公开(公告)号：US11366981B1

公开(公告)日：2022-06-21

申请号：US17111157

申请日：2020-12-03

Applicant: Apple Inc.

Inventor： Lina M. Paz-Perez

IPC: G06K9/00 ,  G06K9/62 ,  G06V30/194

Abstract: Providing localization data includes obtaining a first image of a scene associated with a first condition, determining one or more target conditions, and applying an appearance transfer network to the first image to obtain one or more synthesized images comprising the scene, wherein the scene is associated with the one or more target conditions in the synthesized image. A first patch is selected from the first image, wherein the first patch comprises a keypoint, and an image location is determined for the first patch. Then one or more additional patches can be obtained using the synthesized images and the image location. A descriptor network may be trained to provide localization data based on the first patch and the one or more additional patches.

公开(公告)号：US11875527B1

公开(公告)日：2024-01-16

申请号：US17224192

申请日：2021-04-07

Applicant: Apple Inc.

Inventor： Lina M. Paz-Perez ,  Chavdar Papazov ,  Vimal Thilak ,  Jai Prakash

IPC: G06T7/73 ,  G06T7/11 ,  G06T7/64 ,  G06T17/00 ,  G06F18/25

CPC classification number: G06T7/73 ,  G06F18/253 ,  G06T7/11 ,  G06T7/64 ,  G06T17/00 ,  G06T2207/20084 ,  G06T2207/20132

Abstract: Some implementations involve a process that identifies a subset of points in an image and creates descriptors for these points. The detection and descriptor process may use one or more neural networks. In some implementations, the process includes a neural network that uses one or more fixed (e.g., weight independent) neural network layers to perform certain functions that can be performed more accurately and/or efficiently than via non-fixed (e.g., weight-based) layers. In some implementations, for example, a neural network includes a layer that determines orientation formulaically within the neural network. Such orientations may be determined convolutionally (e.g., using sliding patches) but are not determined based on internal node weights within the layer that were determined during the training of the neural network.

公开(公告)号：US20240406526A1

公开(公告)日：2024-12-05

申请号：US18678972

申请日：2024-05-30

Applicant: Apple Inc.

Inventor： Huiwen Guo ,  Florian Mahlknecht ,  Jose Lamarca Peiro ,  Lina M. Paz-Perez ,  Oleg Naroditsky

IPC: H04N23/52 ,  G01S7/497 ,  G01S17/66 ,  G01S17/894 ,  G02B27/00

Abstract: A method for detecting an occlusion of an image sensor includes obtaining, via the image sensor, a plurality of images of a physical environment of the electronic device while the electronic device is moving. The method includes detecting an occlusion of the image sensor based on a repeated occurrence of a static feature across the plurality of images. The method includes modifying a weight associated with the static feature to decrease an impact of the occlusion on a performance of a function.

公开(公告)号：US20240386599A1

公开(公告)日：2024-11-21

申请号：US18666992

申请日：2024-05-17

Applicant: Apple Inc.

Inventor： Jai Prakash ,  Lina M. Paz-Perez

IPC: G06T7/73 ,  G01C21/16 ,  G06T7/13 ,  G06T13/00

Abstract: In one implementation, a method of determining a downward direction is performed by a device including one or more processors, non-transitory memory, and an image sensor. The method includes capturing, using the image sensor, an image of a physical environment. The method includes detecting a plurality of lines within the image of the physical environment. The method includes determining one or more vanishing directions based on the plurality of lines. The method includes defining a downward direction based on the one or more vanishing directions.