Material spectroscopy

Patent metadata

Field	Value
Publication number	US-11657589-B2
Application number	US-202117147807-A
Country	US
Kind code	B2
Filing date	Jan 13, 2021
Priority date	Jan 13, 2021
Publication date	May 23, 2023
Grant date	May 23, 2023

Abstract

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine a first measure of pixel values in the first image, acquire a second image, estimate ambient light illuminating the first object based on the second image and modify the first measure of pixel values based on a second measure of pixel values corresponding to estimated ambient light based on the second image. The instructions include further instructions to perform a comparison of the modified first measure of pixel values to a third measure of pixel values determined from a third image of a second object, wherein the third image is previously acquired by illuminating the second object with a second light beam and, when the comparison determines that the first measure is equal to the third measure of pixel values within a tolerance, determine whether the first object and the second object are a same object.

First claim

The invention claimed is:

1. A computer, comprising:
a processor; and
a memory, the memory including instructions executable by the processor to:
acquire a first image by illuminating a first object with a first light beam;
determine a first measure of pixel values in the first image;
acquire a second image;
estimate ambient light illuminating the first object based on the second image;
modify the first measure of pixel values based on a second measure of pixel values corresponding to estimated ambient light based on the second image, wherein the first and second measures of pixel values are first and second mean values calculated on first and second histograms of pixel values included in the first and second images, respectively;
perform a comparison of the modified first measure of pixel values to a third measure of pixel values determined from a third image of a second object, wherein the third image is previously acquired by illuminating the second object with a second light beam, wherein the third measure of pixel values is a third mean value calculated on a third histogram of pixel values included in the third image; and
when the comparison determines that the first measure is equal to the third measure of pixel values within a tolerance, determine whether the first object and the second object are a same object.

2. The computer of claim 1 , wherein the first light beam is a near infrared light beam and the second light beam is a near infrared light beam.

3. The computer of claim 2 , wherein the first, second and third images are acquired with a camera that acquires near infrared pixels, red pixels, green pixels and blue pixels.

4. The computer of claim 1 , the instructions including further instructions to determine the second measure of pixel values by acquiring the second image of the first object using ambient illumination.

5. The computer of claim 1 , the instructions including further instructions to determine the second measure of pixel values by segmenting the first image to determine a plurality of image segments that do not include the first object, measuring a standard deviation of pixel values in each image segment and combining measures of pixel values for segments having standard deviation less than or equal to an overall standard deviation plus a tolerance.

6. The computer of claim 1 , the instructions including further instructions to output the determination whether the first object and the second object are a same type of object.

7. The computer of claim 1 , the instructions including further instructions to, when the comparison determines that each of the first object and the second object is a human face, perform human identification testing.

8. The computer of claim 7 , the instructions including further instructions to, when the comparison determines that each of the first object and the second object is a human face and are the same object, operate a vehicle.

9. The computer of claim 1 , wherein the first and second mean values are calculated based on a Gaussian mixture model applied to the first and second histograms, respectively.

10. The computer of claim 1 , the instructions including further instructions to illuminate the first object with ambient light in addition to near infrared light to acquire a first color/near infrared image.

11. The computer of claim 10 , the instructions including further instructions to estimate the ambient light by dividing each infrared pixel of the first color/near infrared image by a corresponding blue pixel of the first color/near infrared image.

12. A method comprising:
acquiring a first image by illuminating a first object with a first light beam;
determining a first measure of pixel values in the first image;
acquire a second image;
estimate ambient light illuminating the first object based on the second image;
modifying the first measure of pixel values based on a second measure of pixel values corresponding to estimated ambient light based on the second image, wherein the first and second measures of pixel values are first and second mean values calculated on first and second histograms of pixel values included in the first and second images, respectively;
performing a comparison of the modified first measure of pixel values to a third measure of pixel values determined from a third image of a second object, wherein the third image is previously acquired by illuminating the second object with a second light beam, wherein the third measure of pixel values is a third mean value calculated on a third histogram of pixel values included in the third image; and
when the comparison determines that the first measure is equal to the third measure of pixel values within a tolerance, determining whether the first object and the second object are a same object.

13. The method of claim 12 , wherein the first light beam is a near infrared light beam and the second light beam is a near infrared light beam.

14. The method of claim 13 , wherein the first, second, and third images are acquired with a camera that acquires near infrared pixels, red pixels, green pixels and blue pixels.

15. The method of claim 12 , the instructions including further instructions to determine the second measure of pixel values by acquiring the second image of the first object using ambient illumination.

16. The method of claim 12 , the instructions including further instructions to determine the second measure of pixel values by segmenting the first image to determine a plurality of image segments that do not include the first object, measuring a standard deviation of pixel values in each image segment and combining measures of pixel values for segments having standard deviation less than or equal to an overall standard deviation plus a tolerance.

17. The method of claim 12 , the instructions including further instructions to output the determination whether the first object and the second object are a same type of object.

18. The method of claim 12 , the instructions including further instructions to, when the comparison determines that each of the first object and the second object is a human face, perform human identification testing.

19. The method of claim 18 , the instructions including further instructions to, when the comparison determines that each of the first object and the second object is a human face and are the same object, operate a vehicle.

20. The method of claim 12 , wherein the first and second mean values are calculated based on a Gaussian mixture model applied to the first and second histograms, respectively.

Assignees

• Ford Global Tech Llc

Inventors

• Hassani Ali
• Golgiri Hamid M
• Diedrich Jonathan
• Parenti Robert
• Aradhyula Hemanth Yadav

Classifications

• G06N3/084

  Backpropagation, e.g. using gradient descent · CPC title

• G07C9/00563

  using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns · CPC title

• G06V40/166 Primary

  using acquisition arrangements · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G07C9/37

  using biometric data, e.g. fingerprints, iris scans or voice recognition · CPC title