公开(公告)号：US20240233061A9

公开(公告)日：2024-07-11

申请号：US18491051

申请日：2023-10-20

Applicant: SEOUL NATIONAL UNIVERSITY HOSPITAL ,  Electronics and Telecommunications Research Institute

Inventor： Eun Ju JEONG ,  Young Gon KIM ,  Ju Seong JIN ,  Dae Youn KIM ,  Seung Jae CHOI

IPC: G06T1/00 ,  G06T7/50 ,  G06T7/70

CPC classification number: G06T1/0014 ,  G06T7/50 ,  G06T7/70 ,  G06T2207/20081

Abstract: Provided are a device and method for estimating a pose of an object. The method includes inputting a labeled source image and an unlabeled target image to a recognition model for generating training data, training the recognition model to generate object information of the unlabeled target image, determining the generated object information to be a pseudo label of the unlabeled target image, and training a pose estimation model for estimating a pose of an object by inputting the pseudo-labeled target image and the labeled source image to the pose estimation model.

公开(公告)号：US20150228186A1

公开(公告)日：2015-08-13

申请号：US14615469

申请日：2015-02-06

Applicant: Electronics and Telecommunications Research Institute

Inventor： Eun Ju JEONG ,  Won Ick JANG ,  Sung Jae YUN ,  Soon Mo KIM

IPC: G08C17/02

CPC classification number: G08C17/02 ,  G08C2201/42 ,  H04Q9/00

Abstract: A control method of a gateway communicating with at least one sensor and a service server is provided. The control method may include receiving, from the at least one sensor, first information comprising at least one of bioinformation, disaster prevention information, and public information, transmitting the first information to the service server when the first information meets a first standard, or processing the first information in a data format of the first standard and transmitting the processed first information to the service server when the first information does not meet the first standard, receiving, from the service server, a control command to control the at least one sensor, and transmitting the control command to a sensor corresponding to the control command.

Abstract translation: 提供了与至少一个传感器和服务服务器通信的网关的控制方法。 所述控制方法可以包括从所述至少一个传感器接收包括生物信息，防灾信息和公共信息中的至少一个的第一信息，当所述第一信息满足第一标准时，将所述第一信息发送到所述服务服务器，或者处理 所述第一信息以所述第一标准的数据格式发送，并且当所述第一信息不满足所述第一标准时将所处理的第一信息发送到所述服务服务器，从所述服务服务器接收控制所述至少一个传感器的控制命令， 以及将所述控制命令发送到与所述控制命令相对应的传感器。

公开(公告)号：US20240135481A1

公开(公告)日：2024-04-25

申请号：US18491051

申请日：2023-10-19

Applicant: SEOUL NATIONAL UNIVERSITY HOSPITAL ,  Electronics and Telecommunications Research Institute

Inventor： Eun Ju JEONG ,  Young Gon KIM ,  Ju Seong JIN ,  Dae Youn KIM ,  Seung Jae CHOI

IPC: G06T1/00 ,  G06T7/50 ,  G06T7/70

CPC classification number: G06T1/0014 ,  G06T7/50 ,  G06T7/70 ,  G06T2207/20081

Abstract: Provided are a device and method for estimating a pose of an object. The method includes inputting a labeled source image and an unlabeled target image to a recognition model for generating training data, training the recognition model to generate object information of the unlabeled target image, determining the generated object information to be a pseudo label of the unlabeled target image, and training a pose estimation model for estimating a pose of an object by inputting the pseudo-labeled target image and the labeled source image to the pose estimation model.

公开(公告)号：US20230237821A1

公开(公告)日：2023-07-27

申请号：US18099447

申请日：2023-01-20

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Eun Ju JEONG

IPC: G06V20/70 ,  G06V10/774 ,  G06V20/64

CPC classification number: G06V20/70 ,  G06V10/774 ,  G06V20/64

Abstract: A method and apparatus for recognizing a three-dimensional (3D) object based on deep learning are provided. An object recognition apparatus constructs a data set including a virtual image and a real image, in which the data set includes labeled data corresponding to the virtual image and the real image, and unlabeled data corresponding to the virtual image and the real image. The object recognition apparatus inputs the data set to a recognition model for pre-trained object recognition based on self-supervised learning to perform the object recognition and acquire object information according to the object recognition.

公开(公告)号：US20150099961A1

公开(公告)日：2015-04-09

申请号：US14500741

申请日：2014-09-29

Applicant: Electronics and Telecommunications Research Institute

Inventor： Yong Jae LEE ,  Bong Kyu KIM ,  Hyun Woo SONG ,  Chang Geun AHN ,  Eun Ju JEONG ,  Hyung Wook NOH ,  Won Ick JANG

IPC: A61B5/00

CPC classification number: A61B5/0095

Abstract: Provided is a miniaturized photo-acoustic probe for a clinical image capable of effectively measuring a photo-acoustic signal by making an ultrasonic axis and an optical axis parallel. The photo-acoustic probe for a clinical image includes a laser generator configured to generate a laser beam, an ultrasound transducer disposed to be parallel to the laser generator and configured to analyze ultrasound output from an object, first and second reflectors configured to receive ultrasound generated in an axis identical to that of the laser beam generated by the laser generator, and a medium material configured to allow the laser to be transmitted from the first reflector to the object and increase ultrasound reflectivity of the first and the second reflector.

Abstract translation: 提供了一种用于临床图像的小型化光声探头，其能够通过使超声波轴和光轴平行来有效地测量光声信号。 用于临床图像的光声探头包括被配置为产生激光束的激光发生器，设置成平行于激光发生器并被配置为分析来自物体的超声波输出的超声波换能器，被配置为接收产生的超声的第一和第二反射器 在与由激光发生器产生的激光束的轴线相同的轴上，以及介质材料，被配置为允许激光从第一反射器传送到物体并增加第一和第二反射器的超声波反射率。