matlab - Motion vectors calculation -

i working on following code:

filename = 'c:\li_walk.avi'; hvidreader = vision.videofilereader(filename, 'imagecolorspace', 'rgb','videooutputdatatype', 'single'); hopticalflow = vision.opticalflow('outputvalue', 'horizontal , vertical components in complex form', 'referenceframedelay', 3); hmean1 = vision.mean; hmean2 = vision.mean('runningmean', true); hmedianfilt = vision.medianfilter; hclose = vision.morphologicalclose('neighborhood', strel('line',5,45)); hblob = vision.blobanalysis('centroidoutputport', false, 'areaoutputport', true, 'boundingboxoutputport', true, 'outputdatatype', 'double','minimumblobarea', 250, 'maximumblobarea', 3600, 'maximumcount', 80); herode = vision.morphologicalerode('neighborhood', strel('square',2)); hshapeins1 = vision.shapeinserter('bordercolor', 'custom', 'custombordercolor', [0 1 0]); hshapeins2 = vision.shapeinserter( 'shape','lines', 'bordercolor', 'custom','custombordercolor', [255 255 0]); htextins = vision.textinserter('text', '%4d', 'location',  [1 1],'color', [1 1 1], 'fontsize', 12); sz = get(0,'screensize'); pos = [20 sz(4)-300 200 200]; hvideo1 = vision.videoplayer('name','original video','position',pos); pos(1) = pos(1)+220; % move next viewer right hvideo2 = vision.videoplayer('name','motion vector','position',pos); pos(1) = pos(1)+220; hvideo3 = vision.videoplayer('name','thresholded video','position',pos); pos(1) = pos(1)+220; hvideo4 = vision.videoplayer('name','results','position',pos); % initialize variables used in plotting motion vectors. linerow   =  22; firsttime = true; motionvecgain  = 20; borderoffset   = 5; decimfactorrow = 5; decimfactorcol = 5; while ~isdone(hvidreader)  % stop when end of file reached     frame  = step(hvidreader);  % read input video frame     grayframe = rgb2gray(frame);     ofvectors = step(hopticalflow, grayframe);   % estimate optical flow     % optical flow vectors stored complex numbers. compute     % magnitude squared later used thresholding.     y1 = ofvectors .* conj(ofvectors);     % compute velocity threshold matrix of complex velocities.     vel_th = 0.5 * step(hmean2, step(hmean1, y1));     % threshold image , filter remove speckle noise.     segmentedobjects = step(hmedianfilt, y1 >= vel_th);     % thin-out parts of road , fill holes in blobs.     segmentedobjects = step(hclose, step(herode, segmentedobjects));     % estimate area , bounding box of blobs.     [area, bbox] = step(hblob, segmentedobjects);     % select boxes inside roi (below white line).     idx = bbox(:,1) > linerow;     % based on blob sizes, filter out objects can not cars.     % when ratio between area of blob , area of     % bounding box above 0.4 (40%), classify car.     ratio = zeros(length(idx), 1);     ratio(idx) = single(area(idx,1))./single(bbox(idx,3).*bbox(idx,4));     ratiob = ratio > 0.4;     count = int32(sum(ratiob));    % number of cars     bbox(~ratiob, :) = int32(-1);     % draw bounding boxes around tracked cars.     y2 = step(hshapeins1, frame, bbox);     % display number of cars tracked , white line showing roi.     y2(22:23,:,:)   = 1;   % white line.     y2(1:15,1:30,:) = 0;   % background displaying count     result = step(htextins, y2, count);     % generate coordinates plotting motion vectors.     if firsttime       [r c] = size(ofvectors);            % height , width in pixels       rv = borderoffset:decimfactorrow:(r-borderoffset);       cv = borderoffset:decimfactorcol:(c-borderoffset);       [y x] = meshgrid(cv,rv);       firsttime = false;       sumu=0;       sumv=0;     end  grayframe = rgb2gray(frame); [ra ca na] = size(grayframe); ofvectors = step(hopticalflow, grayframe);   % estimate optical flow  ua = real(ofvectors); ia = ofvectors - ua; va = ia/complex(0,1);   sumu=ua+sumu; sumv=va+sumv; [xa ya]=meshgrid(1:1:ca,ra:-1:1);       % calculate , draw motion vectors.     tmp = ofvectors(rv,cv) .* motionvecgain;     lines = [y(:), x(:), y(:) + real(tmp(:)), x(:) + imag(tmp(:))];     motionvectors = step(hshapeins2, frame, lines);     % display results     step(hvideo1, frame);            % original video     step(hvideo2, motionvectors);    % video motion vectors     step(hvideo3, segmentedobjects); % thresholded video     step(hvideo4, result);           % video bounding boxes      quiver(xa,ya,sumu,sumv) end release(hvidreader); 

please me understand following statements of above code:

ua = real(ofvectors); ia = ofvectors - ua; va = ia/complex(0,1); 

these horizontal (ua) , vertical (va) components of motion vectors. real part of (ofvectors) be? please me in understanding code segment

when object hopticalflow constructed in third line of code, outputvalue property set 'horizontal , vertical components in complex form' has effect when apply step command hopticalflow , image (frame), not magnitudes of flowvectors, complex numbers represent these planar flow vectors. compact way command return information. once have complex numbers in ofvectors, output of step command, command

ua = real(ofvectors); 

stores horizontal component of each vector in ua. after command

ia = ofvectors - ua; 

is executed, ia contains imaginary (i.e., vertical components of flow vectors) because real parts in ua subtracted complex numbers in ofvectors. however, need rid of imaginary units in ia, divide 0+1i. command

va = ia/complex(0,1); 

does.