Local feature descriptor extracting apparatus, method for extracting local feature descriptor, and program

• US 9,805,282 B2
• Filed: 09/11/2012
• Issued: 10/31/2017
• Est. Priority Date: 11/18/2011
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Mase, Ryota, Iwamoto, Kota
• Primary Examiner(s): Shah, Utpal
• Application Number:
  US14/358,664
• Publication Number:
  US 20140301647A1
• Time in Patent Office: 1,876 Days
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]

Abstract

The size of a feature descriptor is reduced, with the accuracy of object identification maintained. A local feature descriptor extracting apparatus includes a feature point detecting unit configured to detect a plurality of feature points in an image and output feature point information that is information on each of the feature points, a feature point selecting unit configured to select the predetermined number of feature points from the detected plurality of feature points in order of decreasing importance based on the feature point information, and a local feature descriptor generating unit configured to generate a local feature descriptor that is a feature descriptor in a local region for each of the selected feature points.

Claims

1. A local feature descriptor extracting apparatus comprising:

a computer configured to perform

determining a detection range of feature points in an image,

detecting a plurality of feature points in the image within the determined detection range and output feature point information that is information on each of the feature points, the feature point information including scale information indicative of a scale of each feature point;

selecting a plurality of feature points from the detected plurality of feature points in an order based on the scale information included in the feature point information;

repeating said determining, detecting, and selecting until a number of the feature points selected from the detected plurality of feature points becomes equal to or larger than a predetermined number, and

generating a local feature descriptor that is a feature descriptor in a local region for each of the selected feature points; and

a memory storing the local feature descriptor for each of the selected features points.

2. The local feature descriptor extracting apparatus according to claim 1, wherein the computer

is configured to classify the detected plurality of feature points into a plurality of groups based on the feature point information;

and

select at least one feature point from each of the groups in order to select the predetermined number of feature points.

3. The local feature descriptor extracting apparatus according to claim 1, wherein the computer is configured to receive the specified-number of pieces of information that is information used to determine the predetermined number, and determine the predetermined number based on the specified-number of pieces of information.

4. The local feature descriptor extracting apparatus according to claim 1, wherein the computer is configured to further detect feature points when the number of the feature points selected from the detected plurality of feature points is less than the predetermined number.

5. A method for extracting a local feature descriptor, the method comprising executing on a computer:

determining a detection range of feature points in an image;

detecting a plurality of feature points in the image within the determined detection range;

outputting feature point information that is information on each of the feature points, the feature point information including scale information indicative of a scale of each feature point;

selecting a plurality of feature points from the detected plurality of feature points in an order based on the scale information included in the feature point information;

repeating said determining, detecting, and selecting until a number of the feature points selected from the detected plurality of feature points becomes equal to or larger than a predetermined number;

generating a local feature descriptor that is a feature descriptor in a local region for each of the selected feature points; and

storing the local feature descriptor for each of the selected features points in a memory.

6. A computer-readable non-transitory storage medium storing a program for causing a computer to implement:

a function of determining a detection range of feature points in an image;

a function of detecting a plurality of feature points in the image within the determined detection range;

a function of outputting feature point information that is information on each of the feature points, the feature point information including scale information indicative of a scale of each feature point;

a function of selecting a plurality of feature points from the detected plurality of feature points in an order based on the scale information included in the feature point information;

a function of repeating said determining, detecting, and selecting until a number of the feature points selected from the detected plurality of feature points becomes equal to or larger than a predetermined number;

a function of generating a local feature descriptor that is a feature descriptor in a local region for each of the selected feature points; and

a function of storing the local feature descriptor for each of the selected features points in a memory.