Peking University

Peng Cheng Laboratory

Byd Company Limited

Huawei Technologies Co., Limited

Shenzhen Ucloudlink New Technology Co., Ltd.

Wen Gao

Qinghai Zeng

Qufang Huang

Yi Guo

Ronggang Wang

Zhenyu Wang

Kui Fan

Xi Xie

Yaowei Wang

Yonghong Tian

Yubo Lian

Ge Li

Siwei Ma

Heping Ling

Jing Wang

Zhihui Gong

Wenji Liu

Chuang Ma

Yong Xiong

Lei Yan

Yi Ting Shao

Yun Jiang

Yun Liang

Tao Wei

Wen Ji

Xinbei Bai

Chang Wen Chen

Bo Teng

Jianhui Chang

This application discloses an image processing method, device, system, electronic equipment, and storage medium, applied at the encoding end. The method includes extracting a one-dimensional feature vector from an original image block; transforming the original image block into a multidimensional feature map based on the one-dimensional feature vector; quantizing and encoding the one-dimensional feature vector to generate a first code stream; discretely encoding the multidimensional feature map to generate a second code stream, thereby efficiently compressing the spatial-independent vector and the multidimensional feature map; and sending the first and second code streams to the decoding end. Since the encoding stream comprises two layers each representing different types of image information, image reconstruction from the two-layer code streams maintains information integrity even at low bit rates, thus improving visual effects and experience.

Method, device, system, electronic device, and storage medium for image processing

The present disclosure belongs to the field of vehicles, and relates to a battery energy processing device and method and a vehicle, which can charge batteries during self-heating of the batteries. The battery energy processing device includes: an energy exchange interface; a first circuit, wherein a first end of the first circuit is connected with the energy exchange interface, and a second end of the first circuit is connected with a battery; a second circuit, wherein a first end of the second circuit is connected with the battery; an energy storage device, connected with a second end of the second circuit; and a controller, configured to: in a first preset state, control the second circuit to charge and discharge the battery to heat the battery, and control the first circuit to receive energy from the energy exchange interface and output the energy to the battery to charge the battery.

Battery energy processing apparatus and method, and vehicle

A visual computing system is disclosed. The visual computing system may include a front-end device, an edge service and a cloud service which are in communication connection, the front-end device is configured to output compressed video data and feature data, the edge service is configured to store the video data, and converge the feature data, transmit various types of data and control commands, and the cloud service is configured to store algorithm models used to support various applications, and return a model stream according to a model query command, realizing a data transmission architecture with multiple streams of video stream, feature stream, and model stream in parallel, and a system architecture of end, edge, and cloud collaboration.

Scalable visual computing system

A method and a device for encoding or decoding based on an inter-frame prediction. The method includes steps of: determining a temporal motion vector prediction value of a to-be-processed coding unit, where the temporal motion vector prediction value is a temporal motion vector prediction value of a sub-block, a temporal motion vector of which is obtainable through prediction, in sub-blocks adjacent to the to-be-processed coding unit and/or sub-blocks in the to-be-processed coding unit; determining a motion vector residual prediction value of the to-be-processed coding unit according to the temporal motion vector prediction value; determining a motion vector of a sub-block in the to-be-processed coding unit according to the temporal motion vector prediction value and the motion vector residual prediction value and performing a motion compensation according to the motion vector of the sub-block in the to-be-processed coding unit to determine a prediction block of the to-be-processed coding unit.

Method and device for encoding or decoding based on inter-frame prediction

Provided are a point cloud attribute prediction method and prediction device based on a filter. The method comprises a coding method and a decoding method, and the device comprises a coding device and a decoding device. The method comprises: determining K nearest neighbor points of the current point; determining a filter matrix; and determining an attribute prediction value of the current point according to the filter matrix. Therefore, the compression performance of a point cloud attribute can be improved by means of selecting an appropriate filter.

Point cloud attribute prediction method and device based on filter

Disclosed is a method and system for achieving optimal separable convolutions, the method is applied to image analyzing and processing and comprises steps of: inputting an image to be analyzed and processed; calculating three sets of parameters of a separable convolution: an internal number of groups, a channel size and a kernel size of each separated convolution, and achieving optimal separable convolution process; and performing deep neural network image process. The method and system in the present disclosure adopts implementation of separable convolution which efficiently reduces a computational complexity of deep neural network process. Comparing to the FFT and low rank approximation approaches, the method and system disclosed in the present disclosure is efficient for both small and large kernel sizes and shall not require a pre-trained model to operate on and can be deployed to applications where resources are highly constrained.

Method and system for achieving optimal separable convolutions

A method for deriving motion vector is provided, this method includes: obtaining a space domain motion vector prediction and a time domain motion vector prediction of adjacent blocks of a coding unit in a predetermined direction; performing a filtering operation on the space domain motion vector and the time domain motion vector prediction to obtain the space domain motion vector prediction and the time domain motion vector prediction of the filtered adjacent blocks; determining, according to a predetermined inter-frame prediction mode, reference motion vectors of a current block in four side directions by using the space domain motion vector prediction and the time domain motion vector prediction of the filtered adjacent blocks and a coordinate position of the current block in the coding unit; and deriving motion vectors of the current block according to the reference motion vectors and the coordinate position of the current block in the coding unit.

Method for deriving motion vector, and electronic device of current block in coding unit

Embodiments of the present disclosure provide a method and device for selecting a context model of a quantized coefficient end flag. The method comprises: obtaining a scanning position POS of a non-zero coefficient corresponding to current quantized coefficient end flag in a specific scanning order; wherein the scanning position POS is a subscript of the non-zero coefficient in the scanning order; configuring a first context model array, and using a fixed value as the base to calculate the logarithmic value of the value of the scanning position POS plus 1, and according to the logarithmic value, selecting a first context model from the first context model array; and using the first context model to encode or decode a binary symbol of the current quantized coefficient end flag. According to the technical solution of the present application, it is able to improve encoding and decoding efficiency for a quantized coefficient end flag, thereby further improve the efficiency of video encoding and decoding.

Method and device for selecting context model of quantization coefficient end flag bit

An embodiment of the present description provides a decoding method and device for a quantization block as well as an electronic device. The method comprises: determining the scanning order of quantization coefficients in the quantization block, initializing the scanning position of the quantization coefficients, and decoding a run-length; adding a subscript value of the current scanning position and the value of the run-length to obtain the scanning position of nonzero coefficients, decoding the values of the nonzero coefficients; judging whether the subscript value of the nonzero coefficients is the maximum subscript value, if yes, ending the decoding of the quantization block; if not, judging whether there are undecoded nonzero coefficients, and if there are no undecoded nonzero coefficients, ending the decoding of the quantization block; if there are undecoded nonzero coefficients, adding 1 to the subscript value of the decoded nonzero coefficients to obtain an updated current scanning position, taking the current scanning position as the initial scanning position to decode the next run-length until the decoding of the quantization block is completed. The technical solution of the present application can improve the decoding efficiency of quantization block.

Decoding method and device for quantization block, video decoding method, and electronic device

Growing community of inventors

Shenzhen, China

Wen Gao