SYSTEM AND METHOD FOR MODIFYING IMAGES

• US 20120224019A1
• Filed: 03/01/2011
• Published: 09/06/2012
• Est. Priority Date: 03/01/2011
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Samadani, Ramin, Wu, Chen
• Granted Patent: US 8,780,161 B2
• Time in Patent Office: Days
• US Class Current: 348/14.01
• CPC Class Codes: H04N 23/13 with multiple sensors
• CPC Class Codes: H04N 23/74 by influencing the scene brightness using illuminating means
• CPC Class Codes: H04N 5/325 Image enhancement, e.g. by subtraction techniques using polyenergetic X-rays
• CPC Class Codes: H04N 7/142 Constructional details of the terminal equipment, e.g. arrangements of the camera and the display

Abstract

The present invention describes a method of modifying an image in a video that includes the step of capturing a visible light image of an area, where the visible light image captured at a first frame rate. The method in addition includes the step of capturing a corresponding infrared light image of an area, the infrared light image being captured when the area is illuminated with an infrared light source, the infrared light image captured at the substantially the same frame rate as the visible light image. Based on the infrared light image, at least a subset of the human perceptible characteristics of the captured visible light image are modified.

Claims

1. A method of modifying an image in a video comprising the steps of:

Capturing a visible light image of an area, the visible light image captured at a first frame rate;

Capturing a corresponding infrared light image of an area, the infrared light image being captured when the area is illuminated with an infrared light source, the infrared light image captured at the substantially the same frame rate as the visible light image; and

Based on the infrared light image, adjusting at least a subset of the human perceptible characteristics of the captured visible light image.

2. The method recited in claim 1 wherein the human perceptible characteristics of the captured visual image include skin brightness.

3. The method recited in claim 2 further including the step of detecting skin in the infrared light image and the corresponding visible light image and determining the skin brightness in the skin regions of the IR image and the visible range image.

4. The method recited claim 3 wherein the skin brightness of the frames in the visible range image is modified to be closer to skin brightness of the frames in the IR range.

5. The method recited in claim 4 further including the step of determining the ratio of skin brightness in the IR frame and the visible light video frames, wherein the ratio of skin brightness is determined by the albedo ratio.

6. A method of modifying an image in a video comprising the steps of:

Capturing a visible light image of an area, the visible light image captured at a first frame rate;

Capturing a corresponding infrared light image of an area, the infrared light image being captured when the area is illuminated with an infrared light source, the infrared light image captured at the substantially the same frame rate as the visible light image; and

Determining whether a region of the visible light image is out of range, and for the out of range regions using data from the infrared light image to replace out of range regions in the visible light image.

7. The method recited in claim 6 wherein for the regions of the visible light image that are not out of range, modifying the human perceptible characteristics of the visible light image based on the infrared light image.

8. The method recited in claim 6 wherein for the out of range regions, the luminance values of the pixels, in the visible light image are replaced with the luminance value of the pixels in the corresponding IR light image.

9. The method recited in claim 6 further including the step of creating a color map that maps luminance values to chrominance values.

10. The method recited in claim 9 further including the step of using the color map to map the luminance values of the out of range pixels in the visible light image to the chrominance values.

11. The method recited in claim 10 wherein pyramid blending is used to blend the chrominance pixels and the luminance pixels in the visible light image.

12. A system for modifying an image in a video comprising the steps of:

A visible light image capture component for capturing a visible light image of an area, the visible light image captured at a first frame rate;

An IR light image capture component for capturing a corresponding infrared light image of an area, the infrared light image being captured when the area is illuminated with an infrared light source, the infrared light image captured at the substantially the same frame rate as the visible light image; and

A video modification component for modifying the visible light image based on the infrared light image, wherein the visible light image is modified by adjusting at least a subset of the human perceptible characteristics of the visible light image.

13. A system for modifying an image in a video comprising the steps of:

A visible light image capture component for capturing a visible light image of an area, the visible light image captured at a first frame rate;

An IR light image capture component for capturing a corresponding infrared light image of an area, the infrared light image being captured when the area is illuminated with an infrared light source, the infrared light image captured at the substantially the same frame rate as the visible light image; and

A video modification component determining whether a region of the visible light image is out of range, and for the out of range regions using data from the infrared light image to replace out of range regions in the visible light image.