Calculate optical flow using Lucas & Kanade. Fast, parallel code. Note that the window of integration can either be a hard square window of radius winN or it can be a soft 'gaussian' window with sigma winSig. In general the soft window should be more accurate. USAGE [Vx,Vy,reliab]=optFlowLk( I1, I2, winN, ... [winSig], [sigma], [thr], [show] ) INPUTS I1, I2 - input images to calculate flow between winN - window radius for hard window (=[] if winSig provided) winSig - [] sigma for soft 'gauss' window (=[] if winN provided) sigma - [1] amount to smooth by (may be 0) thr - [3e-6] ABSOLUTE reliability threshold (min eigenvalue) show - [0] figure to use for display (no display if == 0) OUTPUTS Vx, Vy - x,y components of flow [Vx>0->right, Vy>0->down] reliab - reliability of flow in given window (cornerness of window) EXAMPLE % create square + translated square (B) + rotated square (C) A=zeros(50,50); A(16:35,16:35)=1; B=zeros(50,50); B(17:36,17:36)=1; C=imrotate(A,5,'bil','crop'); optFlowLk( A, B, [], 2, 2, 3e-6, 1 ); optFlowLk( A, C, [], 2, 2, 3e-6, 2 ); % compare on stored real images (of mice) load optFlowData; [Vx,Vy,reliab] = optFlowLk( I5A, I5B, [], 4, 1.2, 3e-6, 1 ); [Vx,Vy,reliab] = optFlowCorr( I5A, I5B, 3, 5, 1.2, .01, 2 ); [Vx,Vy] = optFlowHorn( I5A, I5B, 2, 3 ); See also OPTFLOWHORN, OPTFLOWCORR