SPECTRAL SCENE SIMPLIFICATION THROUGH BACKGROUND SUBTRACTION

• US 20140133753A1
• Filed: 11/09/2012
• Published: 05/15/2014
• Est. Priority Date: 11/09/2012
• Status: Abandoned Application

• Current Assignee: GE Aviation Systems LLC (GE Aerospace)
• Original Assignee: GE Aviation Systems LLC (GE Aerospace)
• Inventors: Sebastian, Thomas Baby, Buehler, Eric Daniel, Occhipinti, Benjamin Thomas, Kuczynski, Konrad Robert
• Application Number:
  US13/673,052
• Publication Number:
  US 20140133753A1
• Time in Patent Office: Days
• US Class Current: 382/173
• CPC Class Codes: G06T 2207/10036 Multispectral image; Hyperspectral image
• CPC Class Codes: G06T 2207/20224 Image subtraction
• CPC Class Codes: G06T 2207/30181 Earth observation
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 20/194 using hyperspectral data, i.e. more or other wavelengths than RGB
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats

Abstract

A method of removing stationary objects from hyperspectral imagery, includes among other things, collecting a series of hyperspectral images of a target scene; determining at least one first hyperspectral image having no moving or new objects in the target scene; selecting the at least one first hyperspectral image; determining at least one second hyperspectral image having moving objects in the target scene; and subtracting the at least one first hyperspectral image from the at least one second hyperspectral image to create a background-subtracted hyperspectral image.

Claims

1. A method of removing stationary objects from at least one hyperspectral image, the method comprising:

collecting a series of hyperspectral images of a target scene;

determining at least one first hyperspectral image having no moving objects in the target scene;

selecting the at least one first hyperspectral image;

determining at least one second hyperspectral image having moving objects in the target scene; and

subtracting the at least one first hyperspectral image from the at least one second hyperspectral image to create a background-subtracted hyperspectral image.

2. The method of claim 1 further comprising the step of displaying the background-subtracted hyperspectral image.

3. The method of claim 1 further comprising the step of storing the background-subtracted hyperspectral image.

4. The method of claim 1 wherein if the absolute difference between the averaged signatures of the at least one first hyperspectral image and the signatures of the at least one second hyperspectral image in the subtracting step is less than a predetermined threshold value, the value of the difference is set to zero.

5. The method of claim 1 further comprising the step of calibrating of the at least one first hyperspectral image and the at least one second hyperspectral image to account for differences in illumination of the target scene.

6. The method of claim 1 wherein the determining and selecting steps are done manually.

7. The method of claim 1 wherein the determining and selecting steps are done automatically.

8. The method of claim 1 wherein the selecting step further comprises selecting at least two first hyperspectral images and averaging signatures for the at least two first hyperspectral images.

9. The method of claim 1 wherein the step of determining the at least one first hyperspectral image having no moving objects in the target scene is done by comparing the at least one first hyperspectral image to the series of hyperspectral images of a target scene.