Huawei Technologies Co., Limited

Baidu Online Network Technology (beijing) Co., Ltd.

Lenovo (beijing) Limited

Tsinghua University

Beijing Baidu Netcom Science Technology Co., Ltd

Beijing Lenovo Software Ltd.

Apollo Intelligent Driving Technology (beijing) Co., Ltd.

Mudanjiang Linrun Pharama Excipients Llc.

Shenzhen Yinwang Intelligent Technologies Co., Ltd.

China General Nuclear Power Corporation

China Techenergy Co., Ltd

Chen Yang

Li Wang

Jiming Mao

Qingrui Sun

Dun Luo

Qian Ma

Zhihui Zhang

Fangfang Dong

Tizheng Wang

Manjun Xiao

Jinnan Liu

Ying Wang

Junfei Zhang

Ke Chen

Shisheng Zheng

Rongyao Fu

Xiaoe Wang

Jingduo Tian

Wenjing Liu

Mu Zhou

Xiaorong Gao

Zheng Tan

Zhaolei Xiao

Jingang Wang

Tianxing Yang

Jinlei Zhang

Jianxing Liao

Chen Su

Zhuo Sun

Jiamin Chen

Shuming Xu

Xinyi Yan

Bingchuan Liu

Ziyang Zhang

Li Yang

Weihua He

Kun Tian

Yunlong Zhan

Min Qi

Guojin Jiang

Baohua Ren

Weiqing Gu

Jianxin Ma

This application provides an image processing method, including: performing stabilization on two adjacent image frames of a video stream acquired by a camera to obtain cropped areas, and performing perspective distortion correction on the cropped areas obtained through stabilization. Because the cropped areas output after stabilization is performed on the two adjacent frames include same or basically same content, it can be ensured that a subsequently generated video is smooth and stable. In this application, position relationships, for perspective distortion correction, between the cropped areas obtained through stabilization are further mapped, so that degrees or effects of perspective distortion correction of the adjacent frames of the subsequently generated video are the same, in other words, degrees of transformation of a same object in the images are the same.

Image processing method and related device

The present disclosure provides a text checking method based on a knowledge graph, an electronic device and a medium. The method includes: obtaining a text of a contract to be checked; establishing a knowledge graph according to the text of the contract to be checked, the knowledge graph including a plurality of attributes and a plurality of attribute values corresponding to the plurality of attributes; and checking the text of the contract to be checked based on the knowledge graph.

Text checking method based on knowledge graph, electronic device, and medium

Methods for improving solubility of active pharmaceutical ingredients (APIs) through co-attriting the APIs with select excipients, especially solubility enhancing excipients, and the products prepared by the methods, are disclosed. Pharmaceutical compositions containing co-attrited mixture of an API with a solubility enhancing excipient and use of the pharmaceutical compositions for treatment of diseases or disorders are also disclosed.

Methods of improving pharmaceutical substance solubilization and products thereof

An image transformation method includes obtaining a first image for a target scenario by using a front-facing camera, where the target scenario includes a face of a target person; obtaining a target distance between the face of the target person and the front-facing camera; and when the target distance is less than a preset threshold, performing first processing on the first image to obtain a second image. The first processing includes performing distortion correction on the first image based on the target distance. The face of the target person in the second image is closer to a real appearance of the face of the target person than the face of the target person in the first image.

Image transformation method and apparatus

Embodiments of this application disclose a signal processing method, a radar system, and a vehicle. The method is applied to a radar system including an array antenna. The method includes: sequentially transmitting signals according to a first transmission sequence through M transmit antennas, where the first transmission sequence is different from a sequence that is formed by arranging the M transmit antennas based on spatial locations; receiving, through N receive antennas, echo signals that are formed after a target reflects the transmitted signals, where M and N are positive integers, and M is greater than 2; and measuring a parameter of the target based on the echo signals. According to the embodiments of this application, correlation between space and a Doppler phase shift is reduced by changing a switching order of transmit antennas.

Signal processing method, radar system, and vehicle

The present invention provides a virtual keyboard for inputting Chinese characters and a configuring method thereof, an input method, and a Chinese character input system. The configuring method includes the following steps: setting a geometric layout of the virtual keyboard; and setting initials and finals on available keys of the virtual keyboard respectively using a cost function-based search algorithm so as to obtain an optimal layout of initial keys and final keys, wherein the initial keys and the final keys in the optimal layout are set based on a minimum cost function value for spelling all Chinese syllables, and the minimum cost function value is a minimum sum of weighted distances of the initial keys and the final keys for all the Chinese syllables. When the Chinese characters are input by the virtual keyboard obtained by this method, the number of operation times and the movement distance can be reduced effectively and thus the input efficiency of the Chinese characters and the usability of the virtual keyboard are greatly improved.

Virtual keyboard for inputting Chinese characters and configuring method thereof, and Chinese character input system

Embodiments of the present disclosure provide a method and an apparatus for generating a simulation scene. The method includes: acquiring scene parameters of a benchmark scene, where a dimensionality of the scene parameters of the benchmark scene is M; inputting the scene parameters of the benchmark scene into an encoder that is trained, and acquiring encoding parameters according to an output result of the encoder, where a dimensionality of the encoding parameters is N, and N<M; adjusting the encoding parameters to obtain adjusted encoding parameters, and inputting respectively the adjusted encoding parameters into a decoder that is trained; and generating a simulation scene according to the scene parameters of the reconstructed scene that are output by the decoder. According to the method, generating massive simulation scenes similar to the benchmark scene based on the benchmark scene can be achieved, which meets the diversity requirements for the simulation scenes.

Method and apparatus for generating simulation scene

Embodiments of a method, apparatus, device and computer readable storage medium for classifying driving scenario data includes: acquiring a first driving scenario data set from a crowdsourcing platform, driving scenario data in the first driving scenario data set having been classified; generating a driving scenario classification model at least based on the first driving scenario data set, for classifying driving scenario data collected by a collection entity; acquiring a rule for classifying the driving scenario data, the rule is generated based on a result of classifying the driving scenario data collected by the collection entity using the driving scenario classification model; updating the driving scenario classification model at least based on the rule.

Method, apparatus, device and medium for classifying driving scenario data

Provided are a method and an apparatus for acquiring a control amount for a performance test of an unmanned vehicle, including: acquiring coordinates of y key points on a trajectory of a simulated obstacle vehicle and speeds at the y key points, where y&#x2265;2; acquiring trajectory equations of the obstacle vehicle between every two adjacent key points according to the coordinates of the y key points, where the trajectory equation is an ndegree polynomial equation, n&#x2265;2; acquiring accelerations of the obstacle vehicle between every two adjacent key points according to speeds at the y key points and a trajectory curve corresponding to the trajectory equation; for each running duration, according to the accelerations, acquiring a dynamic attribute and a coordinate when the obstacle vehicle has run for the running duration according to trajectories corresponding to the trajectory equations.

Method and apparatus for acquiring control amount for performance test of unmanned vehicle

Embodiments of the present disclosure provide a method and an apparatus for generating a simulation scene. The method includes: acquiring scene parameters of a benchmark scene, where a dimensionality of the scene parameters of the benchmark scene is M; inputting the scene parameters of the benchmark scene into an encoder that is trained, and acquiring encoding parameters according to an output result of the encoder, where a dimensionality of the encoding parameters is N, and N&#x3c;M; adjusting the encoding parameters to obtain adjusted encoding parameters, and inputting respectively the adjusted encoding parameters into a decoder that is trained; and generating a simulation scene according to the scene parameters of the reconstructed scene that are output by the decoder. According to the method, generating massive simulation scenes similar to the benchmark scene based on the benchmark scene can be achieved, which meets the diversity requirements for the simulation scenes.

A method for processing data and an apparatus thereof are provided. The method includes: projecting a first structure light and a second structure light onto a surface of a target object, wherein the first structure light is a stripe-structure light; capturing a first image comprising the target object; detecting first image information corresponding to the first structure light in the first image, wherein the first image information is stripe image information; detecting second image information corresponding to the second structure light in the first image; and obtaining a depth of the target object based on the first image information and the second image information.

Method for processing data and apparatus thereof

Image processing method and device are provided. The method includes: controlling a projector to project multi-stripe structured light and dot structured light onto an object, to form multiple light stripes and light spots between the light stripes on the surface of the object; acquiring a target image of the object having the light stripes and the light spots on the surface; obtaining a reference image including the light stripes and the light spots; calculating a first depth value at each light stripe in the target image based on feature information of the light stripes in the reference image and target image; calculating a second depth value at each light spot in the target image based on feature information of the light spots in the reference image and target image; and generating a depth image of the target image based on the first depth value and the second depth value.

Image processing method and device

Growing community of inventors

Beijing, China

Chen Yang