Back to results
US 11,057,558 B2Granted
Using change of scene to trigger automatic image capture
AssigneeMicrosoft Technology Licensing, LLC
InventorsOnkar Nath Tiwari, Abhishek Agarwal, Rahul Bhuptani, Mahesh Sridharan, Sachin Talreja, Anish Chandran
Life of this patent
Estimating the term…
Abstract
A series of frames or live images received by a camera can be processed by an automatic image capture system to determine when an automatic image capture should take place. The system can detect when a scene change occurs by comparison of data for two or more frames. If a scene change is followed by a stabilization of the scene, the system can trigger an auto-capture of the stabilized scene, without the need for user input.
Claims16
A system comprising:
- at least one processor;
- and
- one or more computer readable media including instructions which, when executed by the at least one processor, cause the at least one processor to:
- receive, at a first time, a first image corresponding to a first real-world scene;
- receive, at a second time subsequent to the first time, a second image corresponding to a second real-world scene;
- generate a first histogram for the first image by plotting a number of pixels for each of a plurality of tonal values included in the first image;
- generate a second histogram for the second image by plotting the number of pixels for each of the plurality of tonal values included in the second image;
- determine that the first image differs from the second image by at least a first amount by computing a correlation coefficient between the first histogram and the second histogram and determining that the correlation coefficient is lower than a difference threshold which indicates that the first image and the second image differ by at least the first amount;
- receive, at a third time subsequent to the second time, a third image corresponding to a third real-world scene;
- generate a third histogram for the third image by plotting the number of pixels for each of the plurality of tonal values included in the third image;
- determine that the second image differs from the third image by less than the first amount by computing a correlation coefficient between the second histogram and the third histogram and determining that the correlation coefficient is greater than or equal to a difference threshold which indicates that the second image and the third image differ by less than the first amount;
- and
- automatically capture at least a first region of the third image via a camera optical system in response to determining the second image and third image differ by less than the first amount.
10 more elements
A system comprising:
- at least one processor;
- and
- one or more computer readable media including instructions which, when executed by the at least one processor, cause the at least one processor to:
- receive, at a first time, a first image corresponding to a first real-world scene;
- receive, at a second time subsequent to the first time, a second image corresponding to a second real-world scene;
- generate a first histogram for the first image by plotting a number of pixels for each of a plurality of tonal values included in the first image;
- generate a second histogram for the second image by plotting the number of pixels for each of the plurality of tonal values included in the second image;
- determine that the first image differs from the second image by at least a first amount by comparing the first histogram with the second histogram;
- receive, at a third time subsequent to the second time, a third image corresponding to a third real-world scene;
- generate a third histogram for the third image;
- determine that the second image and the third image differ by less than the first amount by comparing the second histogram with the third histogram;
- automatically discard the first histogram in response to determining that the second image and the third image differ by less than by at least the first amount;
- and
- automatically capture at least a first region of the third image via a camera optical system in response to determining the second image and third image differ by less than the first amount.
11 more elements
A method of capturing an image comprising:
- receiving, at a first time, a first image corresponding to a first real-world scene;
- receiving, at a second time subsequent to the first time, a second image corresponding to a second real-world scene;
- generating a first histogram for the first image by plotting a number of pixels for each of a plurality of tonal values included in the first image;
- generating a second histogram for the second image by plotting the number of pixels for each of the plurality of tonal values included in the second image;
- determining that the first image differs from the second image by at least a first amount by computing a correlation coefficient between the first histogram and the second histogram and determining that the correlation coefficient is lower than a difference threshold which indicates that the first image and the second image differ by at least the first amount;
- receiving, at a third time subsequent to the second time, a third image corresponding to a third real-world scene;
- generating a third histogram for the third image by plotting the number of pixels for each of the plurality of tonal values included in the third image;
- determining that the second image differs from the third image by less than the first amount by computing a correlation coefficient between the second histogram and the third histogram and determining that the correlation coefficient is greater than or equal to a difference threshold which indicates that the second image and the third image differ by less than the first amount;
- and
- automatically capturing at least a first region of the third image via a camera optical system in response to determining the second image and third image differ by less than the first amount.
7 more elements
A method of capturing an image, comprising:
- receiving, at a first time, a first image corresponding to a first real-world scene;
- receiving, at a second time subsequent to the first time, a second image corresponding to a second real-world scene;
- generating a first histogram for the first image by plotting a number of pixels for each of a plurality of tonal values included in the first image;
- generating a second histogram for the second image by plotting the number of pixels for each of the plurality of tonal values included in the second image;
- determining that the first image differs from the second image by at least a first amount by comparing the first histogram with the second histogram;
- receiving, at a third time subsequent to the second time, a third image corresponding to a third real-world scene;
- generating a third histogram for the third image;
- determining that the second image and the third image differ by less than the first amount by comparing the second histogram with the third histogram;
- and
- automatically discarding the first histogram in response to determining that the second image and the third image differ by less than the first amount;
- and
- automatically capturing at least a first region of the third image via a camera optical system in response to determining the second image and third image differ by less than the first amount.
9 more elements
A system for determining when an automatic image capture should occur, the system comprising:
- at least one processor;
- and
- one or more computer readable media including instructions which, when executed by the at least one processor, cause the at least one processor to:
- receive, via a camera, a plurality of images frames including a first image frame and a subsequent second image frame;
- determine a scene change has occurred between the first image frame and the second image frame by:
- generate a first histogram for the first image frame by plotting a number of pixels for each of a plurality of tonal values included in the first image frame;
- generate a second histogram for the second image frame by plotting the number of pixels for each of the plurality of tonal values included in the second image frame;
- and
- determining that the first image frame differs from the second image frame by at least a first amount by computing a correlation coefficient between the first histogram and the second histogram and determining that the correlation coefficient is lower than a difference threshold which indicates that the first image frame and the second image frame differ by at least the first amount and that the scene change has occurred;
- receive, via the camera, a third image frame subsequent to receiving the second image frame;
- generating a third histogram for the third image by plotting the number of pixels for each of the plurality of tonal values included in the third image;
- determine a scene stabilization has occurred between the second image frame and the third image frame by computing a correlation coefficient between the second histogram and the third histogram and determining that the correlation coefficient is greater than or equal to a difference threshold which indicates that the second image and the third image differ by less than the first amount and that the scene stabilization has occurred;
- and
- initiate an auto-capture of a fourth image frame received after the third image frame based at least on the determinations that the scene change occurred and the scene stabilization occurred.
11 more elements
Dependencies are inferred from the claim text.