-
51.发明授权公开(公告)号：US12015873B1
公开(公告)日：2024-06-18
申请号：US17638098
申请日：2021-01-05
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Lihua Geng , Xitong Ma , Ran Duan , Xiaodong Shi
IPC: H04N7/01
CPC classification number: H04N7/0127
Abstract: An image transmission device includes: a frequency detector configured to detect a frame rate of an image frame and output a frequency switching mark signal when detecting that the frame rate changes; a frequency configuration device configured to output a first configuration signal according to a safe frequency step value in response to the frequency switching mark signal; a frequency processor configured to output a reference clock signal, adjust a frequency of the output reference clock signal repeatedly according to the first configuration signal, and until a frequency of an adjusted reference clock signal is substantially equal to a frequency of a reference clock signal corresponding to a changed frame rate, end adjustment; and an image frame transmitter configured to convert a format of the image frame into a format corresponding to the image frame transmitter according to the adjusted reference clock signal, and output the format-converted image frame.
-
公开(公告)号：US20240062344A1
公开(公告)日：2024-02-22
申请号：US17764458
申请日：2021-03-22
Applicant: BOE Technology Group Co., Ltd.
Inventor： Ran Duan , Dan Zhu , Yanhong Wu , Guannan Chen
CPC classification number: G06T5/005 , G06T3/40 , G06T5/002 , G06T5/30 , G06T5/50 , G06T7/254 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/20016 , G06T2207/20032 , G06T2207/20081 , G06T2207/20084 , G06T2207/20224
Abstract: An image processing method and an image processing device are provided. The image processing method includes performing at least one of a scratch repairing step, a dead point repairing step, a denoising step and a color cast correcting step on a to-be-processed video frame. According to the embodiments of the present disclosure, it is able to repair a scratch and a dead point, remove a noise and/or correct color cast for a video frame, thereby to improve a display effect of the video frame.
-
公开(公告)号：US11800053B2
公开(公告)日：2023-10-24
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
CPC classification number: H04N7/0137 , G06T3/40 , G06T7/246 , G06T7/269 , G06T7/50 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221
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：US11689693B2
公开(公告)日：2023-06-27
申请号：US17265568
申请日：2020-04-30
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Yunhua Lu , Guannan Chen , Ran Duan , Lijie Zhang , Hanwen Liu
CPC classification number: H04N7/0135 , G06N20/00 , H04N7/0145
Abstract: A video frame interpolation method and device, and a computer-readable storage medium are described. The method includes: inputting at least two image frames into a video frame interpolation model to obtain at least one frame-interpolation image frame, training the initial model using a first loss to obtain a reference model, copying the reference model to obtain three reference models with shared parameters, selecting different target sample images according to a preset rules to train the first/second reference model to obtain a first/second frame-interpolation result; selecting third target sample images from the first/second frame-interpolation result to train the third reference model to obtain the frame-interpolation result, obtaining a total loss of the first training model based on the frame-interpolation result and the sample images, adjusting parameters of the first training model based on the total loss, and using a parameter model via a predetermined number of iterations as the video frame interpolation model.
-
公开(公告)号：US20230156147A1
公开(公告)日：2023-05-18
申请号：US17625714
申请日：2021-03-02
Applicant: BOE Technology Group Co., Ltd.
IPC: H04N7/01
CPC classification number: H04N7/012 , H04N7/0102
Abstract: A video image de-interlacing method is provided. The method-includes: acquiring a single frame of original video image; extracting odd field data and even field data in an original video image; performing N-1 times of down-sampling on the odd field data to obtain N-1 odd field data with different resolutions and performing N-1 times of down-sampling on the even field data to obtain N-1 even field data with different resolutions; combining odd field data and even field data with the same resolution to obtain a down-sampled image; and inputting the original video image and the down-sampled image to the de-interlacing network for de-interlacing.
-
Patent Agency Ranking
公开(公告)号：US11508144B2
公开(公告)日：2022-11-22
申请号：US16760847
申请日：2019-09-17
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Ran Duan
Abstract: The present disclosure provides an object detection method and an object detection device. The object detection device includes: a heterogeneous processor and a memory, the heterogeneous processor including: a processing unit and a programmable logic unit, wherein the programmable logic unit is configured to receive a to-be-detected image, perform feature extraction on the to-be-detected image, and write an extracted feature into the memory; the processing unit is configured to read the feature from the memory, perform target object detection according to the feature, and output a detection result to the programmable logic unit; and the programmable logic unit is further configured to receive the detection result, generate prompt information according to the detection result, and output the prompt information.
-
公开(公告)号：US11412274B2
公开(公告)日：2022-08-09
申请号：US16305189
申请日：2018-04-13
Applicant: BOE Technology Group Co., Ltd.
Inventor： Zhiguo Zhang , Ran Duan
IPC: H04N21/2343 , H04N21/2183 , H04N21/4402 , H04N21/231 , H04N21/44
Abstract: The present disclosure relates to a video transmission method, apparatus and computer-readable storage medium in the field of video play. The method includes: acquiring a first video frame and a second video frame of a video to be transmitted; acquiring difference information of the second video frame relative to the first video frame; and sending the difference information to a video receiving apparatus, the difference information being used for instructing the video receiving apparatus to generate the second video frame based on the difference information and the first video frame after receiving the first video frame. The needed bandwidth is small in the video transmission method of the present disclosure, the video transmission may not be restricted by the distance, and thus video transmission has a high flexibility.
-
公开(公告)号：US11361553B2
公开(公告)日：2022-06-14
申请号：US16332906
申请日：2018-06-13
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Ran Duan , Xiaojun Tang
Abstract: A method for tracking an at least partially occluded object. The method includes recognizing a non-occluded portion of the at least partially occluded object in an input image; generating a simulated image of the at least partially occluded object based on features of the non-occluded portion extracted from the input image; determining first coordinates of the at least partially occluded object in a first coordinate system; and converting the first coordinates of the at least partially occluded object in the first coordinate system into second coordinates in a second coordinate system defined in a display apparatus.
-
公开(公告)号：US20210407460A1
公开(公告)日：2021-12-30
申请号：US17361399
申请日：2021-06-29
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Xian Wang , Ran Duan , Masakazu Okamura
Abstract: Provided is a method for displaying an image including: acquiring a to-be-displayed image; correcting the to-be-displayed image based on a target look-up table, wherein in the target look-up table, at least one of the original pixel values and a corresponding corrected pixel value satisfy: an absolute value of a difference between a first chroma and a second chroma is less than or equal to a chroma difference threshold, wherein the first chroma is a chroma of a first pixel, a pixel value of the first pixel being acquired by converting the original pixel value, and the second chroma is a chroma of a second pixel displayed by the display device, a pixel value of the second pixel being acquired by converting the corrected pixel value; and displaying a corrected to-be-displayed image.
-
公开(公告)号：US11210992B2
公开(公告)日：2021-12-28
申请号：US16649356
申请日：2019-08-21
Applicant: BOE Technology Group Co., Ltd.
Inventor： Ran Duan
Abstract: A display controller is provided. The display controller includes n field-programmable gate arrays (FPGAs) (n is an integer greater than 1). A respective one of the n FPGAs includes a first input circuit and an output circuit and a first process circuit connected between the first input circuit and the output circuit. The first input circuit is configured to receive a respective one first sub-image corresponding to the respective one of the n FPGAs. The n first sub-images are combined to form one frame of initial image. The first process circuit is configured to enhance image-resolution of the respective one first sub-image to obtain a respective one second sub-image and the output circuit is configured to deliver the respective one second sub-image corresponding to the respective one of the n FPGAs to a timing-controller.
-
-
-
-
-
-
-
-
-
Search Results
64
records
(took 0.027 seconds)
