Method and apparatus for processing image
AssigneeSamsung Electronics Co., Ltd.
InventorsSung-wook Youn, Do-wan Kim, Jae-kyeong Lee, Yong-gyoo Kim
Life of this patent
Estimating the term…
Abstract
Provided is a method of processing an image, the method including: obtaining rotation information with respect to each of a plurality of regions included in a 360-degree image; determining representative rotation information indicating movement of a capturing device, the movement occurring when capturing the 360-degree image, based on the rotation information of each of the plurality of regions; and correcting distortion of the 360-degree image based on the determined representative rotation information.
Claims13
A method of processing an image, the method comprising:
- obtaining rotation information with respect to each of a plurality of regions included in a 360-degree image;
- identifying at least one object included in the 360-degree image;
- selecting one or more regions of the plurality of regions based on at least one of a characteristic and a distribution of the identified at least one object;
- determining representative rotation information indicating movement of a capturing device, the movement occurring when capturing the 360-degree image, based on rotation information of the selected one or more regions;
- and
- correcting distortion of the 360-degree image based on the determined representative rotation information.
An apparatus for processing an image, the apparatus comprising:
- an input portion configured to obtain a 360-degree image;
- and
- a processor configured to obtain rotation information with respect to each of a plurality of regions included in the 360-degree image, identify at least one object included in the 360-degree image, select one or more regions of the plurality of regions based on at least one of a characteristic and a distribution of the identified at least one object, determine representative rotation information indicating movement of a capturing device, the movement occurring when capturing the 360-degree image, based on rotation information of the selected one or more regions, and correct distortion of the 360-degree image based on the determined representative rotation information.
Dependencies are inferred from the claim text.