IP Library Granted Patent US 11,189,018
Granted Patent B2
US 11,189,018 · App. 16/616,555 · Granted Nov 30, 2021

Image generation device, image generation method, and storage medium on which program is stored

Inventor: Kenichiro Fukushi (Tokyo, JP)
Assignee: NEC CORPORATION
G06T5/50G06T5/002G06T5/20G06T11/001H04N5/247H04N5/265G06T2207/10048G06T2207/20221G06T2207/20224
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,189,018
App. No.
16/616,555
Granted
Nov 30, 2021
Kind
B2
Abstract

An image generation device according to an aspect of the present invention includes: at least one memory storing a set of instructions; and at least one processor configured to execute the set of instructions to: generate, from a first image in a first wavelength band and a second image in a second wavelength band different from the first wavelength band, a composite image containing a first frequency component based on the first image and a second frequency component based on the second image; and output the composite image.

Claims (63)

1. An image generation device comprising:

at least one memory storing a set of instructions; and

at least one processor configured to execute the set of instructions to:

generate, from a first image in a first wavelength band and a second image in a second wavelength band different from the first wavelength band, a composite image containing a first frequency component based on the first image and a second frequency component based on the second image output the composite image, wherein

the at least one processor is further configured to execute the set of instructions to:

perform noise suppression processing on a difference image between the first image and the composite image; and

add a noise-suppressed difference image to the composite image, the noise-suppressed difference image being generated by performing the noise suppression processing on the difference image.

2. The image generation device according to claim 1 , wherein

the at least one processor is further configured to execute the set of instructions to:

extract a texture of the second image; and

add a first texture image to the composite image into which the noise-suppressed difference image is incorporated by adding, the first texture image representing the extracted texture.

3. The image generation device according to claim 1 , wherein

the at least one processor is further configured to execute the set of instructions to:

separate a structure component from the second image; and

generate the composite image containing the first frequency component and a second frequency component based on the structure component of the second image.

4. The image generation device according to claim 3 , wherein

the at least one processor is further configured to execute the set of instructions to:

separate a texture component from the second image; and

generate the composite image into which a second texture image is incorporated by adding, the second texture image representing the separated texture component.

5. The image generation device according to claim 1 , wherein

the at least one processor is further configured to execute the set of instructions to:

separate a structure component from the first image; and

generate the composite image containing the first frequency component and the second frequency component, the first frequency component being based on the structure component of the first image.

6. The image generation device according to claim 1 , wherein

light in the first wavelength band includes visible light, and

light in the second wavelength band includes far-infrared light.

7. The image generation device according to claim 1 , wherein

the first frequency component is a component of the composite image in a spatial frequency band, and the second frequency component is a component of the composite image in a spatial frequency band including a spatial frequency higher in comparison with the spatial frequency band of the first frequency component.

8. An image generation system including the image generation device according to claim 1 , the system comprising:

a first image acquisition device capturing the first image;

a second image acquisition device capturing the second image; and

a display device, wherein

the at least one processor is further configured to execute the set of instructions to display the composite image on the display device.

9. An image generation method comprising:

generating, from a first image in a first wavelength band and a second image in a second wavelength band different from the first wavelength band, a composite image containing a first frequency component based on the first image and a second frequency component based on the second image;

performing noise suppression processing on a difference image between the first image and the composite image; and

adding a noise-suppressed difference image to the composite image, the noise-suppressed difference image being generated by performing the noise suppression processing on the difference image; and

outputting the composite image.

10. The image generation method according to claim 9 , further comprising:

extracting a texture of the second image; and

adding a first texture image to the composite image into which the noise-suppressed difference image is incorporated by adding, the first texture image representing the extracted texture.

11. The image generation method according to claim 9 , comprising:

separating a structure component from the second image; and

generating the composite image containing the first frequency component and a second frequency component based on the structure component of the second image.

12. The image generation method according to claim 11 , comprising:

separating a texture component from the second image; and

generating the composite image into which a second texture image is incorporated by adding, the second texture image representing the separated texture component.

13. The image generation method according to claim 9 , comprising:

separating a structure component from the first image; and

generating the composite image containing the first frequency component and the second frequency component, the first frequency component being based on the structure component of the first image.

14. The image generation method according to claim 9 , wherein

light in the first wavelength band includes visible light, and

light in the second wavelength band includes far-infrared light.

15. The image generation method according to claim 9 , wherein

the first frequency component is a component of the composite image in a spatial frequency band, and the second frequency component is a component of the composite image in a spatial frequency band including a spatial frequency higher in comparison with the spatial frequency band of the first frequency component.

16. A non-transitory computer readable storage medium storing a program causing a computer to execute:

generation processing of generating, from a first image in a first wavelength band and a second image in a second wavelength band different from the first wavelength band, a composite image containing a first frequency component based on the first image and a second frequency component based on the second image;

noise suppression processing of performing noise suppression processing on a difference image between the first image and the composite image; and

first addition processing of adding a noise-suppressed difference image to the composite image, the noise-suppressed difference image being generated by performing the noise suppression processing on the difference image; and

output processing of outputting the composite image.

17. The storage medium according to claim 16 , the program further causing a computer to execute:

separation processing of extracting a texture of the second image; and

second addition processing of adding a first texture image to the composite image into which the noise-suppressed difference image is incorporated by adding, the first texture image representing the extracted texture.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 25, 2019
From: FUKUSHI, KENICHIRO
To: NEC CORPORATION
Reel/Frame 051101/0597 →
Continuity (1)
Related Publication 20210166361A1 · Jun 3, 2021