US 11,861,804 B1
Systems and method for smooth segmentation
Sukhraj Singh, Mandi (IN); Nitish Puri, Delhi (IN); and Michael Kohnen, Heitersheim (DE)
Assigned to MAKO Surgical Corp., Weston, FL (US)
Filed by MAKO Surgical Corp., Weston, FL (US)
Filed on Dec. 28, 2020, as Appl. No. 17/134,745.
Claims priority of provisional application 62/957,899, filed on Jan. 7, 2020.
Int. Cl. G06T 19/20 (2011.01); G06T 17/20 (2006.01)
CPC G06T 19/20 (2013.01) [G06T 17/20 (2013.01); G06T 2207/10081 (2013.01); G06T 2219/2024 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A surface-mesh smoothing method, comprising:
receiving an input surface mesh, the input surface mesh comprising a plurality of vertices;
identifying a plurality of reference vectors;
for each of the plurality of reference vectors, identifying a set of artifact vertices from the plurality of vertices of input surface mesh by:
calculating normalized angles between the reference vector and a plurality of normal vectors, the plurality of normal vectors associated with a plurality of faces defined in the input surface mesh; and
defining a vertex of the plurality of vertices of the input surface mesh as an artifact vertex if the normalized angles associated with a set of the faces adjacent the vertex are different by more than a threshold amount;
aggregating the plurality of sets of artifact vertices associated with the plurality of reference vectors to define a master set of artifact vertices;
calculating a weighted value for each vertex of the plurality of vertices in the input surface mesh, wherein the said weighted value is based on a normalized distance of the vertex to a nearest artifact vertex of the master set of artifact vertices; and
applying a smoothing algorithm to the input surface mesh, wherein the weighted values are used to adjust the smoothing algorithm to obtain a smoothed output surface mesh.