US 9,436,870 B1Granted

Automatic camera selection for head tracking using exposure control

AssigneeAmazon Technologies, Inc.

InventorsStephen Vincent Mangiat, Ambrish Tyagi

Life of this patent

Estimating the term…

Loading patent…

Abstract

The subject technology provides embodiments for tracking a user's face/head (or another object) using one or more cameras provided by a computing device. Embodiments implement exposure sweeping based on an average intensity of a current scene to a target intensity for a given image. If a face is not detected, an exposure duration and/or gain may be adjusted and the face detection is performed again. Once the face is detected, an average intensity of a virtual bounding box surrounding the detected face is determined and exposure sweeping may be performed solely within the virtual bounding box to reach a target intensity. When the average intensity is within a predetermined threshold of the target intensity, the detected face may be at an optimal exposure. Embodiments also provide for switching to another camera(s) of the computing device when not detecting a face in the image upon performing a full exposure sweep.

Claims20

Dependent claims

A computing device comprising:

at least one processor;
a plurality of cameras comprising at least a first camera configured according to a current exposure duration setting and a second camera;
and
a memory device including instructions that, when executed by the at least one processor, cause the at least one processor to:
acquire first image information using at least the first camera of the computing device;
perform until each target intensity value from a plurality of target intensity values is selected:
select a respective target intensity value from the plurality of target intensity values, each of the target intensity values being different values within a range of possible intensity values of the first image information;
determine a current average intensity value of the first image information, the first image information including intensity information for a plurality of pixels, the intensity information corresponding to respective grey levels for each of the plurality of pixels;
adjust the current exposure duration setting to be an adjusted exposure duration setting based on a ratio of the respective target intensity value to the current average intensity value;
acquire subsequent image information at the adjusted exposure duration setting;
and
determine that a representation of a face of a user is undetected in the subsequent image information;
and
activate, after determining that the representation of the face of the user is undetected for each target intensity value from the plurality of target intensity values, the second camera of the computing device.

11 more elements

A computer-implemented method, the method comprising:

acquiring first image data using a first camera of a computing device configured according to a current exposure duration;
performing until each target intensity value from a plurality of target intensity values is selected:
selecting a target intensity value from the plurality of target intensity values;
determining a current average intensity value of the first image data;
and
adjusting the current exposure duration to be at an adjusted exposure duration based on a ratio of the target intensity value to the current average intensity value;
acquiring subsequent image information at the adjusted exposure duration;
and
determining that a representation of an object is undetected in the subsequent image information;
and
switching, after determining that the representation is undetected for each target intensity value from the plurality of target intensity values, to a second camera of the computing device.

8 more elements

A non-transitory computer-readable medium including instructions stored therein that, when executed by at least one computing device, cause the at least one computing device to:

acquire first image data using a first camera of a computing device configured according to a current exposure duration;
perform until each target intensity value from a plurality of target intensity values is selected:
select a target intensity value from the plurality of target intensity values;
determine a current average intensity value of the first image data;
and
adjust the current exposure duration to be at an adjusted exposure duration based on a ratio of the target intensity value to the current average intensity value;
acquire subsequent image information at the adjusted exposure duration;
and
determine that a representation of an object is undetected in the subsequent image information;
and
switch, after determining that the representation is undetected for each target intensity value from the plurality of target intensity values, to a second camera of the computing device.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 14/298,745Filed 6 Jun 2014
Granted: 6 Sep 2016
Term ends: Not estimatedThe source records don’t support an estimate.

Classification9 codes

G06F 3/017
Input arrangements or combined input and output arrangements for interaction between user and computer: gesture based interaction, e.g. based on a…
G06F 3/005
Specific input/output arrangements not covered by G06F3/01 - G06F3/16: input arrangements through a video camera
G06F 3/012
Arrangements for interaction with the human body, e.g. for user immersion in virtual reality: head tracking input arrangements
G06V 10/141
Optical characteristics of the device performing the acquisition or on the illumination arrangements: control of illumination

Family

No related US applications are recorded in the indexed filing history.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key