US 11,388,334 B2Granted

Automatic camera guidance and settings adjustment

AssigneeQUALCOMM Incorporated

InventorsMuhua Li, An Chen

Life of this patent

Estimating the term…

Loading patent…

Abstract

An image capture and processing device captures an image. Based on the image and/or one or more additional images, the image capture and processing device generates and outputs guidance for optimizing image composition, image capture settings, and/or image processing settings. The guidance can be generated based on determination of a direction that a subject of the image is facing, based on sensor measurements indicating that a horizon may be skewed, another image of the same scene captured using a wide-angle lens, another image of the same subject, another image of a different subject, and/or outputs of a machine learning model trained using a set of images. The image capture and processing device can automatically apply certain aspects of the generated guidance, such as image capture settings and/or image processing settings.

Claims35

Dependent claims

An apparatus for guiding image capture, the apparatus comprising:

one or more memory units storing instructions;
and
one or more processors that execute the instructions, wherein execution of the instructions by the one or more processors causes the one or more processors to:
receive a first image of a scene captured by an image sensor;
identify a subject depicted in the first image;
receive pose sensor measurement data from one or more pose sensors;
determine a pose of the apparatus based on the pose sensor measurement data;
input the first image into a machine learning model, the machine learning model trained using a plurality of training images with identified subjects;
identify, at least in part using the pose of the apparatus as an input to the machine learning model, one or more changes to one or more properties associated with image capture that cause a visual difference between the first image and a second image to be captured by the image sensor after capturing the first image;
and
output guidance indicative of the one or more changes to produce the visual difference before the image sensor captures the second image.

8 more elements

A method of guiding image capture, the method comprising:

receiving a first image of a scene captured by an image sensor of an image capture device;
identifying a subject depicted in the first image;
receiving pose sensor measurement data from one or more pose sensors;
determining a pose of the image capture device based on the pose sensor measurement data;
inputting the first image into a machine learning model, the machine learning model being trained using a plurality of training images with identified subjects;
identifying, at least in part using the pose of the image capture device as an input to the machine learning model, one or more changes to one or more properties of the image capture device that cause a visual difference between the first image and a second image to be captured by the image sensor after capturing the first image;
and
outputting guidance indicative of the one or more changes to produce the visual difference before the image sensor captures the second image.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/071,971Filed 15 Oct 2020 · us provisional application
Priority: 22 May 2020
Published: US 2021/0368094 A125 Nov 2021
Granted: 12 Jul 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification25 codes

G06T 7/73
Determining position or orientation of objects or cameras: using feature-based methods
G06N 3/0464
Architecture, e.g. interconnection topology: convolutional networks [CNN, ConvNet]
G06N 3/09
Learning methods: supervised learning
G06N 20/00
Machine learning