公开(公告)号：US20240397184A1

公开(公告)日：2024-11-28

申请号：US18600730

申请日：2024-03-10

Applicant: Apple Inc.

Inventor： Hengzhou Ding ,  Christophe Seyve

IPC: H04N23/56 ,  G02B27/00 ,  G02B27/01 ,  H04N23/21 ,  H04N23/611

Abstract: A head-mounted device may include one or more scene cameras configured to capture images of a scene, one or more hands sensors configured to detect a user's hands, one or more supplemental emitters configured to provide supplemental illumination for the user's hands, and control circuitry configured to determine whether the user's hands are sufficiently illuminated, to determine whether the captured images are properly exposed, and to adjust the one or more supplemental emitters based on whether the user's hands are sufficiently illuminated and based on whether the captured images are properly exposed. The control circuitry can activate the supplemental emitters when the captured images are too dark or when one of the detected hands is too dark. The control circuitry can deactivate the supplemental emitters when one of the detected hands is too bright or when the captured images are overly exposed.

公开(公告)号：US20240388683A1

公开(公告)日：2024-11-21

申请号：US18583729

申请日：2024-02-21

Applicant: Apple Inc.

Inventor： Renbo Cao ,  Yonghui Zhao ,  Yingjun Bai ,  Christophe Seyve ,  Henryk K. Blasinski

IPC: H04N13/133 ,  H04N13/15 ,  H04N13/161 ,  H04N13/167 ,  H04N13/339

Abstract: An apparatus can include a first image sensor having a first field of view (FOV) and configured to capture a first image, a second image sensor having a second FOV and configured to capture a second image, an image statistics collection subsystem configured to gather first image statistics information associated with the first image and to gather second image statistics information associated with the second image, a disparity detection subsystem configured to compare the first image statistics information with the second image statistics information, and image signal processing blocks configured to synchronize processing of the first and second images based on the comparison of the first image statistics information with the second image statistics information. Processing of the first and second images can involve using one or more combined image signal processing control parameters based on image statistics information within an overlapping FOV and/or a within a total FOV.

公开(公告)号：US20240348933A1

公开(公告)日：2024-10-17

申请号：US18634197

申请日：2024-04-12

Applicant: Apple Inc.

Inventor： Simon Fortin-Deschenes ,  Christian I. Moore ,  Daniel A. Glynn ,  Anthony Ghannoum ,  Paolo Di Febbo ,  Luke A. Pillans ,  Christophe Seyve ,  Zhongmin Wang

IPC: H04N23/73 ,  H04N13/239 ,  H04N13/296 ,  H04N13/344 ,  H04N13/371 ,  H04N13/383 ,  H04N23/68 ,  H04N23/71 ,  H04N23/745 ,  H04N23/76

CPC classification number: H04N23/73 ,  H04N13/239 ,  H04N13/296 ,  H04N13/344 ,  H04N13/371 ,  H04N13/383 ,  H04N23/6812 ,  H04N23/684 ,  H04N23/71 ,  H04N23/745 ,  H04N23/76

Abstract: Various implementations disclosed herein improve the appearance of captured video by accounting for motion-induced blur, noise, lighting, and/or other factors related to the appearance of video captured by rotating or otherwise moving wearable electronic device. Some implementations reduce or eliminate camera motion blur during video capture by dynamically adjusting the exposure used to capture the video based on user motion. For example, exposure may be reduced to reduce the amount of blur during motion. Since such a reduced exposure captures a lesser amount of light, gain may be increased such that the captured video maintains a relatively constant image brightness in spite of the changing exposure over time.

公开(公告)号：US20240106976A1

公开(公告)日：2024-03-28

申请号：US17934849

申请日：2022-09-23

Applicant: Apple Inc.

Inventor： Christophe Seyve ,  Xuemei Zhang

IPC: H04N5/783 ,  G06T5/00 ,  G06T5/40 ,  G06V10/74

CPC classification number: H04N5/783 ,  G06T5/002 ,  G06T5/40 ,  G06V10/761

Abstract: Devices, methods, and non-transitory program storage devices are disclosed herein to perform intelligent determinations of non-linear (i.e., dynamic) image recording rates for the production of improved timelapse videos. The techniques described herein may be especially applicable to timelapse videos captured over long durations of time and/or with varying amounts of device motion/scene content change over the course of the captured video (e.g., when a user is walking, exercising, driving, etc. during the video's capture). By smoothly varying the image recording rate of the timelapse video in accordance with multi-temporal scale estimates of scene content change, the quality of the produced timelapse video may be improved (e.g., fewer long stretches of the video with too little action, as well as fewer stretches of the video where there is so much rapid action in the timelapse video that it is difficult for a viewer to perceive what is happening in the video).

公开(公告)号：US12041383B2

公开(公告)日：2024-07-16

申请号：US17934849

申请日：2022-09-23

Applicant: Apple Inc.

Inventor： Christophe Seyve ,  Xuemei Zhang

IPC: H04N5/783 ,  G06T5/40 ,  G06T5/70 ,  G06V10/74

CPC classification number: H04N5/783 ,  G06T5/40 ,  G06T5/70 ,  G06V10/761

Abstract: Devices, methods, and non-transitory program storage devices are disclosed herein to perform intelligent determinations of non-linear (i.e., dynamic) image recording rates for the production of improved timelapse videos. The techniques described herein may be especially applicable to timelapse videos captured over long durations of time and/or with varying amounts of device motion/scene content change over the course of the captured video (e.g., when a user is walking, exercising, driving, etc. during the video's capture). By smoothly varying the image recording rate of the timelapse video in accordance with multi-temporal scale estimates of scene content change, the quality of the produced timelapse video may be improved (e.g., fewer long stretches of the video with too little action, as well as fewer stretches of the video where there is so much rapid action in the timelapse video that it is difficult for a viewer to perceive what is happening in the video).

公开(公告)号：US20240107131A1

公开(公告)日：2024-03-28

申请号：US17934834

申请日：2022-09-23

Applicant: Apple Inc.

Inventor： Christophe Seyve

IPC: H04N21/8547 ,  G06T7/30 ,  H04N5/783

CPC classification number: H04N21/8547 ,  G06T7/30 ,  H04N5/783 ,  G06T2207/10016 ,  G06T2207/20024

Abstract: Devices, methods, and non-transitory program storage devices are disclosed herein to perform intelligent determinations of non-linear (i.e., dynamic) image recording rates for the production of improved timelapse videos. The techniques described herein may be especially applicable to timelapse videos captured over long durations of time and/or with varying amounts of device motion/scene detail change over the course of the captured video (e.g., when a user is walking, exercising, driving, etc. during the video's capture). By smoothly varying the image recording rate of the timelapse video in accordance with estimates of device motion, the quality of the produced timelapse video may be improved (e.g., fewer long stretches of the video with no action or too little action, as well as fewer stretches of the video where there is so much rapid action in the timelapse video that it is difficult for a viewer to perceive what is happening in the video).

公开(公告)号：US11935322B1

公开(公告)日：2024-03-19

申请号：US17369416

申请日：2021-07-07

Applicant: Apple Inc.

Inventor： Renbo Cao ,  Christophe Seyve ,  Yonghui Zhao

IPC: G06V40/16 ,  G06V10/20 ,  G06V10/26 ,  G06V10/766

CPC classification number: G06V40/16 ,  G06V10/255 ,  G06V10/26 ,  G06V10/766

Abstract: Devices, methods, and non-transitory program storage devices are disclosed to: obtain an input image; identify a first face in the input image; divide the first face into a plurality of regions; identify obstructions in one or more of the plurality of regions; select a subset of regions, based on the identified obstructions; and determine a white point for the first face based, at least in part, on the selected subset of regions. In some embodiments, obstructions may be identified using a face obstruction detection model (e.g., a logistic regression model trained based on a large dataset of annotated facial images with and without obstructions). The identified obstructions may comprise, e.g., facial hair, head hair, glasses, a facial covering, a head covering, a face mask, or clothing. In some embodiments, a white balancing operation may be performed on the input image based, at least in part, on the determined white point.