US 9,807,972 B1
Vision system with leg detection
Mark A. Foresman, Houston, TX (US); and Bradley J. Prevost, Pearland, TX (US)
Assigned to Technologies Holdings Corp., Houston, TX (US)
Filed by Technologies Holdings Corp., Houston, TX (US)
Filed on Aug. 17, 2016, as Appl. No. 15/239,477.
Int. Cl. G06K 9/00 (2006.01); A01J 5/007 (2006.01); A01J 5/017 (2006.01); H04N 13/02 (2006.01); G06T 7/00 (2017.01); G06T 7/60 (2017.01); G06T 1/00 (2006.01)
CPC A01J 5/007 (2013.01) [A01J 5/017 (2013.01); G06T 1/0014 (2013.01); G06T 7/0081 (2013.01); G06T 7/60 (2013.01); H04N 13/0203 (2013.01); G06T 2207/10004 (2013.01)] 20 Claims
OG exemplary drawing
 
13. A leg detection method comprising:
obtaining a three-dimensional (3D) image of a rearview of a dairy livestock in a stall, wherein each pixel of the 3D image is associated with a depth value;
identifying one or more regions within the 3D image comprising depth values greater than a depth value threshold;
applying a thigh gap detection rule set to the one or more regions to identify a thigh gap region among the one or more regions, wherein the thigh gap region comprises a space between hind legs of the dairy livestock;
demarcating an access region within the thigh gap region, wherein:
the access region comprises a first vertical edge and a second vertical edge defining a width of the access region;
the width of the access region corresponds with a dimension of the access region between the hind legs of the dairy livestock;
reducing the width of the access region by shifting the first vertical edge and the second vertical edge, wherein shifting the first vertical edge and the second vertical edge comprises:
shifting the first vertical edge toward the second vertical edge; and
shifting the second vertical edge toward the first vertical edge; and
determining position information for the first vertical edge and the second vertical edge of the access region.