Method of tracking objects using hyperspectral imagery

• US 9,430,846 B2
• Filed: 04/19/2013
• Issued: 08/30/2016
• Est. Priority Date: 04/19/2013
• Status: Active Grant

• Current Assignee: GE Aviation Systems LLC (GE Aerospace)
• Original Assignee: GE Aviation Systems LLC (GE Aerospace)
• Inventors: Sebastian, Thomas Baby, Buehler, Eric Daniel, Lassini, Stefano Angelo Mario, Occhipinti, Benjamin Thomas, Kuczynski, Konrad Robert, Kelly, Richard Shawn, Schafer, Matthew James, Smith, Rebecca Jeanne
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): Torres, Jose M
• Application Number:
  US13/866,086
• Publication Number:
  US 20140314272A1
• Time in Patent Office: 1,229 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10036 Multispectral image; Hyperspectral image
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/254 involving subtraction of images

Abstract

A method of tracking motion of at least one object of a group of moving objects using hyperspectral imaging includes, among other things, obtaining a series of hyperspectral image frames; comparing each frame in the series to a template to determine changes in the image between frames; identifying a group of pixels in each frame associated with the changes; identifying changes as motion of the moving objects; correlating the pixel groups frame to frame to spatially determine at least one parameter of the motion of the objects; and correlating the pixel groups with a spectral reflectance profile associated with the at least one object wherein the track of the at least one object is distinguishable from the tracks of other moving objects.

Claims

1. A method of tracking motion of at least one object of a group of moving objects using hyperspectral imaging, comprising:

obtaining a series of hyperspectral image frames;

comparing frames in the series to a template to determine changes in the image between frames;

identifying a group of pixels in the frames associated with the changes;

identifying the changes as motion of the moving objects;

correlating the pixel groups frame-to-frame to spatially determine at least one parameter of the motion of the objects; and

correlating the pixel groups with a spectral reflectance profile associated with the at least one object, and distinguishably tracking, based on the spectral reflectance profile, the at least one object from the other moving objects.

2. The method of claim 1 wherein the correlating the pixel groups with the spectral reflectance profile is performed as the next step after the comparing.

3. The method of claim 1 wherein the correlating the pixel groups with a spectral reflectance profile is performed as the next step after the correlating the pixel groups frame-to-frame to spatially determine at least one parameter of the motion of the objects.

4. The method of claim 1 wherein the correlating the pixel groups with a spectral reflectance profile is performed as the next step after the comparing frames in the series to the template and as the next step after the correlating the pixel groups frame-to-frame to spatially determine at least one parameter of the motion of the object.

5. The method of claim 1 wherein correlating the pixel groups with a spectral reflectance profile, includes correlating the pixel groups with a spectral reflectance profile when the value of the at least one parameter of the motion of the objects is less than a predetermined threshold.

6. The method of claim 1 wherein the at least one parameter of the motion of the objects is velocity.

7. The method of claim 1 wherein the at least one parameter of the motion of the objects is acceleration.

8. The method of claim 1 wherein the spectral reflectance profile is stored in and retrieved from a database of spectral reflectance profiles.

9. The method of claim 1 wherein the spectral reflectance profile is derived from a group of pixels in the series of hyperspectral image frames.

10. A method of tracking motion of an object using hyperspectral imaging, comprising:

acquiring a set of hyperspectral image frames;

determining characteristics of the object by comparing a first frame in the set of hyperspectral image frames with a second frame in the set of hyperspectral image frames;

determining changes in the imagery based on comparing the set of frames and characteristics to a set of templates;

identifying a set of pixels in the set frames associated with the changes;

determining at least one spatial parameter of the motion of the object based on correlating the set of pixels across the set of frames;

correlating the set of pixels with a spectral reflectance profile; and

tracking the object based at least in part on the spectral reflectance profile.

11. The method of claim 10, wherein the characteristics include characteristics relating to calibration and alignment.

12. The method of claim 10, wherein the characteristics include characteristics relating to imaged objects in motion.