Samsung Electronics Co., Ltd.

Beijing Jingdong Shangke Information Technology Co., Ltd.

Beijing Jingdong Century Trading Co., Ltd.

Inha-industry Partnership Institute

Quarkdata Software Co., Ltd

Weihua Zhang

Fan Li

Jiangxu Wu

Ganglin Peng

Hongguang Zhang

Leifeng Kong

Yuefeng Wu

Changwei Wang

Ke Lin

Yingying Jiang

Man Zhang

Zhenbo Luo

Jinfu Wang

Xiangyu Zhu

Jaekeun Na

Li Zuo

Xiansong Song

Xuechao Cao

Sikun Yao

Shitao Song

Mengmeng Bai

Zhihao Chu

Xue Leng

Kyoung Seop Kwak

Wooshik Kang

Xinghui Yong

Shilei Liu

The disclosure relates to a communication method and system for converging a 5-Generation (5G) communication system for supporting higher data rates beyond a 4-Generation (4G) system with a technology for IoT. The disclosure may be applied to intelligent services based on the 5G communication technology and the IoT-related technology, such as smart home, smart building, smart city, smart car, connected car, health care, digital education, smart retail, security and safety services. An image processing method and apparatus, electronic device and computer readable storage medium, which belong to image processing field are provided. The method and apparatus, electronic device and computer readable storage medium include segmenting an image to be processed to obtain a target region in the image to be processed, and performing style transfer on the target region. The solution provided may effectively improve effects of image processing, and better meet requirements of practical application.

Image processing method and apparatus, electronic device and computer readable storage medium

The present disclosure provides a pedestrian re-identification method and apparatus. The pedestrian re-identification apparatus detects a pedestrian to be identified in a specified video frame, and within a specified time period before the capture time of the specified video frame, extracts all pedestrians appearing in the captured video frame and taking them to be historical pedestrians; calculating the feature distances between the pedestrian to be identified and the historical pedestrians; in order of feature distance, from small to large, extracting historical pedestrian identifications corresponding to a predetermined number of feature distances, and clustering the extracted historical pedestrian identifications so as to re-identify the pedestrians to be identified. The present disclosure effectively suppresses external noise interference and improves the success rate of pedestrian re-identification.

Pedestrian re-identification method and apparatus

An image processing apparatus including: at least one memory; and at least one processor coupled to the at least one memory and configured to implement: an image acquisition module configured to acquire an input image including an object region; a mask image generation module configured to generate a mask image based on the input image; and an image inpainting module configured to extract a fusion feature map corresponding to the input image using an encoding network according to the input image and the mask image, and to inpaint the object region in the input image using a decoding network based on the fusion feature map, to obtain an inpainting result.

Inpainting via an encoding and decoding network

Provided is a method for pose estimation in a device, the method comprising capturing an image; estimating poses of an object included in the captured image; obtaining skeleton information of the object based on the estimating of the poses of the object; and processing the skeleton information of the object for at least one of detecting blocking of the object, detecting the poses of the object and adjusting content based on detected virtual object distinct from human body poses.

Method and apparatus for pose processing

The invention discloses an augmented reality method and device, and relates to the field of computer technology. A specific implementation of the method includes: acquiring video information of a target, and acquiring real image information and real sound information of the target from the same; using the real image information to determine at least one image-based target state data, and using the real sound information to determine at least one sound-based target state data; fusing the image-based and sound-based target state data of the same type to obtain a target portrait data; and acquiring virtual information corresponding to the target portrait data, and superimposing the virtual information on the video information. This implementation can identify the current state of the target based on the image information and sound information of the target, and fuse the two identification results to obtain an accurate target portrait. Based on the target portrait, virtual information display matching the user status can be displayed, thereby improving augmented reality and user experience.

Augmented reality method and device fusing image-based target state data and sound-based target state data

The present disclosure provides drawing content processing method and device for a terminal apparatus. The method includes positioning a drawing focus of a user based on a drawing operation of the user and processing drawing content displayed on a screen of the terminal apparatus based on the positioned drawing focus.

Drawing content processing method and device for terminal apparatus, and terminal apparatus

A video sharing implementation method and system are provided, with the method including receiving a user's access request for a video sharing link which carries an address of a video and an identifier of a shared object, parsing the video sharing link to obtain the address of the video and the identifier of the shared object, playing the video according to the address of the video, and displaying the shared object corresponding to the identifier of the shared object in a video display interface, and jumping to a product link of the shared object in response to the user's selection of the shared object.

Video sharing implementation method and system

Provided are a terminal management framework and a terminal management method. The framework includes an application layer, a business layer, a protocol and message processing layer and a porting layer. The application layer includes a device user interface, a business logic module and a tree module. The business layer includes a software component management object module, a firmware update management object module and a lock and wipe management object module. The business logic module is configured to assemble a business logic based on a type of a session and a business type of the session, invoke an interface in a business module to process a business based on the business logic, and control a progress of business processing based on the business logic and a state of the business processing.

Terminal management framework and terminal management method

Disclosed herein is an Ultra-WideBand (UWB) ranging method using a narrowband interference suppression waveform. A transmission signal is transmitted to a target object. The transmission signal, reflected from the target object, is received. A template signal is generated by combining the narrowband interference suppression waveform and a channel estimation signal together. A correlation output signal is generated by convoluting the template signal and the received signal. A distance is calculated using a time delay when the correlation output signal has the maximum value thereof. The narrowband interference suppression waveform is any one of two waveforms that are expressed by the following Equation:()=(/2)+(/2)()=(/2)&#x2212;(/2)where g(t) is a basic UWB pulse waveform, &#x3b4;=(N+1/2)f, &#x3b4;=(N)/f, N is an integer, and fis the center frequency of a narrowband interference signal.

Ultra-wideband ranging method and system using narrowband interference supression waveform

Growing community of inventors

Beijing, China

Weihua Zhang