Method of identifying a tracked object for use in processing hyperspectral data

• US 9,122,929 B2
• Filed: 08/17/2012
• Issued: 09/01/2015
• Est. Priority Date: 08/17/2012
• Status: Expired due to Fees

• Current Assignee: GE Aviation Systems LLC (GE Aerospace)
• Original Assignee: GE Aviation Systems LLC (GE Aerospace)
• Inventors: Buehler, Eric Daniel, Occhipinti, Benjamin Thomas, Kuczynski, Konrad Robert
• Primary Examiner(s): Akhavannik, Hadi
• Application Number:
  US13/588,568
• Publication Number:
  US 20140050352A1
• Time in Patent Office: 1,110 Days
• Field of Search: 382/100, 382103-107, 382/276, 382293-294, 382/154, 382/285, 345/419, 348169-172, 348 42- 60, 700/1, 707/600, 707/687
• US Class Current: 1/1
• CPC Class Codes: G01J 3/02 Details
• CPC Class Codes: G01N 21/359 using near infrared light
• CPC Class Codes: G06V 20/13 Satellite images

Abstract

The invention relates a method of identifying a tracked object that has a known database of hyperspectral and spatial information. The method associates an identifier with the tracked object; selects a parameter associated with the hyperspectral or spatial information of the tracked object; detects a deviation in the selected parameter; compares the deviation with the database; and if the deviation exceeds a predetermined threshold, assigns a new identifier to the tracked object, and if the deviation does not exceed the predetermined threshold, continues tracking the tracked object.

Claims

1. A method of identifying a tracked object comprising:

tracking an object using at least one image sensor, the tracked object corresponding to a predetermined identifier associated with hyperspectral and spatial information maintained in at least one database;

selecting at least one parameter associated with the hyperspectral or spatial information of the tracked object;

detecting a deviation in the selected at least one parameter;

comparing the deviation with the hyperspectral and spatial information associated with predetermined identifier; and

in response to the deviation exceeding a predetermined threshold, assigning a new identifier to the tracked object.

2. The method of claim 1, further comprising updating the predetermined identifier based on the deviation in the at least one parameter.

3. The method of claim 1, further comprising identifying the deviation in the selected at least one parameter as a target event.

4. The method of claim 1, wherein the at least one parameter includes at least one of color, contrast, brightness, shape, velocity, direction, size, or location.

5. The method of claim 1, wherein the comparing the deviation with the hyperspectral and spatial information associated with predetermined identifier includes using at least one of Spectral Angle Mapping, Spectral Information Divergence, Zero Mean Differential Angle, Mahalanobis Distance, or Bhattacharyya Distance.

6. The method of claim 1, further comprising continuing tracking the object, in response to the deviation not exceeding the predetermined threshold.

7. The method of claim 3, further comprising including the target event in a timeline of target events associated with at least one of the at least one parameter, tracked object, or predetermined identifier.

8. A method of identifying a tracked object, comprising:

acquiring a set of hyperspectral and spatial image data;

generating a set of hyperspectral image frames based on processing the set of hyperspectral and spatial image data;

selecting a set of candidate targets, corresponding to predetermined reference templates, included in a subset of the hyperspectral image frames;

tracking the set of candidate targets in the set of hyperspectral image frames;

generating a matching value by comparing the set of candidate targets and a set of predetermined reference templates;

determining that the matching value satisfies a predetermined threshold;

in response to the matching value satisfying the predetermined threshold, generating a new reference template based on the set of candidate targets.

9. The method of claim 8, further comprising:

determining that the matching value does not satisfy the predetermined threshold; and

continuing tracking the set of candidate targets, in response to the matching value not satisfying the predetermined threshold.

10. The method of claim 8, wherein the generating the set of hyperspectral image frames includes processing the set of hyperspectral and spatial image data via at least one of noise filtering, corner detection, image registration, homography, or frame-to-frame alignment.

11. The method of claim 8, wherein the selecting the set of candidate targets includes identifying a set of moving objects in the set of hyperspectral image frames, and selecting the set of candidate targets from the set of moving objects.

12. The method of claim 8, wherein the comparing the set of candidate targets and the set of predetermined reference templates, includes comparing a first set of spectral signatures included in the set of candidate targets with a second set of spectral signatures included in the set of predetermined reference templates.

13. The method of claim 12, wherein the comparing the first set of spectral signatures included in the set of candidate targets with the second set of spectral signatures included in the set of predetermined reference templates, includes determining a first distribution of the first set of spectral signatures in the set of candidate targets and a second distribution of the second set of set of spectral signatures in the set of predetermined reference templates, and comparing the first and second distributions.

14. The method of claim 8, further comprising associating a deviation event indicator with the set of candidate targets, in response to the matching value satisfying the predetermined threshold.

15. The method of claim 14, further comprising adding the deviation event indicator to a timeline including a set of indicators.