FAST_CORNER_DETECTOR

Name

Purpose

This function will return a 2xn array of corner coordinates identified
in the provided greyscale image.

Parameters

image
A two-dimensional (m x n) array containing the greyscale image to be used
for feature/corner extraction.

Keywords

DIFFERENCE_THRESHOLD
An optional named variable containing the brightness threshold to
be used to determine whether a surrounding pixels is brighter than
or darker than the candidate corner pixel (default value is 50).
CONTIGUOUS_THRESHOLD
An optional named variable containg the number of contiguous pixels
that must appear in sequence in order for a candidate pixel to be
considered a corner pixel (default value is 12).
NON_MAXIMAL_SUPPRESSION
An optional keyword indicating whether non-maximal suppression
should be used to eliminate "clumping" of identified corner points.
CORNER_IMAGE
An optional named variable that will contain, upon return, a visualization
of the corner points (shown in red) laid upon the original image (the
returned value is a 3 x m x n color image array).
VERBOSE
An optional keyword indicating whether diagnostic information should
be displayed to the console during execution.

Return Value

This function returns a 2xn array containing the image coordinates of the
n corner points identified by the FAST detector.

Reference

E. Rosten and T. Drummond, "Machine learning for high-speed corner
detection,” in Computer Vision - ECCV 2006, A. Leonardis, H. Bischof,
and A. Pinz, eds., Lecture Notes in Computer Science 3951, pp. 430–443,
Springer Berlin / Heidelberg, 2006.

Modification History

Written by: Carl Salvaggio
Original Code: Sep 25, 2010

Disclaimer

This source code is provided "as is" and without warranties as to performance
or merchantability. The author and/or distributors of this source code may
have made statements about this source code. Any such statements do not
constitute warranties and shall not be relied on by the user in deciding
whether to use this source code.
This source code is provided without any express or implied warranties
whatsoever. Because of the diversity of conditions and hardware under which
this source code may be used, no warranty of fitness for a particular purpose
is offered. The user is advised to test the source code thoroughly before
relying on it. The user must assume the entire risk of using the source code.