Clever Geek Handbook

Find edge based on normals

I have a 480 * 640 depth image and I got the normals (480 * 640 * 3 matrix) of each pixel from this depth image. Does anyone know how I can find an advantage based on the usual information?

Thank you so much!

0


source to share


1 answer


An intuitive definition of an edge in a depth image is where the surface normal is facing away from the viewer. Assuming the viewing direction [0 0 -1]

(in the XY plane), any normal with an almost vanishing component z

can be characterized as an edge.

e = abs( depth(:,:,3) ) < 1e-3; %// a nice starting point


You need to set a threshold based on your data.

After this, you may consider applying some non-maximal suppression or other morphological cleaning operations.

+2


source






More articles:


All Articles