbox = insertObjectAnnotation(fraRes,'rectangle',fbbox,'Face');
        %imshow(addfbbox,'border','tight');

        if size(fbbox,1) == 0 %if there is no face detected
            disp('Face not detected'); %display this
            pause(0.5) %and pasue the programme
        else if size(fbbox,1) > 1 %if there is more than one face detected
                disp('Too many Faces') %display this
            else %or for one face follow on
                I = imcrop(fraRes,fbbox); 
                %imshow(I);

                %Convert the image to single precision, then compute optical flow for the video. Generate coordinate points and draw lines to indicate flow. Display results.
                im = step(converter,I);
                of = step(opticalFlow,im);
                lines = videooptflowlines(of, 20);
                if ~isempty(lines)
                    out = step(shapeInserter,im,lines);
                    step(vidPlayer,out);
                end
            end
        end
    end
    release(vidPlayer);
    release(VidObj);

Answer 1

[Kamil Stepien]

UPDATE: I went and edited the function for optical flow which creates lines and this sorts out the size issue however it is necessary to to input this manually for each input however there is a problem that I need to use release() method before making another step but non of the variables are allowed to be entered. Does anyone know how to create this release() method to make it work. Here is the updated code:

    faceDetector = vision.CascadeObjectDetector();
    faceDetector.MinSize = [150 150];

    vidRead = vision.VideoFileReader('MEXTest.mp4','ImageColorSpace','Intensity','VideoOutputDataType','uint8');
    convert = vision.ImageDataTypeConverter; 
    optFlo = vision.OpticalFlow('ReferenceFrameDelay', 1);
    optFlo.OutputValue = 'Horizontal and vertical components in complex form';
    shapeInserter = vision.ShapeInserter('Shape','Lines','BorderColor','Custom',  'CustomBorderColor', 255);

    while ~isDone(vidRead)
        frame = step(vidRead);
        fraRes = imresize(frame,0.3);
        fraSin = im2single(fraRes);

        bbox = step(faceDetector,fraSin);

        I = imcrop(fraSin, bbox); 

        im = step(convert, I); 
        of = step(optFlo, im); %I need to release something in here
        lines = optfloo(of, 50); %use videooptflowlines instead of (optfloo)
        out =  step(shapeInserter, im, lines); 
        imshow(out);
    end