System and method for determining image resolution

Patent metadata

Field	Value
Publication number	US-9544497-B2
Application number	US-201414284217-A
Country	US
Kind code	B2
Filing date	May 21, 2014
Priority date	May 21, 2014
Publication date	Jan 10, 2017
Grant date	Jan 10, 2017

Abstract

Systems and methods for deductively determining a resolution setting for an imaging device based on one or more features of a scene are disclosed. The features may include the size of primary or foreground faces within the scene, a maximum amount of high frequency content within the scene, a lighting condition of the scene, or a battery level of an electronic device.

First claim

What is claimed is:

1. A system for determining an image capture resolution, comprising:
a processor configured to
operate an imaging device to obtain an image of a scene in a preview mode at a default image capture resolution;
determine sizes of one or more regions of interest in the image of the scene;
determine a scene-dependent resolution setting based on the determined sizes, the scene-dependent resolution setting being higher or lower than the default resolution, wherein the scene-dependent resolution setting is:
higher than the default resolution if a pixel area of a foreground region of the one or more regions of interest is less than a percentage of a field of view of the imaging device, and
lower than the default resolution if the pixel area of the foreground region is not less than the percentage of the field of view of the imaging device;

adjust the image capture resolution for the imaging device to the scene-dependent resolution setting; and
obtain an image of the scene at the scene-dependent resolution setting.

2. The system of claim 1 , further comprising the imaging device, the imaging device comprising an imaging sensor.

3. The system of claim 2 , wherein the processor is further configured to determine the regions of interest in the image of the scene using one or more of a face detection algorithm or an object tracking algorithm.

4. The system of claim 3 , wherein the processor is further configured to classify the regions of interest as foreground or background regions of interest based on a pixel area of each region of interest.

5. The system of claim 4 , wherein the processor is further configured to receive an input from a user specifying the percentage of the field of view of the imaging device.

6. The system of claim 4 , wherein the processor is further configured to increase the image capture resolution if the pixel area of a foreground region of interest is less than 5% of a total field of view of the imaging sensor.

7. The system of claim 1 , wherein the processor is further configured to identify a maximum amount of high frequency content in the scene by scanning the scene for edges using a fast Fourier transform or sliding window.

8. The system of claim 7 , wherein the processor is further configured to access a look up table to determine an increase to a resolution setting based on the amount of high frequency content with the scene.

9. The system of claim 1 , wherein the processor is further configured to determine a lighting condition of a scene and increase a resolution setting based on the lighting condition.

10. The system of claim 1 , wherein the processor operates as a component of a camera application for a mobile device.

11. A method for determining an image capture resolution, comprising:
operating an imaging device in a preview mode at a default image capture resolution to obtain an image of a scene;
determining sizes of one or more regions of interest in the image of the scene;
determining a scene-dependent resolution setting based on the determined sizes, the scene-dependent resolution setting being higher or lower than the default resolution, wherein the scene-dependent resolution setting is:
higher than the default resolution if a pixel area of a foreground region of the one or more regions of interest is less than a percentage of a field of view of the imaging device, and
lower than the default resolution if the pixel area of the foreground region is not less than the percentage of the field of view of the imaging device;

adjusting the image capture resolution for the imaging device to the scene-dependent resolution setting; and
capturing with the imaging device an image of the scene at the scene-dependent resolution setting.

12. The method of claim 11 , further comprising determining the regions of interest using one or more of a face detection algorithm or an object tracking algorithm.

13. The method of claim 12 , further comprising classifying the regions of interest as foreground or background regions of interest based on a pixel area of each region of interest.

14. The method of claim 13 , further comprising receiving an input from a user setting the percentage of the field of view of the imaging device.

15. The method of claim 11 , further comprising identifying a maximum amount of high frequency content in the scene by scanning the scene for edges using a fast Fourier transform or sliding window.

16. The method of claim 15 , further comprising increasing a resolution setting based on the amount of high frequency content with the scene.

17. The method of claim 11 , further comprising operating the imaging device to operate as part of a camera application for a mobile device.

18. An apparatus for determining an image capture resolution, comprising:
means for operating an imaging device in a preview mode at a default resolution to obtain an image of a scene;
means for determining sizes of one or more regions of interest in the image of the scene;
means for determining a scene-dependent resolution setting based on the determined sizes of the one or more regions of interests, the scene-dependent resolution setting being higher or lower than the default resolution, wherein the scene-dependent resolution setting is:
higher than the default resolution if a pixel area of a foreground region of the one or more regions of interest is less than a percentage of a field of view of the imaging device, and
lower than the default resolution if the pixel area of the foreground region is not less than the percentage of the field of view of the imaging device;

means for adjusting the image capture resolution for the imaging device to the scene-dependent resolution setting; and
means for capturing an image of the scene at the scene-dependent resolution setting.

19. A non-transitory computer-readable medium storing instructions that, when executed, cause at least one physical computer processor to perform a method of determining an image capture resolution based on features of a scene, the method comprising:
operating the imaging device in a preview mode at a default image capture resolution to obtain an image of a scene;
determining sizes of one or more regions of interest in the image of the scene;
determining a scene-dependent resolution setting based on the determined sizes, the scene-dependent resolution setting being higher or lower than the default resolution, wherein the scene-dependent resolution setting is:
higher than the default resolution if a pixel area of a foreground region of the one or more regions of interest is not less than a percentage of a field of view of the imaging device, and
lower than the default resolution if the pixel area of the foreground region is not less than the percentage of the field of view of the imaging device;

adjusting the image capture resolution for the imaging device to the scene-dependent resolution setting; and
capturing with the imaging device an image of the scene at the scene-dependent resolution setting.

20. The non-transitory computer-readable medium of claim 19 , the method further comprising operating an imaging device in a preview mode.

21. The non-transitory computer-readable medium of claim 19 , the method further comprising determining the regions of interest using one or more of a face detection algorithm or an object tracking algorithm and classifying the regions of interest as foreground or background regions of interest based on a pixel area of each region of intere

Assignees

• Qualcomm Inc

Inventors

• Forutanpour Babak
• Frantz William Thomas
• Ganesh Shriram
• Baker Daniel Scott
• Yamakawa Devender Akira

Classifications

• H04N23/651

  for reducing power consumption by affecting camera operations, e.g. sleep mode, hibernation mode or power off of selective parts of the camera · CPC title

• H04N23/70

  Circuitry for compensating brightness variation in the scene · CPC title

• H04N23/61 Primary

  based on recognised objects · CPC title

• H04N23/63

  by using electronic viewfinders · CPC title

• H04N25/46

  by combining or binning pixels · CPC title