发明名称 |
Information processing apparatus, control method thereof, and storage medium |
摘要 |
In an information processing apparatus, an object recognition process is performed on each image of a multi-viewpoint image group based on focal length information and information about objects. Objects are specified in each image. A target object is determined based on relationship information indicating a relationship between the objects. An image that contains the determined target object is generated. |
申请公布号 |
US9639778(B2) |
申请公布日期 |
2017.05.02 |
申请号 |
US201514723828 |
申请日期 |
2015.05.28 |
申请人 |
Canon Kabushiki Kaisha |
发明人 |
Shimizu Tomoyuki |
分类号 |
G06K9/00;G06K9/62;H04N7/18;H04N5/225;H04N5/232;H04N5/235 |
主分类号 |
G06K9/00 |
代理机构 |
Fitzpatrick, Cella, Harper & Scinto |
代理人 |
Fitzpatrick, Cella, Harper & Scinto |
主权项 |
1. An information processing apparatus comprising:
an image holding unit configured to hold a multi-viewpoint image captured from a plurality of viewpoints; an object information holding unit configured to hold information about an object and relationship information indicating a relationship between a user of the information processing apparatus and the object; a recognition unit configured to recognize a plurality of objects in the multi-viewpoint image based on the information about the object; a determination unit configured to determine a target object from the plurality of recognized objects based on the relationship information; and a generation unit configured to generate a combined image in which the target object is in focus, based on the multi-viewpoint image, wherein, when the determination unit determines a plurality of objects as the target object, the generation unit sets a focal length based on focal length of the target object and a parameter for an aperture diameter that provides a depth of field covering the target object, and generates a combined image in which the target object is in focus, based on the multi-viewpoint image. |
地址 |
Tokyo JP |