公开(公告)号：US20240378178A1

公开(公告)日：2024-11-14

申请号：US18584048

申请日：2024-02-22

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jae Yoon JANG ,  Jae Hong KIM ,  Ho Sub YOON

IPC: G06F16/11 ,  G06V40/16

Abstract: The present invention relates to a method and apparatus for re-registering pre-registered identity information in a new identity recognition system. A method of re-registering identity feature information in an identity recognition system according to an embodiment of the present disclosure may include: identifying one or more first identity feature information calculated by the first feature calculation device and stored in a database; generating one or more latent space information by inputting the one or more first identity feature information into a specific model for latent space estimation; generating one or more second identity feature information by inputting the one or more latent space information into a second feature calculation device; and storing the one or more second identity feature information in a new database.

公开(公告)号：US20240233145A9

公开(公告)日：2024-07-11

申请号：US18490386

申请日：2023-10-19

Applicant: Electronics and Telecommunications Research Institute

Inventor： Ho Sub YOON ,  Jae Hong KIM ,  Jong Won MOON ,  Jae Yoon JANG

IPC: G06T7/292 ,  G06V10/74 ,  G06V10/774 ,  G06V10/80

CPC classification number: G06T7/292 ,  G06V10/761 ,  G06V10/774 ,  G06V10/80 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20221

Abstract: Provided are a device and method for tagging training data. The method includes detecting and tracking one or more objects included in a video using artificial intelligence (AI), when there is an object to be split in a result of tracking the detected objects, splitting the object in object units, and when there are identical objects to be merged among split objects, merging the objects.

公开(公告)号：US20240135556A1

公开(公告)日：2024-04-25

申请号：US18490386

申请日：2023-10-18

Applicant: Electronics and Telecommunications Research Institute

Inventor： Ho Sub YOON ,  Jae Hong KIM ,  Jong Won MOON ,  Jae Yoon JANG

IPC: G06T7/292 ,  G06V10/74 ,  G06V10/774 ,  G06V10/80

CPC classification number: G06T7/292 ,  G06V10/761 ,  G06V10/774 ,  G06V10/80 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20221

Abstract: Provided are a device and method for tagging training data. The method includes detecting and tracking one or more objects included in a video using artificial intelligence (AI), when there is an object to be split in a result of tracking the detected objects, splitting the object in object units, and when there are identical objects to be merged among split objects, merging the objects.