-
公开(公告)号：US12154251B2
公开(公告)日：2024-11-26
申请号：US17784342
申请日：2020-12-14
Applicant: Huawei Technologies Co., Ltd.
Inventor： Gang Chen , Jiangwei Li , Wei Luo , Chunlin Qin , Zhen Wang , Jing Hu , Jinlei Zhang , Zheng Li
IPC: G06K9/00 , G06T3/40 , G06T5/50 , G06T5/73 , G06T5/77 , G06V10/26 , G06V10/74 , G06V10/75 , G06V20/70
Abstract: An image processing method includes segmenting, by a cloud server and based on a zoom ratio of a high-definition image in a high-definition image library, a low-definition image of a small zoom ratio from a terminal to obtain a plurality of image blocks. For each image block, performing, by the cloud server, retrieval and matching in the high-definition image library to obtain one or more high-definition reference images, and then performing, by the cloud server, image quality improvement using an image enhancement network that is based on the high-definition reference images to obtain a plurality of high-definition image blocks. Finally, stitching, by the cloud server, the high-definition image blocks into a super-definition image with higher resolution and higher definition, and returning, by the cloud server, the super-definition image to the terminal.
-
公开(公告)号：US20230089845A1
公开(公告)日：2023-03-23
申请号：US18070862
申请日：2022-11-29
Applicant: Huawei Technologies Co., Ltd.
Inventor： Wensen Feng , Huan Zhang , Jun Cao , Jiange Ge , Zhongwei Tang , Jiangwei Li
Abstract: A visual localization method includes obtaining an image captured by a terminal device; obtaining two-dimensional line feature information of the image that includes at least one of information about a boundary between a building and a non-building or information about a boundary between a non-building and a non-building; and determining a localization pose of the terminal device based on location information of the terminal device, magnetometer angle deflection information of the terminal device, a satellite map, and the two-dimensional line feature information.
-
公开(公告)号：US20230056332A1
公开(公告)日：2023-02-23
申请号：US17784342
申请日：2020-12-14
Applicant: Huawei Technologies Co., Ltd.
Inventor： Gang Chen , Jiangwei Li , Wei Luo , Chunlin Qin , Zhen Wang , Jing Hu , Jinlei Zhang , Zheng Li
Abstract: An image processing method includes segmenting, by a cloud server and based on a zoom ratio of a high-definition image in a high-definition image library, a low-definition image of a small zoom ratio from a terminal to obtain a plurality of image blocks. For each image block, performing, by the cloud server, retrieval and matching in the high-definition image library to obtain one or more high-definition reference images, and then performing, by the cloud server, image quality improvement using an image enhancement network that is based on the high-definition reference images to obtain a plurality of high-definition image blocks. Finally, stitching, by the cloud server, the high-definition image blocks into a super-definition image with higher resolution and higher definition, and returning, by the cloud server, the super-definition image to the terminal.
-
公开(公告)号：US10445890B2
公开(公告)日：2019-10-15
申请号：US15779859
申请日：2015-11-30
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Kongqiao Wang , Jiangwei Li , Congchao Zhu
IPC: G06T7/33 , H04N5/225 , H04N5/232 , G06K9/62 , H04N5/247 , G06T7/55 , H04N5/265 , G06T7/11 , G06T7/194 , G06T7/174 , H04N5/235 , G06K9/00 , G06K9/46
Abstract: Obtaining a first set including key point descriptors in a first image that is of a to-be-shot scene and that is formed by using a first camera in a dual camera system, and a second set including key point descriptors in a second image that is of the to-be-shot scene and that is formed by using a second; pairing a key point in the first set and a key point in the second set that match each other to form a key point pair; selecting the key point pair that meets a predetermined condition; generating an image alignment vector field according to the selected key point pair; and estimating an occlusion area according to the depth information of the first image and the second image, and eliminating an alignment vector of the occlusion area in the image alignment vector field, to form a corrected image alignment vector field.
-
公开(公告)号：US20250111533A1
公开(公告)日：2025-04-03
申请号：US18941604
申请日：2024-11-08
Applicant: Huawei Technologies Co., Ltd.
Inventor： Haixing Yu , Lei Zhang , Rui Qin , Jiangwei Li
Abstract: A target localization method includes a server that receives a localization request sent by a first electronic device, where the localization request includes a to-be-processed image; the server recognizes a target in the to-be-processed image; the server searches a pose estimation model library for a target pose estimation model corresponding to the target, where the pose estimation model library includes pose estimation models respectively corresponding to a plurality of objects; the server obtains a pose of the target based on the to-be-processed image and the target pose estimation model; and the server sends the pose of the target to the first electronic device.
-
Patent Agency Ranking
公开(公告)号：US10559106B2
公开(公告)日：2020-02-11
申请号：US15557849
申请日：2015-11-16
Applicant: Huawei Technologies Co., Ltd.
Inventor： Kongqiao Wang , Jiangwei Li , Hao Wang , Xiuyan Guo
Abstract: A method includes obtaining a to-be-processed current point in a target area in a current frame, obtaining a first-type smoothing weight of a first-type neighborhood point in an Nth frame before the current frame with respect to the current point, where the first-type neighborhood point is an Xth circle point that encircles a point corresponding to a location of the current point and that is in the Nth frame before the current frame, obtaining a second-type smoothing weight of a second-type neighborhood point in an Mth frame after the current frame with respect to the current point, where the second-type neighborhood point is a Yth circle point that encircles the point corresponding to the location of the current point and that is in the Mth frame after the current frame, and performing smoothing calculation on the current point according to the first-type smoothing weight and the second-type smoothing weight.
-
公开(公告)号：US20190253593A1
公开(公告)日：2019-08-15
申请号：US16345603
申请日：2016-12-05
Applicant: Huawei Technologies Co., Ltd.
Inventor： Jiangwei Li
Abstract: A method includes: obtaining a target zoom ratio; simultaneously photographing a monochrome image and a color image of a target scene based on the target zoom ratio, where resolution of the monochrome image is higher than that of the color image, and there is at least one monochrome image and at least one color image; correspondingly cropping the monochrome image and the color image based on the target zoom ratio, where a field of view corresponding to a monochrome image obtained through cropping is the same as a field of view corresponding to a color image obtained through cropping; and performing fusion on the monochrome image obtained through cropping and the color image obtained through cropping, to obtain a color zoom image.
-
公开(公告)号：US10997778B2
公开(公告)日：2021-05-04
申请号：US16464202
申请日：2017-02-23
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xing Zhang , Kun Liu , Jiangwei Li , Cheng Du
Abstract: A method, where one file includes file data of a plurality of files for generating a three-dimensional model includes obtaining a first file in a picture format, an extension data segment of the first file includes at least one first data segment, and the first data segment includes the file data of the files for generating a first three-dimensional model of the three-dimensional model, obtaining the file data of the files from the first data segment, and generating the first three-dimensional model based on the file data of the files.
-
公开(公告)号：US10827107B2
公开(公告)日：2020-11-03
申请号：US16345603
申请日：2016-12-05
Applicant: Huawei Technologies Co., Ltd.
Inventor： Jiangwei Li
IPC: H04N5/225 , H04N5/232 , G06T3/40 , G06K9/32 , H04N5/262 , G06T7/593 , G06T7/194 , G06T5/00 , G06T5/50 , H04N9/04
Abstract: A method includes: obtaining a target zoom ratio; simultaneously photographing a monochrome image and a color image of a target scene based on the target zoom ratio, where resolution of the monochrome image is higher than that of the color image, and there is at least one monochrome image and at least one color image; correspondingly cropping the monochrome image and the color image based on the target zoom ratio, where a field of view corresponding to a monochrome image obtained through cropping is the same as a field of view corresponding to a color image obtained through cropping; and performing fusion on the monochrome image obtained through cropping and the color image obtained through cropping, to obtain a color zoom image.
-
公开(公告)号：US11625815B2
公开(公告)日：2023-04-11
申请号：US17030038
申请日：2020-09-23
Applicant: Huawei Technologies Co., Ltd.
Inventor： Gregory Slabaugh , Youliang Yan , Fenglong Song , Gang Chen , Jiangwei Li , Tao Wang , Liu Liu , Ioannis Alexiou , Ioannis Marras , Sean Moran , Steven George McDonagh , Jose Costa Pereira , Viktor Vladimirovich Smirnov
Abstract: An image processing apparatus and a method are provided. The apparatus comprises a plurality of processing modules configured to operate in series to refine a raw image captured by a camera, the modules comprising a first module and a second module, each of which independently implements a respective trained artificial intelligence model, wherein: the first module implements an image transformation operation that performs an operation from the set comprising: (i) an essentially pixel-level operation that increases sharpness of an image input to the module, (ii) an essentially pixel-level operation that decreases sharpness of an image input to the module, (iii) an essentially pixel-block-level operation on an image input to the module; and the second module as a whole implements a different operation from the said set.
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.018 seconds)
