Depth image of a segment with low contrast
1 answer
This may not be the answer you were hoping for, but it might help you move a little forward. Since I only provide algorithmic hints, I will be using Matlab and not opencv.
Since this is not a normal intensity image, but rather a depth image, you must use the implied geometry of the scene. The main assumption that can help you here is that the hand rests on the surface . If you can estimate the equation of the surface, you can easily spot the hand.
[y x] = ndgrid( linspace(-1,1,size(img,1)), linspace(-1,1,size(img,2)) );
X = [reshape(x(101:140,141:180),[],1), reshape(y(101:140,141:180),[],1), ones(1600,1)];
srf=(X\reshape(img(101:140,141:180),[],1)); %// solving least-squares for the 40x40 central patch
aimg = img - x*srf(1) - y*srf(2) - srf(3); %// subtracting the recovered surface
Using a median filter to "clean up" it a little and apply a simple threshold
medfilt2(aimg,[3 3]) < -1.5
Yield
Not what you were hoping for, but I think this is a step forward;)
PS,
You can find work by Alpert, Galun, Nadler and Basri Detecting Weak Curved Edges in Noisy Images (ECCV2010) related to your problem.
+2
source to share