公开(公告)号：US20130077866A1

公开(公告)日：2013-03-28

申请号：US13681039

申请日：2012-11-19

Applicant: Apple Inc.

Inventor： David William Singer ,  Courtney Ann Kennedy

IPC: G06K9/46

CPC classification number: H04N5/907 ,  G06F17/30265 ,  G06F17/30793 ,  G06F17/30817 ,  G06K9/00221 ,  G06K9/00255 ,  G06K9/46 ,  G06T7/73

Abstract: A perimeter around a detected object in a frame of image data can be generated in a first coordinate system. The perimeter can be converted from the first coordinate system into a second coordinate system having the same aspect ratio as the first coordinate system. A first metadata entry can include dimensions of image data in the second coordinate system. A second metadata entry can provide a location and dimensions of the converted perimeter in the second coordinate space. Additional metadata can indicate matching objects between frames, position of an object relative to other objects in a frame, a probability that an object is correctly detected, and a total number of objects detected across multiple frames of image data.

Abstract translation: 可以在第一坐标系中生成图像数据的帧中的检测对象周围的周边。 周边可以从第一坐标系转换成具有与第一坐标系相同的纵横比的第二坐标系。 第一元数据条目可以包括第二坐标系中的图像数据的尺寸。 第二元数据条目可以提供第二坐标空间中转换的周边的位置和尺寸。 附加元数据可以指示帧之间的匹配对象，对象相对于帧中的其他对象的位置，正确检测对象的概率以及跨多个图像数据帧检测到的对象的总数。

公开(公告)号：US11962786B2

公开(公告)日：2024-04-16

申请号：US17671512

申请日：2022-02-14

Applicant: Apple Inc.

Inventor： Krishnakanth Rapaka ,  Alexandros Tourapis ,  David William Singer

IPC: H04N19/176 ,  H04N19/103 ,  H04N19/119 ,  H04N19/124 ,  H04N19/136 ,  H04N19/159 ,  H04N19/50

CPC classification number: H04N19/176 ,  H04N19/103 ,  H04N19/119 ,  H04N19/124 ,  H04N19/136 ,  H04N19/159 ,  H04N19/50

Abstract: A multi-stage coding method includes receiving an input block of data for encoding and one or more previously coded samples associated with the input block. The input block is segmented into at least a first sub-region and a second sub-region. A prediction for the first sub-region is generated based on the one or more previously coded samples. Residual data for the first sub-region is obtained using the prediction for the first sub-region. A reconstruction of the first sub-region is generated using the residual data for the first sub-region and the prediction for the first sub-region. A prediction for the second sub-region is generated using the reconstruction of the first sub-region. Residual data for the second sub-region is obtained using the prediction for the second sub-region. The input block is encoded based in part on the residual data for the first region and the residual data for the second region.

公开(公告)号：US20210243455A1

公开(公告)日：2021-08-05

申请号：US17167413

申请日：2021-02-04

Applicant: Apple Inc.

Inventor： Krishnakanth Rapaka ,  Alexandros Tourapis ,  David William Singer

IPC: H04N19/176 ,  H04N19/119 ,  H04N19/50 ,  H04N19/159 ,  H04N19/136 ,  H04N19/103 ,  H04N19/124

Abstract: A multi-stage coding method includes receiving an input block of data for encoding and one or more previously coded samples associated with the input block. The input block is segmented into at least a first sub-region and a second sub-region. A prediction for the first sub-region is generated based on the one or more previously coded samples. Residual data for the first sub-region is obtained using the prediction for the first sub-region. A reconstruction of the first sub-region is generated using the residual data for the first sub-region and the prediction for the first sub-region. A prediction for the second sub-region is generated using the reconstruction of the first sub-region. Residual data for the second sub-region is obtained using the prediction for the second sub-region. The input block is encoded based in part on the residual data for the first region and the residual data for the second region.

公开(公告)号：US10432961B2

公开(公告)日：2019-10-01

申请号：US15067041

申请日：2016-03-10

Applicant: Apple Inc.

Inventor： Alexandros Michael Tourapis ,  Yeping Su ,  David William Singer ,  Hsi-Jung Wu

IPC: H04N19/117 ,  H04N19/82 ,  H04N19/169 ,  H04N19/517 ,  H04N19/70 ,  H04N19/61 ,  H04N19/132 ,  H04N19/182 ,  H04N19/59 ,  H04N19/147 ,  H04N19/152 ,  H04N19/40 ,  H04N19/44 ,  H04N19/86

Abstract: A video coding system may include an encoder performs motion-compensated prediction on a video signal in a second format converted from an input format of the video signal. The video coding system may also include a decoder to decode portions of the encoded video, and a filtering system that filters portions of the decoded video, for example, by deblocking filtering or SAO filtering, using parameters derived from the video signal in the input format. A prediction system may include another format converter that converts the decoded video to the input format. The prediction system may select parameters of the motion-compensated prediction based at least in part on a comparison of the video signal in the input format to decoded video in the input format.

公开(公告)号：US10349064B2

公开(公告)日：2019-07-09

申请号：US15066992

申请日：2016-03-10

Applicant: Apple Inc.

Inventor： Alexandros Michael Tourapis ,  Yeping Su ,  David William Singer ,  Hsi-Jung Wu

IPC: H04N19/186 ,  H04N19/189 ,  H04N9/64 ,  H04N11/20 ,  H04N19/70 ,  H04N19/147 ,  H04N19/46 ,  H04N19/117 ,  H04N19/132 ,  H04N19/154 ,  H04N19/80 ,  H04N19/85 ,  H04N19/59 ,  H04N19/44 ,  H04N9/67

Abstract: A method of adaptive chroma downsampling is presented. The method comprises converting a source image to a converted image in an output color format, applying a plurality of downsample filters to the converted image and estimating a distortion for each filter chose the filter that produces the minimum distortion. The distortion estimation includes applying an upsample filter, and a pixel is output based on the chosen filter. Methods for closed loop conversions are also presented.

公开(公告)号：US09736335B2

公开(公告)日：2017-08-15

申请号：US14875432

申请日：2015-10-05

Applicant: Apple Inc.

Inventor： Alexandros Michael Tourapis ,  Yeping Su ,  David William Singer ,  Hsi-Jung Wu

IPC: H04N1/60 ,  H04N9/67 ,  H04N19/46 ,  H04N19/186 ,  H04N19/85

CPC classification number: H04N1/6005 ,  H04N1/6058 ,  H04N9/67 ,  H04N19/186 ,  H04N19/46 ,  H04N19/85

Abstract: Image and video processing techniques are disclosed for processing components of a color space individually by determining limits for each component based on the relationship between each component in a color space. These limits may then be used to clip each component such that the component values are within the determined range for that component. In this manner, more efficient processing of images and/or video may be achieved.

公开(公告)号：US20160269733A1

公开(公告)日：2016-09-15

申请号：US15066992

申请日：2016-03-10

Applicant: Apple Inc.

Inventor： Alexandros Michael Tourapis ,  Yeping Su ,  David William Singer ,  Hsi-Jung Wu

IPC: H04N19/186 ,  H04N19/44 ,  H04N19/117

CPC classification number: H04N19/186 ,  H04N9/64 ,  H04N9/67 ,  H04N11/20 ,  H04N19/117 ,  H04N19/132 ,  H04N19/147 ,  H04N19/154 ,  H04N19/189 ,  H04N19/44 ,  H04N19/46 ,  H04N19/59 ,  H04N19/70 ,  H04N19/80 ,  H04N19/82 ,  H04N19/85

Abstract: A method of adaptive chroma downsampling is presented. The method comprises converting a source image to a converted image in an output color format, applying a plurality of downsample filters to the converted image and estimating a distortion for each filter chose the filter that produces the minimum distortion. The distortion estimation includes applying an upsample filter, and a pixel is output based on the chosen filter. Methods for closed loop conversions are also presented.

Abstract translation: 提出了一种自适应色度下采样方法。 该方法包括将源图像转换为输出颜色格式的转换图像，将多个下采样滤波器应用于转换的图像，并估计每个滤波器的失真选择产生最小失真的滤波器。 失真估计包括应用上采样滤波器，并且基于所选择的滤波器输出像素。 还提出了闭环转换的方法。

公开(公告)号：US09204161B2

公开(公告)日：2015-12-01

申请号：US14462396

申请日：2014-08-18

Applicant: Apple Inc.

Inventor： Barin Geoffry Haskell ,  David William Singer ,  Adriana Dumitras ,  Atul Puri

IPC: H04N7/12 ,  H04N19/513 ,  H04N19/61 ,  H04N19/176 ,  H04N19/102 ,  G06T9/00 ,  H04N19/503 ,  H04N19/46 ,  H04N19/51 ,  H04N19/13 ,  H04N19/91 ,  H04N19/132 ,  H04N19/43 ,  H04N19/587 ,  H04N19/577 ,  H04N19/40

CPC classification number: H04N19/513 ,  G06T9/005 ,  H04N19/13 ,  H04N19/132 ,  H04N19/176 ,  H04N19/40 ,  H04N19/43 ,  H04N19/44 ,  H04N19/46 ,  H04N19/503 ,  H04N19/51 ,  H04N19/577 ,  H04N19/587 ,  H04N19/61 ,  H04N19/91 ,  H04N21/4305

Abstract: A method and apparatus for variable accuracy inter-picture timing specification for digital video encoding is disclosed. Specifically, the present invention discloses a system that allows the relative timing of nearby video pictures to be encoded in a very efficient manner. In one embodiment, the display time difference between a current video picture and a nearby video picture is determined. The display time difference is then encoded into a digital representation of the video picture. In a preferred embodiment, the nearby video picture is the most recently transmitted stored picture. For coding efficiency, the display time difference may be encoded using a variable length coding system or arithmetic coding. In an alternate embodiment, the display time difference is encoded as a power of two to reduce the number of bits transmitted.

Abstract translation: 公开了一种用于数字视频编码的可变精度画面间时序规范的方法和装置。 具体地说，本发明公开了一种允许以非常有效的方式编码附近视频图像的相对定时的系统。 在一个实施例中，确定当前视频图像和附近视频图像之间的显示时间差。 然后将显示时间差编码为视频图像的数字表示。 在优选实施例中，附近的视频图像是最近发送的存储图像。 对于编码效率，可以使用可变长度编码系统或算术编码对显示时间差进行编码。 在替代实施例中，显示时间差被编码为2的幂，以减少发送的比特数。

公开(公告)号：US09100630B2

公开(公告)日：2015-08-04

申请号：US14268168

申请日：2014-05-02

Applicant: Apple Inc.

Inventor： David William Singer ,  Courtney Ann Kennedy

IPC: G06K9/50 ,  H04N5/907 ,  G06F17/30 ,  G06K9/00 ,  G06K9/46 ,  G06T7/00

CPC classification number: H04N5/907 ,  G06F17/30265 ,  G06F17/30793 ,  G06F17/30817 ,  G06K9/00221 ,  G06K9/00255 ,  G06K9/46 ,  G06T7/73

Abstract: A perimeter around a detected object in a frame of image data can be generated in a first coordinate system. The perimeter can be converted from the first coordinate system into a second coordinate system having the same aspect ratio as the first coordinate system. A first metadata entry can include dimensions of image data in the second coordinate system. A second metadata entry can provide a location and dimensions of the converted perimeter in the second coordinate space. Additional metadata can indicate matching objects between frames, position of an object relative to other objects in a frame, a probability that an object is correctly detected, and a total number of objects detected across multiple frames of image data.

Abstract translation: 可以在第一坐标系中生成图像数据的帧中的检测对象周围的周边。 周边可以从第一坐标系转换成具有与第一坐标系相同的纵横比的第二坐标系。 第一元数据条目可以包括第二坐标系中的图像数据的尺寸。 第二元数据条目可以提供第二坐标空间中转换的周边的位置和尺寸。 附加元数据可以指示帧之间的匹配对象，对象相对于帧中的其他对象的位置，正确检测对象的概率以及跨多个图像数据帧检测到的对象的总数。

公开(公告)号：US20140240603A1

公开(公告)日：2014-08-28

申请号：US14268168

申请日：2014-05-02

Applicant: Apple Inc.

Inventor： David William Singer ,  Courtney Ann Kennedy

IPC: H04N5/907

CPC classification number: H04N5/907 ,  G06F17/30265 ,  G06F17/30793 ,  G06F17/30817 ,  G06K9/00221 ,  G06K9/00255 ,  G06K9/46 ,  G06T7/73

Abstract: A perimeter around a detected object in a frame of image data can be generated in a first coordinate system. The perimeter can be converted from the first coordinate system into a second coordinate system having the same aspect ratio as the first coordinate system. A first metadata entry can include dimensions of image data in the second coordinate system. A second metadata entry can provide a location and dimensions of the converted perimeter in the second coordinate space. Additional metadata can indicate matching objects between frames, position of an object relative to other objects in a frame, a probability that an object is correctly detected, and a total number of objects detected across multiple frames of image data.

Abstract translation: 可以在第一坐标系中生成图像数据的帧中的检测对象周围的周边。 周边可以从第一坐标系转换成具有与第一坐标系相同的纵横比的第二坐标系。 第一元数据条目可以包括第二坐标系中的图像数据的尺寸。 第二元数据条目可以提供第二坐标空间中转换的周边的位置和尺寸。 附加元数据可以指示帧之间的匹配对象，对象相对于帧中的其他对象的位置，正确检测对象的概率以及跨多个图像数据帧检测到的对象的总数。