IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0368831
(2009-02-10)
|
등록번호 |
US-8416302
(2013-04-09)
|
발명자
/ 주소 |
- Zhang, Chunhui
- Matsushita, Yasuyuki
- Kong, Yuan
- Liu, Zicheng
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
1 인용 특허 :
12 |
초록
▼
In some implementations, invisible light is emitted toward a subject being imaged in a low-light environment. A camera having a first color image sensor captures an image of the subject. Image processing is used to correct distortion in the image caused by the invisible light, and an augmented color
In some implementations, invisible light is emitted toward a subject being imaged in a low-light environment. A camera having a first color image sensor captures an image of the subject. Image processing is used to correct distortion in the image caused by the invisible light, and an augmented color image is output.
대표청구항
▼
1. A method comprising: emitting invisible light in a non-visible wavelength toward a subject being imaged in a low-light environment;capturing a first image of the subject using a camera having a first color image sensor, the first image being a color image;processing the first image to correct dis
1. A method comprising: emitting invisible light in a non-visible wavelength toward a subject being imaged in a low-light environment;capturing a first image of the subject using a camera having a first color image sensor, the first image being a color image;processing the first image to correct distortion in the first image caused by the invisible light to produce an augmented color first image; andoutputting the augmented color first image. 2. The method according to claim 1, wherein the processing the first image further comprises: applying a Gaussian mask to evaluate a light level of the first image;determining an optimal gamma correction value from a best mean output intensity and a weighted mean input intensity; andcorrecting an intensity of the first image by using the determined optimal gamma value. 3. The method according to claim 1, wherein the processing the first image further comprises: detecting a facial region of the first image;generating a first color tone map based on the facial region of the first image and a set of training images; andcorrecting the color of the first image by applying the first color tone map to the first image. 4. The method according to claim 1, wherein the processing the first image further comprises: providing a white light source on the camera;obtaining a full color reference image by flashing the white light source to illuminate the subject prior to emitting the invisible light;detecting a facial region of the first image;generating a first color tone map based on the facial region of the first image and the full color reference image; andcorrecting the color of the first image by applying the first color tone map to the first image. 5. The method according to claim 1, further comprising: emitting the invisible light as infrared light in a wavelength between 800 and 900 nm, or as ultraviolet light in a wavelength between 280-350 nm. 6. The method according to claim 1, wherein the camera is a webcam, and further comprising: receiving the first image at a first computer in communication with the webcam prior to the processing of the first image to correct color distortion;carrying out the processing of the first image to correct color distortion at the first computer; andtransmitting the color-corrected image over a network from the first computer to a second computer for display at the second computer as part of a video image. 7. The method according to claim 1, wherein the invisible light is infrared light, and further comprising: providing a second color image sensor in the camera;providing an infrared filter with the second color image sensor for blocking the emitted infrared light;splitting light received by the camera using a mirror, wherein the first image is projected onto the first image sensor, and a duplicate of the first image is projected onto the second image sensor; andcombining the first image and the duplicate of the first image to create the augmented color first image. 8. The method according to claim 1, further comprising: receiving a full color reference image specified by the user;detecting a facial region of the first image;generating a first color tone map based on the facial region of the first image and the full color reference image; andcorrecting the color of the first image by applying the first color tone map to the first image. 9. One or more computer readable storage devices storing processor-readable program code, said processor-readable program code implemented at least in part by one or more processors for processing the first image to correct the distortion in the first image caused by the invisible light according to the method of claim 1. 10. A system comprising: a camera including a color image sensor;an infrared light source for emitting infrared light toward a subject being imaged by the camera; anda processor coupled to a memory, wherein the memory contains an image-processing module for correcting image distortion caused by the infrared light for images captured by the camera, the images captured by the camera being color images. 11. The system according to claim 10, wherein the image-processing module is configured to correct the image distortion by: applying a Gaussian mask to evaluate a light level of the first image;determining an optimal gamma correction value from a best mean output intensity and a weighted mean input intensity; andcorrecting an intensity of the first image by using the determined optimal gamma value. 12. The system according to claim 10, wherein the image-processing module is configured to correct the image distortion by: detecting a facial region of the first image;generating a first color tone map based on the facial region of the first image and a set of training images; andcorrecting color distortion of the first image by applying the first color tone map to the first image. 13. The system according to claim 10, further comprising: a white light LED mounted on the camera,wherein a reference image is obtained by flashing the white light LED to illuminate the subject at least once prior to emitting of the infrared light,wherein the image-processing module is configured to detecting a facial region of the first image, generate a first color tone map based on the facial region of the first image and the reference image, and correct color distortion of the first image by applying the first color tone map to the first image. 14. The system according to claim 10, further comprising: one or more infrared LEDs mounted on the camera for emitting the infrared light in a wavelength between 800 and 900 nm. 15. The system according to claim 10, further comprising: a first computer in communication with the camera,wherein the processor and the memory are contained in the first computer for executing the image-processing module. 16. The system according to claim 10, further comprising: a second color image sensor in the camera;an infrared filter located with the second color image sensor for blocking the emitted infrared light;a mirror in the camera for splitting light received by the camera, wherein the first image is projected onto the first image sensor, and a duplicate of the first image is projected onto the second image sensor; andwherein the image processing module is configured to correct color distortion by combining the first image and the duplicate of the first image by replacing a Y′ channel of the duplicate image with a Y′ channel of the first image to create a combined image. 17. The system according to claim 10, further comprising: providing the processor, the memory and the image processing module in the camera, wherein the processor in the camera processes the first image to correct color distortion prior to transmitting the first image outside the camera. 18. A method of obtaining color images in low-light environments, comprising: providing a webcam for capturing images of a user of a computer, the webcam including a first image sensor and at least one infrared light emitter;emitting infrared light toward the user being imaged in a low-light environment, wherein the infrared light is in wavelength between 800 and 900 nm;capturing a plurality of video images of the user by the webcam in the low-light environment, said video images being color images and having color distortion due to the infrared light;transmitting the captured video images sequentially from the webcam to the computer;processing each video image to correct the color distortion in the video image caused by the infrared light; andtransmitting the color-corrected video images sequentially to a second computer for display as part of a live video feed at the second computer. 19. The method according to claim 18, wherein the processing each video image to correct the color distortion in the video image further comprises: providing a white light source on the camera;obtaining a full color reference image by flashing the white light source to illuminate the subject prior to emitting the infrared light;detecting a facial region of the first image;generating a first color tone map based on the facial region of the first image and the full color reference image; andcorrecting the color of the first image by applying the first color tone map to the first image. 20. The method according to claim 18, further comprising: providing a second color image sensor in the camera;providing an infrared filter with the second color image sensor for blocking the emitted infrared light;splitting light received by the camera using a mirror, wherein each captured image is projected onto the first image sensor, and a duplicate of each captured image is projected onto the second image sensor; andcorrecting the color distortion by combining the each image and the duplicate of the each image by replacing a Y′ channel of the duplicate image with a Y′ channel of the image to create a combined image.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.