公开(公告)号：US20190392254A1

公开(公告)日：2019-12-26

申请号：US16563531

申请日：2019-09-06

Applicant: LG ELECTRONICS INC.

Inventor： Seungkyun OH ,  Sanghoon KIM ,  Jinseok IM

IPC: G06K9/62 ,  G06K9/46 ,  G06N3/08 ,  G06N3/04 ,  B25J11/00 ,  B25J9/16

Abstract: An artificial intelligence moving agent is provided. The artificial intelligence moving agent includes: a camera configured to photograph an image, and a processor configured to photograph an object, acquire type information of the object by providing an image of the photographed object to an artificial intelligence model, acquire correction type information designated by a user with respect to the image of the photographed object, and train the artificial intelligence model by using the correction type information.

公开(公告)号：US20210165996A1

公开(公告)日：2021-06-03

申请号：US16865986

申请日：2020-05-04

Applicant: LG ELECTRONICS INC.

Inventor： Seongmock YOO ,  Seung-Kyun OH ,  Jinseok IM ,  Sanghoon KIM

IPC: G06K9/00 ,  G06N3/08 ,  G06K9/62

Abstract: An automatic labeling apparatus for object recognition and a method therefor are provided. The automatic labeling apparatus for object recognition is configured to apply an object recognition algorithm to each of a plurality of image frames so as to recognize an object, and in response to a determination that an object recognition result in at least one first image frame among the image frames corresponds to a predetermined error condition, automatically generate a data set on an object which is a target of object recognition by using an object recognition result of a second image frame other than the first image frame among the image frames and an object image of the first image frame. The object recognition algorithm, which is a neural network model generated through machine learning, may be stored in a memory or provided through a server in an artificial intelligence environment through a 5G network.

公开(公告)号：US20210034972A1

公开(公告)日：2021-02-04

申请号：US16814578

申请日：2020-03-10

Applicant: LG ELECTRONICS INC.

Inventor： Seung-Kyun OH ,  Jinseok IM ,  Sanghoon KIM

IPC: G06N3/08 ,  G06N3/04

Abstract: Disclosed is a batch normalization layer training method, which may be used in a neural network learning apparatus having limited operational processing capability and storage space. A batch normalization layer training method according to an embodiment of the present disclosure may perform batch normalization transform by setting the gradients of the standard deviation and the mean of the loss function to zero, and applying a normalized statistic value obtained from an initial neural network or a previous neural network to the gradient of the loss function. The neural network learning apparatus of the present disclosure may be connected or converged with an Artificial Intelligence module, an Unmanned Aerial Vehicle (UAV), a robot, an Augmented Reality (AR) apparatus, a Virtual Reality (VR), a 5G network service-related apparatus, etc.

公开(公告)号：US20160309178A1

公开(公告)日：2016-10-20

申请号：US15037594

申请日：2014-11-20

Applicant: LG ELECTRONICS INC.

Inventor： Jaewon HA ,  Naeri PARK ,  Sungho BAE ,  Jinseok IM ,  Cheoijoo LEE ,  Hyunsoo KIM

IPC: H04N19/52 ,  H04N19/105 ,  H04N19/172 ,  H04N19/159 ,  H04N19/167 ,  H04N19/119 ,  H04N19/139

CPC classification number: H04N19/52 ,  H04N19/436 ,  H04N19/82

Abstract: In a method for processing a video signal, according to the present invention, a first video decoder can extract motion information for inter prediction on a current half frame from a bitstream, a second video decoder can perform the inter prediction on the current half frame by using the extracted motion information, and the first video decoder can restore the inter-predicted current half frame. Accordingly, the coding time of a video sequence can be reduced.

Abstract translation: 在根据本发明的视频信号处理方法中，第一视频解码器可以从比特流中提取当前半帧上的帧间预测的运动信息，第二视频解码器可以在当前半帧上执行帧间预测， 使用所提取的运动信息，并且第一视频解码器可以恢复帧间预测的当前半帧。 因此，可以减少视频序列的编码时间。