中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

25 records (took 0.024 seconds)

    Non-linear timelapse videos based on multi-temporal scale detection of scene content change
    12.
    发明授权
    Non-linear timelapse videos based on multi-temporal scale detection of scene content change 有权

    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).

    Method and Device for Generating Metadata Estimations based on Metadata Subdivisions
    13.
    发明公开
    Method and Device for Generating Metadata Estimations based on Metadata Subdivisions 审中-公开

    公开(公告)号：US20240104766A1

    公开(公告)日：2024-03-28

    申请号：US18369354

    申请日：2023-09-18

    Applicant: Apple Inc.

    Inventor： Xiaohua Yang ,  Jin Wook Chang ,  Xin Wang ,  Xuemei Zhang

    IPC: G06T7/73 ,  G06F3/01

    CPC classification number: G06T7/73 ,  G06F3/012 ,  G06F3/013 ,  G06T2207/20021 ,  G06T2207/30196

    Abstract: In one implementation, a method is performed for generating metadata estimations based on metadata subdivisions. The method includes: obtaining an input image; obtaining metadata associated with the input image; subdividing the metadata into a plurality of metadata subdivisions; determining a viewport relative to the input image based on at least one of head pose information and eye tracking information; generating one or more metadata estimations by performing an estimation algorithm on at least a portion of the plurality of metadata subdivisions based on the viewport; and generating an output image by performing an image processing algorithm on the input image based on the one or more metadata estimations.

    Camera motion aware local tone mapping
    14.
    发明授权
    Camera motion aware local tone mapping 有权

    公开(公告)号：US11195247B1

    公开(公告)日：2021-12-07

    申请号：US16777074

    申请日：2020-01-30

    Applicant: Apple Inc.

    Inventor： Henryk K. Blasinski ,  Xuemei Zhang ,  Yingjun Bai

    IPC: G06T7/00 ,  G06T1/00 ,  G06T5/50 ,  G06T5/00 ,  G06T5/40

    Abstract: An electronic image capture device captures a first image of a scene at a first time. A first local tone mapping operator for a first portion of the first image is determined. The electronic image capture device further captures a second image of the scene at a second time. A motion of the electronic device between the first time and the second time is determined. A second local tone mapping operator for a second portion of the second image is determined. The second portion is determined to correspond to the first portion based, at least in part, on the determined motion of the electronic device. The second local tone mapping operator is determined based, at least in part, on the first local tone mapping operator. At least the second local tone mapping operator is applied to the second portion of the second image.

    Multi-scale tone mapping
    17.
    发明授权
    Multi-scale tone mapping 有权
    多尺度色调映射

    公开(公告)号：US09418311B2

    公开(公告)日：2016-08-16

    申请号：US14477679

    申请日：2014-09-04

    Applicant: Apple Inc.

    Inventor： Yingjun Bai ,  Xuemei Zhang

    IPC: G06K9/00 ,  G06K9/46 ,  G06F17/30

    CPC classification number: G06K9/4661 ,  G06F17/3028 ,  G06K9/46 ,  G06K9/4642 ,  G06K2009/4666 ,  G06T5/007 ,  G06T5/40 ,  G06T2207/20016

    Abstract: Methods, devices and computer readable instructions to generate multi-scale tone curves are disclosed. One method includes finding, for a given input image, a global tone curve that exhibits monotonic behavior. The input image may then be partitioned into a first number of sub-regions. For each sub-region, a local tone curve may be determined that has an output level that is constrained to the global tone curve at one or more first luminance levels so that each sub-region's local tone curve's output follows the global tone curve's monotonic behavior. If the resulting local tone curves provide sufficient control of shadow-boost, highlight-suppression, and contrast optimization the first number of local tone curves may be applied directly to the input image. If additional control is needed, each sub-region may again be partitioned and local tone curves determined for each of the new sub-regions.

    Abstract translation: 公开了用于产生多尺度色调曲线的方法，装置和计算机可读指令。 一种方法包括为给定输入图像找到呈现单调行为的全局色调曲线。 然后可以将输入图像分割成第一数量的子区域。 对于每个子区域，可以确定本地色调曲线，其具有在一个或多个第一亮度水平下被限制到全局色调曲线的输出电平，使得每个子区域的局部色调曲线的输出遵循全局色调曲线的单调行为 。 如果所得到的本地色调曲线提供了阴影提升，高光抑制和对比度优化的足够控制，则可以将第一数量的局部色调曲线直接应用于输入图像。 如果需要附加控制，则每个子区域可以再次被划分，并且为每个新的子区域确定局部色调曲线。

    Region-of-Interest Biased Tone Mapping
    18.
    发明申请
    Region-of-Interest Biased Tone Mapping 有权
    感兴趣区域偏爱色调映射

    公开(公告)号：US20160232419A1

    公开(公告)日：2016-08-11

    申请号：US14614568

    申请日：2015-02-05

    Applicant: Apple Inc.

    Inventor： Yingjun Bai ,  Xuemei Zhang

    IPC: G06K9/46 ,  G06K9/52

    CPC classification number: G06T5/007 ,  G06T5/40 ,  G06T2207/20016

    Abstract: Methods, devices and computer readable instructions to generate region-of-interest (ROI) tone curves are disclosed. One method includes obtaining a statistic for an entire image such as, for example, a luminance statistic. The same statistic may then be found for a specified ROI of the image. A weighted combination of the statistic of the entire image and the statistic of the ROI yields a combined statistic which may then be converted to a ROI-biased tone curve. The weight used to combine the two statistics may be selected to emphasize or de-emphasize the role of the ROI's statistic in the final tone curve.

    Abstract translation: 公开了用于生成感兴趣区（ROI）色调曲线的方法，装置和计算机可读指令。 一种方法包括获得整个图像的统计量，例如亮度统计量。 然后可以为图像的指定ROI找到相同的统计量。 整个图像的统计量和ROI的统计量的加权组合产生组合的统计量，然后可以将它们转换为ROI偏置的色调曲线。 可以选择用于组合两个统计量的权重来强调或不强调ROI的统计在最终色调曲线中的作用。

    Highlight exposure metric and its applications
    19.
    发明授权
    Highlight exposure metric and its applications 有权
    突出曝光度量及其应用

    公开(公告)号：US09380218B2

    公开(公告)日：2016-06-28

    申请号：US14292791

    申请日：2014-05-30

    Applicant: Apple Inc.

    Inventor： Juanqing Chen ,  Xuemei Zhang ,  Yingjun Bai

    IPC: H04N5/235 ,  H04N5/357 ,  G06T3/40

    CPC classification number: H04N5/2355 ,  G06T3/40 ,  G06T7/0002 ,  G06T2207/10004 ,  G06T2207/20208 ,  G06T2207/30168 ,  H04N5/2351 ,  H04N5/2353 ,  H04N5/243 ,  H04N5/357

    Abstract: Systems, methods, and computer readable media for the use of a metric whose value is especially sensitive to the information lost when an image's pixels are clipped are disclosed. The metric may be used as an image's score, where higher values are indicative of lost highlight information (more clipped pixels). One use of the disclosed metric would be to determine when the use of high dynamic range (HDR) techniques are appropriate. The disclosed metric may also be used to bias a scene's exposure value (EV) such as to a lower or underexposed value (EV−) so that the scene may be captured with no more than an acceptable number of clipped pixels.

    Abstract translation: 公开了使用度量的系统，方法和计算机可读介质，其度量对于在图像的像素被裁剪时丢失的信息特别敏感。 度量可以用作图像的分数，其中较高的值表示丢失的高亮度信息（更多的剪切的像素）。 所公开的度量的一个用途将是确定何时使用高动态范围（HDR）技术是适当的。 所公开的度量还可以用于将场景的曝光值（EV）偏移到较低或曝光不足的值（EV-），使得可以以不超过可接受数量的限幅像素捕获场景。

    Multi-Band YCbCr Locally-Adaptive Noise Modeling And Noise Reduction Based On Scene Metadata
    20.
    发明申请
    Multi-Band YCbCr Locally-Adaptive Noise Modeling And Noise Reduction Based On Scene Metadata 有权
    基于场景元数据的多频带YCbCr本地自适应噪声建模和降噪

    公开(公告)号：US20160065795A1

    公开(公告)日：2016-03-03

    申请号：US14474103

    申请日：2014-08-30

    Applicant: Apple Inc.

    Inventor： Farhan A. Baqai ,  Claus Molgaard ,  Fabio Riccardi ,  Xuemei Zhang

    IPC: H04N5/217 ,  H04N9/77 ,  G06T5/00 ,  H04N9/04

    CPC classification number: H04N5/217 ,  G06T5/002 ,  G06T5/008 ,  G06T2207/20012 ,  G06T2207/20016 ,  G06T2207/20048 ,  H04N9/045

    Abstract: Image enhancement is achieved by separating image signals, e.g. YCbCr image signals, into a series of frequency bands and performing locally-adaptive noise reduction on bands below a given frequency but not on bands above that frequency. The bands are summed to develop the image enhanced signals. The YCbCr, multi-band locally-adaptive approach to denoising is able to operate independently—and in an optimized fashion—on both luma and chroma channels. Noise reduction is done based on models developed for both luma and chroma channels by measurements taken for multiple frequency bands, in multiple patches on the ColorChecker chart, and at multiple gain levels, in order to develop a simple yet robust set of models that may be tuned off-line a single time for each camera and then applied to images taken by such cameras in real-time without excessive processing requirements and with satisfactory results across illuminant types and lighting conditions.

    Abstract translation: 图像增强通过分离图像信号来实现。 YCbCr图像信号转换成一系列频带，并在给定频率以下的频带上执行局部自适应噪声降低，但不在高于该频率的频带上进行。 将频带相加以开发图像增强信号。 YCbCr多频域局部自适应去噪方法能够在亮度和色度通道上独立运行，并以优化方式运行。 基于通过对ColorChecker图表上的多个频段进行测量，在ColorChecker图表上以多个增益水平测量的亮度和色度通道开发的模型以及多个增益水平来进行降噪，以便开发一个简单但可靠的模型集 为每台摄像机单独调整离线时间，然后实时应用于摄像机所拍摄的图像，而无需过多的处理要求，并且在各种照明类型和照明条件下都能获得令人满意的结果。

Patent Agency Ranking