Online compensation of thermal distortions in a stereo depth camera

Patent metadata

Field	Value
Publication number	US-12425559-B2
Application number	US-202418636707-A
Country	US
Kind code	B2
Filing date	Apr 16, 2024
Priority date	Sep 25, 2015
Publication date	Sep 23, 2025
Grant date	Sep 23, 2025

Abstract

An example apparatus includes: a camera to record an image; memory to store instructions; and a processor in circuit with the memory, the processor to execute the instructions to: determine a depth based on: (a) the image and (b) a calibration parameter of the camera; and adjust the calibration parameter based on a temperature of the camera and the depth.

First claim

What is claimed is:

1. An apparatus comprising:
interface circuitry;
machine-readable instructions; and
at least one processor circuit to be programmed by the machine-readable instructions to:
control a light source to cast an infrared light pattern;
obtain data generated by an infrared camera, the data based on the infrared light pattern;
determine, based on a deformation of the infrared light pattern, depth data including physical distances between the infrared camera and different locations on a face; and
control an application based on the depth data.

2. The apparatus of claim 1 , wherein one or more of the at least one processor circuit is in a smartphone.

3. The apparatus of claim 1 , wherein one or more of the at least one processor circuit is to:
perform facial tracking based on the data;
create a virtual screen based on the facial tracking; and
adapt a user interface of the application based on the facial tracking.

4. The apparatus of claim 1 , wherein one or more of the at least one processor circuit is to:
cause a virtual object to be rendered in a user interface of the application;
determine a body part gesture based on second data generated by the infrared camera;
determine dynamics of the virtual object based on the body part gesture; and
apply the dynamics to the virtual object in the user interface of the application.

5. The apparatus of claim 1 , wherein one or more of the at least one processor circuit is to:
obtain the data based on multiple scans of the infrared light pattern by the infrared camera;
reconstruct a shape of the face based on the multiple scans of the infrared light pattern and based on second data from a second camera;
determine image distortions in the reconstructed shape of the face; and
perform a calibration routine to compensate for the image distortions.

6. The apparatus of claim 1 , wherein one or more of the at least one processor circuit is to determine the physical distances based on the data generated by the infrared camera and based on second data generated by a red-green-blue camera.

7. At least one non-transitory machine-readable medium comprising machine-readable instructions to cause at least one processor circuit to at least:
generate a virtual object for a user interface of an application;
control a light source to cast an infrared light pattern;
determine a body-part gesture based on data generated by an infrared camera, the data based on the infrared light pattern;
determine dynamics of the virtual object based on the body part gesture; and
apply the dynamics to the virtual object in the user interface of the application.

8. The at least one non-transitory machine-readable medium of claim 7 , wherein the machine-readable instructions are to cause one or more of the at least one processor circuit to:
perform facial tracking based on second data generated by an infrared camera;
create a virtual screen based on the facial tracking; and
adapt the user interface of the application based on the facial tracking.

9. The at least one non-transitory machine-readable medium of claim 7 , wherein the machine-readable instructions are to cause one or more of the at least one processor circuit to:
obtain second data based on multiple scans of the infrared light pattern by the infrared camera;
reconstruct a shape of a face based on the multiple scans of the infrared light pattern and based on third data from a second camera;
determine image distortions in the reconstructed shape of the face; and
perform a calibration routine to compensate for the image distortions.

10. The at least one non-transitory machine-readable medium of claim 8 , wherein the machine-readable instructions are to cause one or more of the at least one processor circuit to determine physical distances between the infrared camera and different locations on a face based on a deformation of a second infrared light pattern on the face.

11. The at least one non-transitory machine-readable medium of claim 10 , wherein the machine-readable instructions are to cause one or more of the at least one processor circuit to determine the physical distances based on the second data generated by the infrared camera and based on third data generated by a red-green-blue camera.

12. A method comprising:
controlling a light source to cast an infrared light pattern;
obtaining first data generated by an infrared camera, the first data based on multiple scans of the infrared light pattern by the infrared camera;
reconstructing, by at least one processor circuit programmed by at least one instruction, a shape of a face based on the multiple scans of the infrared light pattern and based on second data from a second camera;
determining, by one or more of the at least one processor circuit, one or more image distortions in the reconstructed shape of the face based on third data from a third camera; and
performing, by one or more of the at least one processor circuit, a calibration routine to compensate for the one or more image distortions.

13. The method of claim 12 , including controlling an application in a smartphone.

14. The method of claim 13 , including:
creating a virtual screen based on facial tracking; and
adapting a user interface of the application based on the facial tracking.

15. The method of claim 13 , including:
rendering a virtual object on a user interface of the application;
determining a body part gesture based on fourth data generated by the infrared camera;
determining dynamics of the virtual object based on the body part gesture; and
applying the dynamics to the virtual object on the user interface of the application.

16. The method of claim 12 , including determining physical distances between the infrared camera and different locations on a face, the physical distances based on a deformation of a second infrared light pattern on the face.

Assignees

• Intel Corp

Inventors

• Zabatani Aviad
• Bareket Sagy
• Menashe Ohad
• Sperling Erez
• Bronstein Alex
• Bronstein Michael
• Kimmel Ron
• Surazhsky Vitaly

Classifications

• G06T5/80

  Geometric correction · CPC title

• G06F3/0488

  using a touch-screen or digitiser, e.g. input of commands through traced gestures · CPC title

• G06F3/017

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title

• G06F3/012

  Head tracking input arrangements · CPC title

• H04N13/243

  using three or more two-dimensional [2D] image sensors · CPC title