Lg Electronics Inc.

Jingyeong Kim

Jaehyun Lim

Joonyoung Park

Yongjoon Jeon

Byeongmoon Jeon

Seungwook Park

Jaewon Sung

Younghee Choi

Taeil Chung

Sangchul Kim

Jungsun Kim

Sungjin Kim

Taehyun Kim

Dongho Kim

Dongkyu Lee

Jeonghyu Yang

Jiwon Lee

Seoksoo Lee

Aram Kim

Jaehyun An

Junhyeong Kim

The method for deriving a temporal motion vector predictor according to the present invention comprises the steps of: selecting a reference picture for a current block; deciding a predictor block corresponding to a predetermined storage unit block, as a reference prediction unit for the current block, in the reference picture; and deriving the temporal motion vector predictor from motion information of the decided reference prediction unit. The present invention enhances image compression efficiency.

Method for encoding image and non-transitory computer readable storage medium storing a bitstream generated by a method

The present disclosure relates to an image display apparatus. The image display apparatus according to an embodiment of the present disclosure comprises: a signal processor configured to perform image processing of an input image, and audio processing of audio corresponding to the input image; a virtual sensor device configured to receive image and audio information processed by the signal processor; a sensor device configured to collect externally captured image information or sound information; and an artificial intelligence (AI) processor configured to perform the image processing of the input image or the audio processing based on AI using the image and audio information from the virtual sensor device, and the image or sound information from the sensor device. Accordingly, the image display apparatus may operate based on AI.

Image display apparatus with AI-based image processing

Disclosed is a display device. A display device according to the present invention comprises: a display panel; a backlight unit located behind the display panel and providing light to the display panel; and a guide panel that is located at an edge of the display panel, and includes a panel support part located between the display panel and the backlight unit and an extension part extending from the panel support part and surrounding a side surface of the backlight unit. The backlight unit includes: a light guide plate; and a light source module located at a light incident part and irradiating at least one side surface of the light guide plate with light, and the panel support part includes a rib protruding toward the light source module and facing the front surface of the light source module.

Display device

An artificial intelligence (AI)-based air conditioner can include a communication unit and a processor. The communication can receive an image including member data from an image acquisition device, where the member data are associated with one or more different members of a member group and are used to distinguish the members from each other. The processor can recognize the member data from the received image, acquire operation data including operation conditions of the air conditioner, which are desired by the members, based on the recognized member data, store member information including the member data and the operation data in a database, analyze the operation conditions of the air conditioner, which are desired by the members, with respect to each member based on the member information corresponding to the member group stored in the database, and autonomously driving the air conditioner for the different members based on the analyzed operation conditions.

Artificial intelligence-based air conditioner

Disclosed is a method and device for image processing. The image processing device may include a processor and a controller. The processor may include an artificial intelligence (AI) image processing model trained in image processing through learning, and an arithmetic logic unit (ALU) configured to perform a computation involved in image processing using the AI image processing model. According to the present disclosure, image processing using a deep neural network (DNN) is possible in an edge device.

Method and device for image processing

Method for encoding and decoding image and device using same

Disclosed herein is a speech recognition method in a distributed network environment. A method of performing a speech recognition operation in an edge computing device includes receiving a natural language understanding (NLU) model from the cloud server, storing the received NLU model, receiving voice data spoken by a user from the client device, performing a natural language processing operation on the received voice data using the NLU model, performing speech recognition according to the natural language processing operation, and transmitting a result of the speech recognition to the client device. At least one of the edge computing device, a voice recognition device, and a server may be associated with an artificial intelligence module, a drone (an unmanned aerial vehicle (UAV)), a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to a 5G service, and the like.

Speech recognition method in edge computing device

Method and apparatus for deriving a temporal motion vector predictor are described. A method for deriving a temporal motion vector predictor according to the present invention includes selecting a reference picture for a current block, determining a prediction block that corresponds to a predetermined storage unit block in the reference picture as a reference prediction unit for the current block, and deriving a temporal motion vector predictor from motion information of the determined reference prediction unit. According to the present invention, image compression efficiency can be improved.

A method for deriving a temporal motion vector predictor includes the steps of: selecting a reference picture for a current block; deciding a predictor block corresponding to a predetermined storage unit block, as a reference prediction unit for the current block, in the reference picture; and deriving the temporal motion vector predictor from motion information of the decided reference prediction unit.

Growing community of inventors

Seoul, South Korea

Jingyeong Kim