-
公开(公告)号：US11436787B2
公开(公告)日：2022-09-06
申请号：US16335350
申请日：2018-09-06
Inventor： Xuefeng Wang , Yukun Sun , Bin Zhao , Lixin Wang , Xi Li , Jianwen Suo , Wenyu Li , Qingwen Fan , Jinbao Peng , Yuanjie Lu , Yali Liu , Chenru Wang , Jiankang Sun , Hao Zhang , Lili Chen , Jinghua Miao
IPC: G06T15/20 , H04N13/383 , H04N13/344 , G06T15/00
Abstract: An image rendering method for a computer product coupled to a display apparatus may include rendering an entire display region of the display apparatus with a first rendering mode to generate a first rendering mode sample image, determining a target region in the entire display region, rendering the target region with a second rendering mode to generate a second rendering mode sample image, and transmitting data of the first rendering mode sample image and the second rendering mode sample image. The second rendering mode comprises at least a value of an image rendering feature that is higher than that of the first rendering mode.
-
公开(公告)号：US11341735B2
公开(公告)日：2022-05-24
申请号：US16905588
申请日：2020-06-18
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Jingtao Xu , Jianwen Suo , Xiangyang Liu , Tingting Wang , Shaonan Zhang , Bo Xu
Abstract: This disclosure provides an image recommendation method, a client, a server, a computer system and a medium. The method includes acquiring an image, sending the acquired image to a server, such that the server extracts a scale invariant feature of the acquired image and performs retrieval of identical images according to the scale invariant feature of the acquired image, and such that the server extracts a multi-scale feature of the acquired image and performs retrieval of similar images according to the multi-scale feature of the acquired image, and receiving at least one recommended image. The at least one recommended image is based on result of the identical image retrieval and result of the similar image retrieval.
-
公开(公告)号：US11288839B2
公开(公告)日：2022-03-29
申请号：US16633393
申请日：2019-07-03
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Jingtao Xu , Jianwen Suo , Yue Li , Bo Xu , Zhiguo Zhang
Abstract: A method for positioning a supermarket shopping cart, a system for positioning a supermarket shopping cart and a supermarket shopping cart. A method for positioning a supermarket shopping cart provided by the present disclosure includes: acquiring a first reference image of a supermarket, and processing a first reference image to obtain a partition in which a shopping cart is located as a positioning partition, in which the supermarket comprises a plurality of partitions; receiving distance information sent by at least one signal transmitter provided in the positioning partition, in which each partition is provided with at least one signal transmitter; and obtaining a first positioning position of the shopping cart, according to distance information sent by at least one signal transmitter corresponding to the positioning partition, and determining an actual position of the shopping cart based on the first positioning position of the shopping cart.
-
公开(公告)号：US20210358200A1
公开(公告)日：2021-11-18
申请号：US16335350
申请日：2018-09-06
Inventor： Xuefeng Wang , Yukun Sun , Bin Zhao , Lixin Wang , Xi Li , Jianwen Suo , Wenyu Li , Qingwen Fan , Jinbao Peng , Yuanjie Lu , Yali Liu , Chenru Wang , Jiankang Sun , Hao Zhang , Lili Chen , Jinghua Miao
IPC: G06T15/20 , G06T15/00 , H04N13/383 , H04N13/344
Abstract: The present disclosure relates to an image rendering method for a computer product coupled to a display apparatus. The image rendering method may include rendering an entire display region of the display apparatus with a first rendering mode to generate a first rendering mode sample image, determining a target region in the entire display region, rendering the target region with a second rendering mode to generate a second rendering mode sample image, and transmitting data of the first rendering mode sample image and the second rendering mode sample image. The second rendering mode comprises at least a value of an image rendering feature that is higher than that of the first rendering mode.
-
公开(公告)号：US11127126B2
公开(公告)日：2021-09-21
申请号：US16500538
申请日：2019-03-13
Inventor： Xi Li , Hao Zhang , Lili Chen , Yukun Sun , Jinghua Miao , Xuefeng Wang , Jinbao Peng , Bin Zhao , Jianwen Suo , Lixin Wang , Qingwen Fan , Wenyu Li , Yuanjie Lu
Abstract: Disclosed is an image processing method, including: determining coordinate values of one or more target pixels in an image, wherein the target pixels are used for dividing the image; carrying out a mapping operation on the coordinate values of the one or more target pixels to obtain first pixel data; reading the image to obtain second pixel data; and combining the first pixel data and the second pixel data to obtain a combined image.
-
Patent Agency Ranking
公开(公告)号：US10970844B2
公开(公告)日：2021-04-06
申请号：US16403805
申请日：2019-05-06
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Jingtao Xu , Jianwen Suo , Yue Li
Abstract: An image segmentation method and device, a computer device and a non-volatile storage medium are provided. The image segmentation method includes: performing super-pixel segmentation on an image to be segmented to obtain a super-pixel image, and binarizing the image to be segmented to obtain a binary image; combining the super-pixel image and the binary image to obtain a binary super-pixel image; performing distance transformation on the binary super-pixel image, to obtain a grayscale super-pixel image; marking seed points in the grayscale super-pixel image, to obtain a seed point super-pixel image in which grayscale values of the seed points are greater than a first value, and grayscale values of pixel blocks other than the seed points in target regions are the first value; and marking and filling the pixel blocks, grayscale values of which are the first value in the seed point super-pixel image, to obtain a segmented image.
-
17.发明授权公开(公告)号：US10922795B2
公开(公告)日：2021-02-16
申请号：US16479103
申请日：2018-11-27
Inventor： Yukun Sun , Hao Zhang , Lili Chen , Jinghua Miao , Bin Zhao , Xuefeng Wang , Wenyu Li , Xi Li , Lixin Wang , Jianwen Suo , Yali Liu , Yakun Wang
Abstract: A method measuring a distortion parameter of a visual reality device includes: obtaining an anti-distortion grid image according to a first distortion coefficient; obtaining a grid image of the anti-distortion grid image at a preset viewpoint after the anti-distortion grid image passes through a to-be-measured optical component of the visual reality device; determining a distortion type of the grid image after passing through the to-be-measured optical component; adjusting the first distortion coefficient according to the distortion type of the grid image, thereby obtaining an adjusted first distortion coefficient and then reducing distortion of the grid image; repeating the above steps until the distortion of the grid image is less than or equal to a distortion threshold. The adjusted first distortion coefficient when the distortion of the grid image is less than or equal to the distortion threshold, is taken as a distortion coefficient of the to-be-measured optical component.
-
18.发明申请公开(公告)号：US20200098183A1
公开(公告)日：2020-03-26
申请号：US16384119
申请日：2019-04-15
Inventor： Bin Zhao , Lixin Wang , Xi Li , Jianwen Suo , Qingwen Fan , Jinbao Peng , Ruifeng Qin , Yuanjie Lu , Jinghua Miao , Yukun Sun , Xuefeng Wang , Wenyu Li , Lili Chen , Hao Zhang
Abstract: The present disclosure proposes a dual-screen display method for eliminating AR/VR picture tearing and an AR/VR display device, each single screen in a dual-screen for the dual-screen display method being divided into a first half-screen and a second half-screen respectively. The method includes: performing rendering and scanning in parallel for the first half-screen and the second half-screen in unit of half a frame. A start time of scanning the second half-screen is adjusted to eliminate a picture tearing phenomenon.
-
公开(公告)号：US11783445B2
公开(公告)日：2023-10-10
申请号：US16641537
申请日：2019-03-13
Inventor： Xuefeng Wang , Yukun Sun , Hao Zhang , Lili Chen , Jinghua Miao , Bin Zhao , Xi Li , Lixin Wang , Jianwen Suo , Wenyu Li , Jinbao Peng , Qingwen Fan , Yuanjie Lu , Yali Liu , Chenru Wang , Jiankang Sun
IPC: G06T3/40 , G06F3/04845 , G06T11/60
CPC classification number: G06T3/4038 , G06F3/04845 , G06T11/60
Abstract: An image processing method is provided, the method includes: performing area division on an input image to obtain a plurality of sub-images; determining a part of the plurality of sub-images as an image to be output; stitching respective sub-images of the image to be output to obtain a stitched image; and transmitting the stitched image, wherein the stitched image is smaller than the input image. An image jointing method is provided, the method includes: receiving a stitched image obtained by the image processing method according to the present disclosure; extracting respective sub-images of an image to be output from the stitched image; and jointing the respective sub-images to obtain a display image, wherein the jointing the respective sub-images refers to obtaining the display image by an operation inverse to a stitching process of stitching the respective sub-images to obtain the stitched image.
-
公开(公告)号：US11763164B2
公开(公告)日：2023-09-19
申请号：US17043591
申请日：2019-12-20
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Jingtao Xu , Jianwen Suo , Xiaojun Tang
IPC: G06F16/55 , G06F16/583 , G06F16/51 , G06F16/532 , G06N3/084 , G06N3/08 , G06F18/22 , G06V10/74
CPC classification number: G06N3/084 , G06F16/51 , G06F16/532 , G06F16/55 , G06F16/583 , G06F18/22 , G06N3/08 , G06V10/761
Abstract: An image-to-image search method which is implemented in a server is provided. The server receives an image to be searched and at least one category of similarity search sent by a terminal. The server extracts a feature code of the image by using a trained hash model that uniquely corresponds to the at least one category of similarity search according to the received image and the at least one category of similarity search. The server obtains target images that are similar to the image according to the feature code of the image in a feature code library that uniquely corresponds to the at least one category of similarity search. The server sends the target images to the terminal.
-
-
-
-
-
-
-
-
-
Search Results
42
records
(took 0.026 seconds)
