Color invariant image fusion of visible and thermal infrared video

• US 7,620,265 B1
• Filed: 04/12/2005
• Issued: 11/17/2009
• Est. Priority Date: 04/12/2004
• Status: Active Grant

• Current Assignee: Equinox Corp. (Oracle Corporation)
• Original Assignee: Equinox Corp. (Oracle Corporation)
• Inventors: Socolinsky, Diego A., Eveland, Christopher K., Wolff, Lawrence B.
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): Krasnic; Bernard
• Application Number:
  US11/103,640
• Time in Patent Office: 1,680 Days
• Field of Search: 382/276, 382/284, 382/254
• US Class Current: 382/276
• CPC Class Codes: G06T 11/001 Texturing; Colouring; Generation of texture or colour inpainting G06T5/77
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/20221 Image fusion; Image merging
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction

Abstract

A methodology for forming a composite color image fusion from a set of N gray level images takes advantage of the natural decomposition of color spaces into 2-D chromaticity planes and 1-D intensity. This is applied to the color fusion of thermal infrared and reflective domain (e.g., visible) images whereby chromaticity representation of this fusion is invariant to changes in reflective illumination.

Claims

1. A method for creating a color composite image fusion, comprising:

providing one or more reflective input images and one or more thermal infrared input images, each image being defined by a plurality of gray scale pixel values; and

employing a processor to

     1) map each of said gray scale pixel values in said one or more reflective input images only to a corresponding value in an intensity space (V) of an HSV color space, said HSV color space including a hue (H), saturation (S) chromaticity space and said intensity (V) space;

     2) map each of said gray scale pixel values in said one or more thermal infrared images to a corresponding value in said HSV color space; and

     3) generate a composite image from the values in said intensity space and said chromaticity space.

2. The method of claim 1, wherein said one or more reflective input images consist of a single visible image and said one or more thermal infrared input images consist of a single LWIR image.

3. The method of claim 1, wherein a degree to which the pixel values of said one or more thermal infrared input images influence the saturation values can be adjusted.

4. The method of claim 3, wherein a degree to which the pixel values of said one or more thermal infrared input images influence the intensity values can be adjusted.

5. The method of claim 1, wherein said mapping steps are carried out by said processor accessing a lookup table.

6. The method of claim 1, wherein each of said input images are preprocessed by said processor using an automatic gain control function.

7. A processing apparatus for implementing image fusion, comprising:

an input for receiving one or more reflective input images and one or more thermal infrared input images, each of said images including a plurality of gray scale pixel values;

a memory for storing said images; and

an image processor for combining said one or more reflective input images and said one or more thermal infrared input images into a third fused image,

said processor being programmed to;

1) map each of said gray scale pixel values in said one or more reflective input images only to a corresponding value in an intensity space (V) of an HSV color space, said HSV color space including a hue (H), saturation (S) chromaticity space and said intensity (V) space;

2) map each of said gray scale pixel values in said one or more thermal infrared input images to a corresponding value in said HSV color space; and

3) generate said third fused image from the values in said intensity space and said chromaticity space.

8. The apparatus of claim 7, wherein said one or more reflective input images consist of a single visible image and said one or more thermal infrared input images consist of a single LWIR image.

9. The apparatus of claim 7, wherein said processor is further programmed to enable a degree to which the pixel values of said one or more thermal infrared input images influence the saturation values to be adjusted.

10. The apparatus of claim 9, wherein said processor is further programmed to enable a degree to which the pixel values of said one or more thermal infrared input images influence the intensity values to be adjusted.

11. The apparatus of claim 7, wherein a lookup table is provided in said memory that is employed by said processor to map pixel values in said input images to values in said color space.

12. The apparatus of claim 7, wherein said processor is further programmed to preprocess each of said input images using an automatic gain control function.