Method and device to compose an image by eliminating one or more moving objects
AssigneeSamsung Electronics Co., Ltd.
InventorsAlok Shankarlal Shukla, Pankaj Kumar Bajpai, Kasireddy Viswanatha Reddy, Keyur Ruganathbhai Ranipa
Life of this patent
Estimating the term…
Abstract
A method and a device to compose an image by eliminating one or more moving objects in a scene being captured are provided. The method includes capturing plurality of images, generating a background image with a plurality of stationary objects after aligning the plurality of captured images, selecting a base image from a plurality of the aligned images, wherein the base image is selected based on a highest similarity measure with the background image, identifying the at least one moving object in the base image, and eliminating said identified at least one moving object in the base image to compose said image.
Claims15
A method of composing an image, the method comprising:
- capturing a plurality of images;
- generating a background image with a plurality of stationary objects after aligning the plurality of captured images;
- selecting a base image from a plurality of aligned images, the base image being selected based on a highest similarity measure with the background image;
- identifying the at least one moving object in the base image;
- eliminating the identified at least one moving object from the base image;
- and
- composing the base image so that the at least one moving object is eliminated from at least one target region,
- wherein the at least one target region is selected from remaining images of the plurality of aligned images based on a highest similarity measure with a corresponding at least one region of the background image, and
- wherein the at least one target region corresponds to the eliminated at least one moving object.
An image capturing device for composing an image, the image capturing device comprising:
- at least one non-transitory memory configured to store computer program code therein;
- and
- at least one processor being, upon execution of the computer program code, configured to:
- capture a plurality of images,
- generate a background image with a plurality of stationary objects after aligning the plurality of captured images,
- select a base image from a plurality of the aligned images, the base image being selected based on a highest similarity measure with the background image,
- identify said at least one moving object in the base image, and
- eliminate the identified at least one moving object from the base image to compose said image,
- wherein the at least one moving object is eliminated within at least one target region,
- wherein the at least one target region is selected from remaining images of the plurality of aligned images based on a highest similarity measure with a corresponding at least one region of the background image, and
- wherein the at least one target region corresponds to the eliminated at least one moving object.
A computer program product comprising computer executable program code recorded on a computer readable non-transitory storage medium, the computer executable program code, when executed, causing actions including:
- capturing a plurality of images;
- generating a background image with a plurality of stationary objects after aligning the plurality of captured images;
- selecting a base image from a plurality of the aligned images, the base image being selected based on a highest similarity measure with the background image;
- identifying the at least one moving object in the base image;
- eliminating the identified at least one moving object from the base image;
- and
- composing the base image that the at least one moving object is eliminated with at least one target region,
- wherein the at least one target region is selected from remaining images of the plurality of aligned images based on a highest similarity measure with a corresponding at least one region of the background image, and
- wherein the at least one target region corresponds to the eliminated at least one moving object.
Dependencies are inferred from the claim text.