ROTATION INVARIANT OBJECT DETECTION

• US 20170323149A1
• Filed: 05/05/2016
• Published: 11/09/2017
• Est. Priority Date: 05/05/2016
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Harary, Sivan, Marder, Mattias
• Application Number:
  US15/146,905
• Publication Number:
  US 20170323149A1
• Time in Patent Office: Days
• CPC Class Codes: G06T 7/579 from motion
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/757 Matching configurations of points or features
• CPC Class Codes: G06V 10/759 Region-based matching
• CPC Class Codes: G06V 2201/11 Technique with transformation invariance effect
• CPC Class Codes: G06V 30/194 References adjustable by an adaptive method, e.g. learning

Abstract

A method, including receiving a two-dimensional (2D) image of a three-dimensional (3D) object recorded at a first angle of rotation of the object, and identifying, in the 2D image, a set of image descriptors, each of the image descriptors including an image keypoint and one or more image features. The set of image descriptors are compared against sets of template descriptors for respective previously captured 2D images, each of the template descriptors comprising a template keypoint and one or more template features. Using a threshold, a given set of template descriptors matching the set of image descriptors are identified, the given set of template descriptors corresponding to a given previously captured 2D image of the 3D object recorded at a second angle of rotation of the object. Any of the image descriptors not in the given set of the template descriptors are added to the given set of template descriptors.

Claims

1. A method, comprising:

receiving a two-dimensional image of a three-dimensional object recorded at a first angle of rotation of the object;

identifying, in the two-dimensional image, a set of image descriptors, each of the image descriptors comprising an image keypoint and one or more image features;

comparing the set of image descriptors against a plurality of sets of template descriptors for respective previously captured two-dimensional images, each of the template descriptors comprising a template keypoint and one or more template features;

identifying, based on a defined threshold, a given set of template descriptors matching the set of image descriptors, the given set of template descriptors corresponding to a given previously captured two-dimensional image of the three-dimensional object recorded at a second angle of rotation of the object; and

adding, to the given set of template descriptors, any of the image descriptors not in the given set of the of template descriptors.

2. The method according to claim 1, and further comprising adding the set of image descriptors to the sets of template descriptors upon failing to identify a given set of template descriptors matching the set of image descriptors.

3. The method according to claim 1, wherein the template keypoints in set of template descriptors comprise a first coordinate system, wherein image keypoints in the set of image descriptors comprise a second coordinate system, and wherein adding the any of the image descriptors not in the given set of the of template descriptors to the given set of template descriptors comprises performing a geometric transformation to transform the image keypoints in any of the image keypoints to the first coordinate system.

4. The method according to claim 1, wherein identifying a given set of template descriptors matching the set of image descriptors comprises matching, based on the defined threshold, a subset of the given set of template descriptors to a subset of the set of image descriptors.

5. The method according to claim 4, wherein the subset of the set of image descriptors comprises a first subset of image descriptors, wherein the given set of template descriptors comprises a first given set of template descriptors, wherein the given previously captured image comprises a first given previously captured image, and further comprising:

matching, based on the defined threshold, a subset of a second given set of template descriptors to a second subset of the set of image descriptors, the second given set of template descriptors corresponding to a second given previously captured two-dimensional image of the three-dimensional object recorded at a third angle of rotation of the object, adding, to the first given set of template descriptors, any of the template descriptors in the second given set of template descriptors not in the first given set of template descriptors and any of the image descriptors not in the first given set of template descriptors, and deleting the second given set of template descriptors.

6. The method according to claim 1, wherein the defined threshold comprises a confidence level.

7. An apparatus, comprising:

a storage device configured to store multiple sets of template descriptors for respective previously captured two-dimensional images, each of the template descriptors comprising a template keypoint and one or more template features; and

a processor configured;

to receive a two-dimensional image of a three-dimensional object recorded at a first angle of rotation of the object,

to identify, in the two-dimensional image, a set of image descriptors, each of the image descriptors comprising an image keypoint and one or more image features,

to compare the set of image descriptors against the multiple sets of template descriptors,

to identify, based on a defined threshold, a given set of template descriptors matching the set of image descriptors, the given set of template descriptors corresponding to a given previously captured two-dimensional image of the three-dimensional object recorded at a second angle of rotation of the object, and

to add, to the given set of template descriptors, any of the image descriptors not in the given set of the of template descriptors.

8. The apparatus according to claim 7, wherein the processor is further configured to add the set of image descriptors to the sets of template descriptors upon failing to identify a given set of template descriptors matching the set of image descriptors.

9. The apparatus according to claim 7, wherein the template keypoints in set of template descriptors comprise a first coordinate system, wherein image keypoints in the set of image descriptors comprise a second coordinate system, and wherein the processor is further configured to add the any of the image descriptors not in the given set of the of template descriptors to the given set of template descriptors by performing a geometric transformation to transform the image keypoints in the any of the image keypoints to the first coordinate system.

10. The apparatus according to claim 7, wherein the processor is configured to identify a given set of template descriptors matching the set of image descriptors by matching, based on the defined threshold, a subset of the given set of template descriptors to a subset of the set of image descriptors.

11. The apparatus according to claim 10, wherein the subset of the set of image descriptors comprises a first subset of image descriptors, wherein the given set of template descriptors comprises a first given set of template descriptors, wherein the given previously captured image comprises a first given previously captured image, and wherein the processor is further configured:

to match, based on the defined threshold, a subset of a second given set of template descriptors to a second subset of the set of image descriptors, the second given set of template descriptors corresponding to a second given previously captured two-dimensional image of the three-dimensional object recorded at a third angle of rotation of the object, to add, to the first given set of template descriptors, any of the template descriptors in the second given set of template descriptors not in the first given set of template descriptors and any of the image descriptors not in the first given set of template descriptors, and to delete the second given set of template descriptors.

12. The apparatus according to claim 7, wherein the defined threshold comprises a confidence level.

13. A computer program product, the computer program product comprising:

a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer readable program code configured to receive a two-dimensional image of a three-dimensional object recorded at a first angle of rotation of the object;

computer readable program code configured to identify, in the two-dimensional image, a set of image descriptors, each of the image descriptors comprising an image keypoint and one or more image features;

computer readable program code configured to compare the set of image descriptors against a plurality of sets of template descriptors for respective previously captured two-dimensional images, each of the template descriptors comprising a template keypoint and one or more template features;

computer readable program code configured to identify, based on a defined threshold, a given set of template descriptors matching the set of image descriptors, the given set of template descriptors corresponding to a given previously captured two-dimensional image of the three-dimensional object recorded at a second angle of rotation of the object; and

computer readable program code configured to add, to the given set of template descriptors, any of the image descriptors not in the given set of the of template descriptors.

14. The computer program product according to claim 13, and further comprising computer readable program code configured to add the set of image descriptors to the sets of template descriptors upon failing to identify a given set of template descriptors matching the set of image descriptors.

15. The computer program product according to claim 13, wherein the template keypoints in set of template descriptors comprise a first coordinate system, wherein image keypoints in the set of image descriptors comprise a second coordinate system, and wherein the computer readable program code is configured to add the any of the image descriptors not in the given set of the of template descriptors to the given set of template descriptors by performing a geometric transformation to transform the image keypoints in the any of the image keypoints to the first coordinate system.

16. The computer program product according to claim 13, wherein the computer readable program code is configured to identify a given set of template descriptors matching the set of image descriptors by matching, based on the defined threshold, a subset of the given set of template descriptors to a subset of the set of image descriptors.

17. The computer program product according to claim 16, wherein the subset of the set of image descriptors comprises a first subset of image descriptors, wherein the given set of template descriptors comprises a first given set of template descriptors, wherein the given previously captured image comprises a first given previously captured image, and further comprising:

computer readable program code configured to match, based on the defined threshold, a subset of a second given set of template descriptors to a second subset of the set of image descriptors, the second given set of template descriptors corresponding to a second given previously captured two-dimensional image of the three-dimensional object recorded at a third angle of rotation of the object, computer readable program code configured to add, to the first given set of template descriptors, any of the template descriptors in the second given set of template descriptors not in the first given set of template descriptors and any of the image descriptors not in the first given set of template descriptors, and computer readable program code configured to delete the second given set of template descriptors.

18. The computer program product according to claim 13, wherein the defined threshold comprises a confidence level.