Method, apparatus, and system for a vertex-based evaluation of polygon similarity

Patent metadata

Field	Value
Publication number	US-10339669-B2
Application number	US-201715683367-A
Country	US
Kind code	B2
Filing date	Aug 22, 2017
Priority date	Aug 22, 2017
Publication date	Jul 2, 2019
Grant date	Jul 2, 2019

Abstract

An approach is provided for a vertex-based evaluation of polygon similarity. The approach, for instance, involves processing, by a computer vision system, an image to generate a first set of vertices of a first polygon representing an object depicted in the image. The approach also involves for each vertex in the first set of vertices, determining a closest vertex in a second set of vertices of a second polygon, and determining a distance between said each vertex in the first set of vertices and the closest vertex in the second set of vertices. The approach further involves calculating a polygon similarity of the first polygon with respect to the second polygon based on a total of the distance determined for said each vertex in the first set of vertices normalized to a number of vertices in the first set of vertices.

First claim

What is claimed is:

1. A computer-implemented method for evaluating polygon similarity using a computer vision system comprising:
processing, by the computer vision system, an image to generate a first set of vertices of a first polygon representing an object depicted in the image;
for each vertex in the first set of vertices, determining a closest vertex in a second set of vertices of a second polygon, and determining a distance between said each vertex in the first set of vertices and the closest vertex in the second set of vertices;
calculating a polygon similarity of the first polygon with respect to the second polygon based on a total of the distance determined for said each vertex in the first set of vertices normalized to a number of vertices in the first set of vertices; and
transmitting the polygon similarity over a network to a mapping platform,
wherein the mapping platform processes the polygon similarity to localize a vehicle within a geographic area.

2. The method of claim 1 ,
wherein the image was captured by a camera sensor of the vehicle.

3. The method of claim 1 , further comprising:
for each vertex in the second set of vertices, determining a closest vertex in the first set of vertices, and determining another distance between said each vertex in the second set of vertices and the closest vertex in the first set of vertices; and
calculating a polygon similarity of the second polygon with respect to the first polygon based on another total of the another distance determined for said each vertex in the second set of vertices normalized to another number of vertices in the second set of vertices.

4. The method of claim 3 , further comprising:
generating an asymmetric polygon similarity as a pair comprising the polygon similarity of the first polygon with respect to the second polygon and the polygon similarity of the second polygon with respect to the first polygon.

5. The method of claim 3 , further comprising:
generating a symmetric polygon similarity by averaging the polygon similarity of the first polygon with respect to the second polygon and the polygon similarity of the second polygon with respect to the first polygon.

6. The method of claim 1 , wherein the distance for said each vertex is based on a Euclidean distance, a city-block distance, a chessboard distance, or a combination thereof.

7. The method of claim 1 , wherein the first polygon and the second polygon are N-dimensional polygons, and wherein N is greater than or equal to two.

8. An apparatus for evaluating polygon similarity using a computer vision system comprising:
at least one processor; and
at least one memory including computer program code for one or more programs,
the at least one memory and the computer program code configured to, within the at least one processor, cause the apparatus to perform at least the following,
process, by the computer vision system, an image to generate a first set of vertices of a first polygon representing an object depicted in the image;
for each vertex in the first set of vertices, determine a closest vertex in a second set of vertices of a second polygon, and determining a distance between said each vertex in the first set of vertices and the closest vertex in the second set of vertices;
calculate a polygon similarity of the first polygon with respect to the second polygon based on a total of the distance determined for said each vertex in the first set of vertices normalized to a number of vertices in the first set of vertices; and
transmit the polygon similarity over a network to a mapping platform,
wherein the mapping platform processes the polygon similarity to localize a vehicle within a geographic area.

9. The apparatus of claim 8 ,
wherein the image was captured by a camera sensor of the vehicle.

10. The apparatus of claim 8 , wherein the apparatus is further caused to:
for each vertex in the second set of vertices, determine a closest vertex in the first set of vertices, and determining another distance between said each vertex in the second set of vertices and the closest vertex in the first set of vertices; and
calculate a polygon similarity of the second polygon with respect to the first polygon based on another total of the another distance determined for said each vertex in the second set of vertices normalized to another number of vertices in the second set of vertices.

11. The apparatus of claim 10 , wherein the apparatus is further caused to:
generate an asymmetric polygon similarity as a pair comprising the polygon similarity of the first polygon with respect to the second polygon and the polygon similarity of the second polygon with respect to the first polygon.

12. The apparatus of claim 10 , wherein the apparatus is further caused to:
generate a symmetric polygon similarity by averaging the polygon similarity of the first polygon with respect to the second polygon and the polygon similarity of the second polygon with respect to the first polygon.

13. The apparatus of claim 8 , wherein the distance for said each vertex is based on a Euclidean distance, a city-block distance, a chessboard distance, or a combination thereof.

14. The apparatus of claim 8 , wherein the first polygon and the second polygon are N-dimensional polygons, and wherein N is greater than or equal to two.

15. A non-transitory computer-readable storage medium for evaluating polygon similarity using a computer vision system, carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to perform:
processing, by the computer vision system, an image to generate a first set of vertices of a first polygon representing an object depicted in the image;
for each vertex in the first set of vertices, determining a closest vertex in a second set of vertices of a second polygon, and determining a distance between said each vertex in the first set of vertices and the closest vertex in the second set of vertices;
calculating a polygon similarity of the first polygon with respect to the second polygon based on a total of the distance determined for said each vertex in the first set of vertices normalized to a number of vertices in the first set of vertices; and
transmitting the polygon similarity over a network to a mapping platform,
wherein the mapping platform processes the polygon similarity to localize a vehicle within a geographic area.

16. The storage medium of claim 15 ,
wherein the image was captured by a camera sensor of the vehicle.

17. The storage medium of claim 15 , further comprising:
for each vertex in the second set of vertices, determining a closest vertex in the first set of vertices, and determining another distance between said each vertex in the second set of vertices and the closest vertex in the first set of vertices; and
calculating a polygon similarity of the second polygon with respect to the first polygon based on another total of the another distance determined for said each vertex in the second set of vertices normalized to another number of vertices in the second set of vertices.

18. The storage medium of claim 17 , further comprising:
generating an asymmetric polygon similarity as a pair comprising the polygon similarity of the first polygon with respect to the second polygon and the polygon similarity of the second polygon with respect to the first polygon.

19. The storage medium of claim 17 , further comprising:
generating a symmetric polygon similarity by averaging the polygon similarity of the

Assignees

• Here Global Bv

Inventors

• Kwant Richard
• Mittal Anish
• Lawlor David

Classifications

• G06T7/75 Primary

  involving models · CPC title

• G06T7/74 Primary

  involving reference images or patches · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06V10/752

  Contour matching · CPC title

• G06T2207/10028

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