Algorithm 2. Computing the Position of Occluded People via Shadows

Input:a represents which side of the user their shadow is located in, hf is the position of the head  joint of Hf in the RGB image, R is the search region, C is the binary image obtained by  background subtraction. Output: The position pb of Hb.  1: $\mathrm{S}\leftarrow \varnothing$ (stores points on the upper contour of Hb)  2: if a = 0 then  3:   i1 = 0, i2 = hf.x − dx/2  4: else  5:   i1 = hf.x + dx/2, i2 = W  6: for each i = i1 to i2 do  7:   for each j = H to 0 do  8:     if C(i, j) = 1 then  9:       Add the point R(i, j) to S;  10:      Break;  11: Use the least squares method to fit the points in S to a line, and map it onto the plane G, designated as st;  12: Compute the intersection point of st and o1pf, marked as pb;  13: Return position pb of Hb