公开(公告)号：US20210073957A1

公开(公告)日：2021-03-11

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

IPC: G06T5/00 ,  G06T3/40 ,  H04N9/73 ,  H04N9/64 ,  G06N3/08

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.

公开(公告)号：US20180357775A1

公开(公告)日：2018-12-13

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 ,  H04N5/247 ,  G06T7/55 ,  H04N5/265 ,  G06K9/62

CPC classification number: G06T7/33 ,  G06K9/00201 ,  G06K9/4671 ,  G06K9/6202 ,  G06K9/6211 ,  G06K9/6215 ,  G06T7/11 ,  G06T7/174 ,  G06T7/194 ,  G06T7/55 ,  G06T2207/10012 ,  H04N5/2258 ,  H04N5/23229 ,  H04N5/23232 ,  H04N5/2355 ,  H04N5/247 ,  H04N5/265

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：US20220375220A1

公开(公告)日：2022-11-24

申请号：US17743892

申请日：2022-05-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Wensen FENG ,  Huan ZHANG ,  Jun CAO ,  Zhongwei TANG ,  Jiangwei LI

IPC: G06V20/00 ,  G06V20/10 ,  G06V10/74 ,  G06T7/73

Abstract: A visual localization method and apparatus are provided. The method includes obtaining a captured first image, determining a first pose based on the first image and an aerial model, determining whether a ground model corresponding to the first pose exists in an aerial-ground model, and when the ground model corresponding to the first pose exists, determining a second pose based on the ground model. The aerial-ground model includes the aerial model and the ground model mapped to the aerial model, a coordinate system of the ground model is the same as a coordinate system of the aerial model, and localization accuracy of the second pose is higher than localization accuracy of the first pose. Performing fine visual localization based on the ground model can improve accuracy and a success rate of localization.