Patient monitor and method

Patent metadata

Field	Value
Publication number	US-9420254-B2
Application number	US-201314394704-A
Country	US
Kind code	B2
Filing date	Apr 17, 2013
Priority date	Apr 19, 2012
Publication date	Aug 16, 2016
Grant date	Aug 16, 2016

Abstract

A patient monitoring system can include stereoscopic cameras connected to a computer which includes a 3D position determination module operable to process stereoscopic images of a patient to identify 3D positions of a plurality of points on the surface of an imaged patient. A target model store can store a target model including data identifying 3D positions of a set of vertices of a triangulated 3D wire mesh model and connectivity indicative of connections between vertices. A matching module can identify the triangles in a target model surface stored in the target model store closest to points identified by the 3D position determination module and calculate a rigid transformation which minimizes point to plane distances between the identified points and the planes containing the triangles of the target model surface identified as being closest to those points.

First claim

The invention claimed is:

1. A computer implemented method of determining a rigid transformation for matching a position of an object with a position of a target object represented by a target model comprising data identifying 3D positions of a set of vertices of a triangulated 3D wire mesh and connectivity indicative of connections between vertices, the method comprising:
obtaining stereoscopic images of an object;
processing the stereoscopic images utilizing a computer to identify 3D positions of a plurality of points on a surface of the imaged object;
generating an array identifying, for a regular grid of points in 3D space, the vertices of the target model closest to those grid points by:
for each vertex in the target model, using 3D co-ordinates associated with the vertex of the target model to identify grid points of the regular 3D grid corresponding to corners of a cube that contains the location of the vertex, determining a distance between the vertex and the positions corresponding to the identified grid points, and determining whether said identified grid points are associated with data indicative of the grid points being closer to another vertex in the target model and if not associating said grid points with data identifying the vertex and the distance between the vertex and said grid points; and
traversing the regular 3D grid in each of the directions corresponding to the axes of the regular 3D grid and determining when traversing the regular 3D grid, whether a vertex associated with a neighboring grid point on the regular 3D grid in a direction of traversal is closer to the position associated with a current grid point than any vertex previously associated with that grid point and if so associating the grid point with data identifying the vertex associated with the neighboring grid point;

identifying, for each point on the surface of the imaged object, grid points of the regular 3D grid corresponding to the corners of a cube that contains the point on the surface of the imaged object;
utilizing the vertices associated with the identified grid points by the array to identify triangles in the target model surface closest to each of said points on the surface of the imaged object;
utilizing the computer to select a set of the identified 3D positions on the surface of the imaged object as points to be utilized to determine a rigid transformation for matching the position of the object with the position of the target object on the basis of the determined distances between the identified 3D positions and vertices of the target model identified as being closest to said positions; and
utilizing the computer to calculate a rigid transformation which minimizes point to plane distances between the identified set of 3D positions and the planes containing the triangles of the target model surface identified as being closest to said positions.

2. The computer implemented method of claim 1 , wherein selecting a set of the identified 3D positions on the surface of the imaged object and calculating a rigid transformation which minimizes point to plane distances between the identified set of 3D positions and the planes containing the triangles of the target model surface identified as being closest to those positions comprises for a number of iterations:
determining threshold values to be utilized for a current iteration;
selecting a set of the identified 3D positions on the surface of the imaged object as points to be utilized to determine a rigid transformation for matching the position of the object with the position of the target object on the basis of a comparison of the distances between the identified 3D positions and vertices of the target model identified as being closest to said positions with a threshold value;
calculating a rigid transformation which minimizes point to plane distances between the identified set of 3D positions and the planes containing the triangles of the target model surface identified as being closest to those positions;
wherein the rigid transformation for matching the position of the object with the position of the target object comprises a sum of the transformations determined at each iteration.

3. The computer implemented method of claim 2 , wherein: determining threshold values to be utilized for a current iteration comprises:
setting an initial threshold value for a first iteration; and
determining a threshold value for use in a subsequent iteration on a basis of average distances between the identified 3D positions and vertices of the target model identified as being closest to said positions.

4. The computer implemented method of claim 1 , wherein selecting a set of the identified 3D positions on the surface of the imaged object as points to be utilized to determine a rigid transformation for matching the position of the object with the position of the target object further comprises:
filtering the selected set of identified 3D positions on the surface of the imaged object to be utilized to calculate a rigid transformation on a basis of a relative orientation of the object at a point and an orientation of a triangle in the target model surface identified as being closest to that point, wherein the orientation of the object at the point is determined by generating a model of the object and calculating an average normal vector of triangles in the generated model that contain the point.

5. The computer implemented method of claim 1 , wherein selecting a set of the identified 3D positions on the surface of the imaged object as points to be utilized to determine a rigid transformation for matching the position of the object with the position of the target object further comprises:
filtering the selected set of identified 3D positions on the surface of the imaged object to be utilized to calculate a rigid transformation to remove any points determined to project to a same location prior to calculating a rigid transformation which minimizes point to plane distances between the filtered identified set of 3D positions and the planes containing the triangles of the target model surface identified as being closest to those points.

6. The computer implemented method of claim 1 , wherein calculating a rigid transformation which minimizes point to plane distances between the identified set of 3D positions on the surface of the imaged object and the planes containing the triangles of the target model surface identified as being closest to those positions comprises:
determining for each of said positions, projections of said positions to the planes containing the triangles of the target model surface identified as being closest to those positions;
determining a translation which aligns a centroid of the positions identified as being locations on the surface of the object with a centroid of projections of said positions to identified planes containing the triangles of the target model surface identified as being closest to those positions; and
determining a rotation which minimizes point to plane distances between the identified set of 3D positions on the surface of the imaged object and the planes containing the triangles of the target model surface identified as being closest to those positions after the determined translation has been applied.

7. The computer implemented method of claim 1 , wherein utilizing the vertices associated with the identified grid points of the regular 3D grid by the array to identify the triangle in the target model surface closest to a point comprises:
determining of the vertices associated with the identified grid points of the regular 3D grid, the vertex of the target model surface closest to the point on the surface of the imaged object currently being processed;
determining if any of the vertices directly con

Assignees

• Vision Rt Ltd

Inventors

• Meir Ivan

Classifications

• G06T2219/2004

  Aligning objects, relative positioning of parts · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T2207/10072

  Tomographic images · CPC title

• G06T7/0046

  Physics · mapped topic

• H04N13/0011 Primary

  Electricity · mapped topic