公开(公告)号：US20220319155A1

公开(公告)日：2022-10-06

申请号：US17419726

申请日：2020-12-29

Applicant: BOE Technology Group Co., Ltd.

Inventor： Yunhua LU ,  Hanwen LIU ,  Pablo NAVARRETE MICHELINI ,  Lijie ZHANG ,  Dan ZHU

IPC: G06V10/77 ,  G06V10/80 ,  G06V10/82 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04

Abstract: A method for processing an image is provided, including: acquiring an input image; performing down-sampling and feature extraction on the input image by an encoder network to obtain multiple feature maps; and performing up-sampling and feature extraction on the multiple feature maps by a decoder network to obtain a target segmentation image; processing levels between the encoder network and the decoder network for outputting feature maps with the same resolution are connected with each other, and the encoder network and the decoder network each includes one or more dense calculation blocks, and at least one convolution module in any dense computation block includes at least one group of asymmetric convolution kernels.

公开(公告)号：US20220201242A1

公开(公告)日：2022-06-23

申请号：US17278403

申请日：2020-05-29

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Yunhua LU ,  Ran DUAN ,  Guannan CHEN ,  Lijie ZHANG ,  Hanwen LIU

IPC: H04N7/01 ,  G06T7/50 ,  G06T7/269 ,  G06T3/40 ,  G06T7/246

Abstract: The present disclosure relates to the field of information display, and specifically to a method, device, computer readable storage medium, and electronic device for video frame interpolation. The method comprises: obtaining, based on two input frames, two initial optical flow maps corresponding to the two input frames; optimizing the initial optical flow maps to obtain target optical flow maps; obtaining an interpolation frame kernel, two depth maps and two context feature maps based on the two input frames; obtaining an output frame using a frame synthesis method based on the target optical flow maps, the depth maps, the context feature maps, and the interpolation frame kernel.

公开(公告)号：US20250104432A1

公开(公告)日：2025-03-27

申请号：US18580701

申请日：2022-12-19

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Jingtao XU ,  Hanwen LIU ,  Mingyue WANG

IPC: G06V20/52 ,  G06T7/215 ,  G06T7/246 ,  G06T7/292 ,  G06V10/74 ,  G06V10/764 ,  G06V40/16

Abstract: A method for managing a storage cabinet is provided. The method includes: acquiring face information of a user in response to the user approaching the storage cabinet, and determining feature information of the user according to the face information; acquiring a plurality of sets of image data in response to an operation of opening the storage cabinet by the user, a set of image data in the plurality of sets of image data including multiple frames of image data obtained by taking photographs of an exit location of the storage cabinet from different directions at a same time; determining change information of items in the storage cabinet according to the plurality of sets of image data; and outputting multimedia data related to at least one of the feature information or the items according to the feature information and the change information in the storage cabinet.

公开(公告)号：US20250095370A1

公开(公告)日：2025-03-20

申请号：US18018712

申请日：2022-02-23

Applicant: BOE Technology Group Co., Ltd.

Inventor： Zeyu SHANGGUAN ,  Hanwen LIU ,  Fanhao KONG

IPC: G06V20/52 ,  G06T3/40 ,  G06V40/10 ,  G06V40/20

Abstract: The present disclosure provides a traffic statistics collection method and apparatus. The method includes: obtaining a first image of a target place; performing body detection on the first image to obtain body detection boxes of respective target objects in the first image, where the body detection boxes indicate body areas of the respective target objects; for each target object of the respective target objects, determining a head detection box of the target object according to the body detection box of the target object, wherein the head detection box indicates a head area of the target object; and obtaining a traffic statistics result of the target place according to head detection boxes of the respective target objects.

公开(公告)号：US20210407041A1

公开(公告)日：2021-12-30

申请号：US17281291

申请日：2020-05-28

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Hanwen LIU ,  Pablo NAVARRETE MICHELINI ,  Dan ZHU ,  Lijie ZHANG

IPC: G06T3/40 ,  G06N3/08 ,  G06N3/04

Abstract: Disclosed are an image processing method and device, a training method of a neural network and a storage medium. The image processing method includes: obtaining an input image, and processing the input image by using a generative network to generate an output image. The generative network includes a first sub-network and at least one second sub-network, and the processing the input image by using the generative network to generate the output image includes, processing the input image by using the first sub-network to obtain a plurality of first feature images; performing a branching process and a weight sharing process on the plurality of first feature images by using the at least one second sub-network to obtain a plurality of second feature images; and processing the plurality of second feature images to obtain the output image.

公开(公告)号：US20210209459A1

公开(公告)日：2021-07-08

申请号：US16073195

申请日：2018-01-19

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Pablo NAVARRETE MICHELINI ,  Hanwen LIU

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: Provided are a processing method and system for a convolutional neural network, and a computer-readable medium, the processing method includes training a generator and training a discriminator, wherein training a generator includes: extracting a low-resolution color image from a high-resolution color image; training parameters of a generator network, by using the low-resolution color image and a noise image as an input image, based on parameters of a discriminator network, and reducing a generator cost function training a discriminator includes: inputting an output image of the trained generator network and the high-resolution color image to the discriminator network, respectively; training parameters of the discriminator network by reducing a discriminator cost function (S204) the generator cost function and the discriminator cost function represent a degree in which the output image of the generator network corresponds to the high-resolution color image.

公开(公告)号：US20210209448A1

公开(公告)日：2021-07-08

申请号：US16069376

申请日：2017-11-17

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Pablo NAVARRETE MICHELINI ,  Hanwen LIU

IPC: G06N3/04 ,  G06N3/08

Abstract: A convolutional neural network, and a processing method for the same. The method includes: using an activation recorder layer as an activation function layer in the convolutional neural network, wherein in response to that a probe image with contents is inputted to the convolutional neural network, the activation recorder layer performs an activation operation the same as the activation function layer does and records an activation result of the activation operation; modifying the convolutional neural network, wherein step of modifying includes replacing the activation recorder layer with a hidden layer that uses the recorded activation result; and inputting an analysis image to the modified convolutional neural network as an input image, so as to output an output image of the modified convolutional neural network, thereby analyzing a forward effect or a backward effect between the input image and the output image, the analysis image being a pixel-level binary image.

公开(公告)号：US20210049447A1

公开(公告)日：2021-02-18

申请号：US17042265

申请日：2019-12-23

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Pablo NAVARRETE MICHELINI ,  Hanwen LIU ,  Yunhua LU

IPC: G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06K9/62

Abstract: A processing method and a processing device of a neural network, an evaluation method of the neural network, a data analysis method and device, and a storage medium are provided. The processing method of the neural network includes: processing an input matrix input to an N-th nonlinear layer in at least one nonlinear layer by using the N-th nonlinear layer to obtain an output matrix output by the N-th nonlinear layer; according to the input matrix and the output matrix, performing linearization processing on the N-th nonlinear layer to determine an expression of a linear function corresponding to the N-th nonlinear layer.

公开(公告)号：US20200057921A1

公开(公告)日：2020-02-20

申请号：US16487885

申请日：2018-10-31

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Pablo NAVARRETE MICHELINI ,  Hanwen LIU

IPC: G06K9/62 ,  G06T9/00

Abstract: Disclosed are an image classification and conversion method, apparatus, image processor and training method thereof, and medium. The image classification method includes receiving a first input image and a second input image; performing image encoding on the first input image by utilizing n stages of encoding units connected in cascades to produce a first output image, wherein n is an integer greater than 1, and wherein as for 1≤i

公开(公告)号：US20240233074A9

公开(公告)日：2024-07-11

申请号：US18396866

申请日：2023-12-27

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Pablo NAVARRETE MICHELINI ,  Wenbin CHEN ,  Hanwen LIU ,  Dan ZHU

IPC: G06T3/4046 ,  G06N3/08 ,  G06T3/4053 ,  G06T5/50

CPC classification number: G06T3/4046 ,  G06N3/08 ,  G06T3/4053 ,  G06T5/50

Abstract: An image processing method, an image processing device, a training method of a neural network, an image processing method based on a combined neural network model, a constructing method of a combined neural network model, a neural network processor, and a storage medium are provided. The image processing method includes: obtaining, based on an input image, initial feature images of N stages with resolutions from high to low, N is a positive integer and N>2; performing, based on initial feature images of second to N-th stages, cyclic scaling processing on an initial feature image of a first stage, to obtain an intermediate feature image; and performing merging processing on the intermediate feature image to obtain an output image. The cyclic scaling processing includes hierarchically-nested scaling processing of N−1 stages, and scaling processing of each stage includes down-sampling processing, concatenating processing, up-sampling processing, and residual link addition processing.