公开(公告)号：US20240242516A1

公开(公告)日：2024-07-18

申请号：US18414991

申请日：2024-01-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyungdong LEE

IPC: G06V20/60 ,  G06T7/70 ,  G06V10/54 ,  G06V10/56 ,  G06V10/82

CPC classification number: G06V20/60 ,  G06T7/70 ,  G06V10/54 ,  G06V10/56 ,  G06V10/82 ,  G06T2207/20084

Abstract: A method of providing information about an Internet-of-Things (IoT) device available in an indoor area, includes: identifying an object in a captured image of the indoor area; identifying a feature of the object based on the captured image, the feature being related to at least one operation method of the object or a configuration of the object; determining an IoT device corresponding to the object, based on a type of the object and the feature of the object; and providing information about the determined IoT device.

公开(公告)号：US20230216985A1

公开(公告)日：2023-07-06

申请号：US18093133

申请日：2023-01-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yoonsik TAK ,  Aeran LIM ,  Junho RIM ,  Jaewook SHIN ,  Hyungdong LEE

IPC: H04N5/783 ,  H04N5/262 ,  G06V10/62 ,  G06V10/74

CPC classification number: H04N5/783 ,  H04N5/2621 ,  G06V10/62 ,  G06V10/761 ,  G06V2201/07

Abstract: A method of generating a time-lapse video includes: identifying an image storage mode; obtaining a first image; based on identifying that the image storage mode is an emphasis mode for emphasizing one or more images, obtaining a first time difference between the first image and a stored image, and a first feature value indicating a first amount of change between the first image and the stored image; for each respective image of a first plurality of images of a first image group stored in a memory, identifying a second image from among the first plurality of images, based on a second time difference and a second feature value; generating a second image group by removing the second image from the first image group and adding the first image to the first image group; and generating the time-lapse video by using a second plurality of images of the second image group.

公开(公告)号：US20230206504A1

公开(公告)日：2023-06-29

申请号：US18082926

申请日：2022-12-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaewook SHIN ,  Haedong YEO ,  Hyungdong LEE

IPC: G06T7/90 ,  G06T7/70 ,  G06V10/56 ,  G09G5/14

CPC classification number: G06T7/90 ,  G06T7/70 ,  G06V10/56 ,  G09G5/14 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/30201

Abstract: An electronic device comprises a processor configured to: obtain a spatial image comprising a plurality of pixels corresponding to a plurality of objects, perform a pixel analysis on the plurality of pixels to extract one or more colors from the spatial image, obtain, based on the extracted one or more colors, color characteristic information about colors included in the plurality of objects in the spatial image and relation characteristic information defining relations between the plurality of objects in the spatial image, obtain, by applying the color characteristic information and the relation characteristic information to a first artificial intelligence model, a score of a color combination between each of the colors included in the plurality of objects in the spatial image and an arbitrary color, and provide color recommendation information with respect to a space comprising the plurality of objects, based on the score of the color combination.

公开(公告)号：US20230419721A1

公开(公告)日：2023-12-28

申请号：US18244088

申请日：2023-09-08

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jungmin LEE ,  Hyungdong LEE

IPC: G06V40/16 ,  G06T7/00

CPC classification number: G06V40/172 ,  G06T7/0002 ,  G06V40/171 ,  G06T2207/20081 ,  G06T2207/20104 ,  G06T2207/30168

Abstract: A method of generating, by an electronic device, a high-quality person image from a low-quality person image by an artificial intelligence model may include identifying a low-quality person image, applying the low-quality person image as input to the artificial intelligence model, and obtaining, as output from the artificial intelligence model, the high-quality person image. The artificial intelligence model may be configured to recognize a first face by performing face identification and face recognition on the low-quality person image, using a face recognition artificial intelligence model, obtain the high-quality person image by performing image processing for enhancing an image quality of an area corresponding to the first face, using an image quality enhancement artificial intelligence model, and output the high-quality person image.