3D object verification system and method

Patent metadata

Field	Value
Publication number	US-12093363-B2
Application number	US-202217831644-A
Country	US
Kind code	B2
Filing date	Jun 3, 2022
Priority date	Jun 3, 2022
Publication date	Sep 17, 2024
Grant date	Sep 17, 2024

Abstract

The present disclosure provides a system and method for object verification. The method comprises obtaining sensor data, from one or more sensors, the sensor data including measurements of one or more physical properties of a given three-dimensional (3D) object, wherein the sensor data comprises a first measurement of the one or more physical properties from a first perspective and a second measurement of the one or more physical properties from a second perspective, the second perspective being different from the first perspective. The method further comprises comparing the sensor data with reference data, the reference data including measurements of one or more corresponding physical properties of a reference 3D object, and generating, based on the comparing, a verification signal indicating a determined match between the given 3D object and the reference 3D object.

First claim

The invention claimed is:

1. A system comprising:
memory storing reference data, the reference data including measurements of one or more physical properties of a reference 3D object; and
a processing unit coupled to the memory and configured to execute instructions to cause the system to:
obtain sensor data, from one or more sensors, the sensor data including measurements of one or more physical properties of a given three-dimensional (3D) object, wherein the sensor data comprises a first measurement of the one or more physical properties of the given 3D object from a first perspective and a second measurement of the one or more physical properties of the given 3D object from a second perspective, the second perspective being different from the first perspective;
compare the sensor data, comprising the first and second measurements, with the reference data; and
generate, based on the comparing, a verification signal indicating a determined match between the given 3D object and the reference 3D object.

2. The system of claim 1 , wherein the processing unit is further configured to execute instructions to cause the system to compare the sensor data with the reference data by:
combining the measurements of the one or more physical properties of the given 3D object to generate a candidate digital model of the given 3D object; and
comparing the candidate digital model of the given 3D object with the reference data comprising a reference digital model of the reference 3D object.

3. The system of claim 1 , wherein the processing unit is further configured to execute instructions to cause the system to compare the sensor data with the reference data by calculating differences between the sensor data and the reference data, and determining that the differences falls below a defined difference threshold.

4. The system of claim 3 , wherein the processing unit is further configured to execute instructions to cause the system to generate the verification signal indicating the determined match by:
determining, from the calculated differences, a confidence level of the determined match between the given 3D object and the reference 3D object; and
in response to determining that the confidence level matches or exceeds a defined confidence threshold, generating the verification signal.

5. The system of claim 4 , wherein the determined confidence level matches or exceeds a first confidence threshold associated with a first security level and falls below a second confidence threshold associated with a second security level, the defined confidence threshold being the first confidence threshold, and
the processing unit being further configured to generate the verification signal indicating the determined match for the given 3D object for the first security level and indicating no match for the given 3D object for the second security level.

6. The system of claim 1 , further comprising the one or more sensors configured to obtain the sensor data.

7. The system of claim 6 , wherein at least one of the one or more sensors is a camera, the processing unit being further configured to execute instructions to cause the system to obtain sensor data by:
obtaining, from the camera, at least two 2D images of the 3D object from the first and second perspectives between the camera and the given 3D object, wherein measurements of at least one of the one or more physical properties are captured in the at least two 2D images of the 3D object.

8. The system of claim 6 , wherein at least one of the one or more sensors is a LIDAR sensor and one of the one or more physical properties of the given 3D object is a 3D surface geometry or topology.

9. The system of claim 1 , wherein the processing unit is further configured to execute instructions to cause the system to generate, as the verification signal, an unlocking signal to unlock a physical lock, or an access signal to grant access to restricted software or website options.

10. A computer-implemented method comprising:
obtaining sensor data, from one or more sensors, the sensor data including measurements of one or more physical properties of a given three-dimensional (3D) object, wherein the sensor data comprises a first measurement of the one or more physical properties of the given 3D object from a first perspective and a second measurement of the one or more physical properties of the given 3D object from a second perspective, the second perspective being different from the first perspective;
comparing the sensor data with reference data, the sensor data comprising the first and second measurements, and the reference data including measurements of one or more corresponding physical properties of a reference 3D object; and
generating, based on the comparing, a verification signal indicating a determined match between the given 3D object and the reference 3D object.

11. The method of claim 10 , wherein comparing the sensor data with the reference data comprises:
combining the measurements of the one or more physical properties of the given 3D object to generate a candidate digital model of the given 3D object; and
comparing the candidate digital model of the given 3D object with the reference data comprising a reference digital model of the reference 3D object.

12. The method of claim 10 , wherein comparing the sensor data with the reference data comprises calculating differences between the sensor data and the reference data, and determining that the differences falls below a defined difference threshold.

13. The method of claim 12 , wherein generating the verification signal indicating the determined match further comprises:
Determining, from the calculated difference, a confidence level of matching between the given 3D object and the reference 3D object; and
in response to a determination that the confidence level equals or exceeds a defined confidence threshold, generating the verification signal.

14. The method of claim 13 , wherein the determined confidence level matches or exceeds a first confidence threshold associated with a first security level and falls below a second confidence threshold associated with a second security level, the defined confidence threshold being the first confidence threshold, and wherein the given 3D object is verified for the first security level and not verified for the second security level.

15. The method of claim 14 , wherein the given 3D object comprises a hologram, and each of the at least two 2D images of the 3D object includes a respective image of the hologram, a state of the hologram captured in each respective image being used to correlate to the respective perspective of the given 3D object in each 2D image.

16. The method of claim 10 , wherein at least one of the one or more sensors is a camera and wherein the sensor data includes at least two 2D images of the 3D object obtained from different perspectives between the camera and the given 3D object, and wherein measurements of at least one of the one or more physical properties are captured in the at least two 2D images of the 3D object.

17. The method of claim 10 , wherein the one or more physical properties of the given 3D object comprises one or more of color, size, microsurface detail, identifying marks, metallic-ness/nonmetallic-ness, and surface roughness.

18. The method of claim 10 , wherein the one or more physical properties comprises a material composition of the given 3D object based on light scattering from the given 3D object captured in the at least two 2D images of the given 3D object.

19. The me

Assignees

• Shopify Inc

Inventors

• Wade Jonathan
• Leroux Stephan
• Beauchamp Daniel
• Ngo Andrew

Classifications

• G01S7/4802

  using analysis of echo signal for target characterisation; Target signature; Target cross-section · CPC title

• G06F21/629 Primary

  to features or functions of an application · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title

• G06V2201/12

  Acquisition of 3D measurements of objects · CPC title

• G06V20/647

  by matching two-dimensional images to three-dimensional objects · CPC title