Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

ORB FAST non-maximal suppression

For the code segment at https://github.com/Itseez/opencv/blob/master/modules/features2d/src/fast.cpp#L59

Why take K=patternSize/2 and N = patternSize + K + 1 ?

patternSize = 16 for this case, because we are using FAST-9_16 and there are 16 pixels around the circle of radius 3