公开(公告)号：US09141855B2

公开(公告)日：2015-09-22

申请号：US13977506

申请日：2012-12-20

Applicant: Intel Corporation

Inventor： Lin Xu ,  Yangzhou Du ,  Jianguo Li ,  Qiang Li ,  Ya-Ti Peng ,  Yi-Jen Chiu

IPC: G06K9/62 ,  G06K9/74 ,  G06K9/00

CPC classification number: G06K9/0055 ,  G06K9/00248 ,  G06K9/00986 ,  G06K9/3233 ,  G06K9/6201 ,  G06K9/6257 ,  G06K2009/6213

Abstract: Systems, apparatus and methods are described related to accelerated object detection filter using a video estimation module.

Abstract translation: 与使用视频估计模块的加速对象检测滤波器相关的系统，装置和方法被描述。

公开(公告)号：US20150146915A1

公开(公告)日：2015-05-28

申请号：US13977061

申请日：2012-12-18

Applicant: Intel Corporation

Inventor： Ya-Ti Peng ,  Yi-Jen Chiu ,  Jianguo Li

IPC: G06K9/46 ,  G06K9/62 ,  G06T7/00

CPC classification number: G06K9/4609 ,  G06K9/00986 ,  G06K9/6257 ,  G06K9/6286 ,  G06T2207/20024

Abstract: Systems, apparatus, articles, and methods are described related to a hardware-based convolution pre-filter to accelerate object detection.

Abstract translation: 描述了与基于硬件的卷积预滤器相关的系统，装置，物品和方法，以加速对象检测。

公开(公告)号：US12182979B2

公开(公告)日：2024-12-31

申请号：US18474936

申请日：2023-09-26

Applicant: Intel Corporation

Inventor： Ya-Ti Peng ,  Yi-Jen Chiu

IPC: G06T5/94 ,  G06T5/40 ,  G06T7/136 ,  H04N9/64

Abstract: Methods and systems to improve a visual perception of dark scenes in video. An example device includes one or more processors to receive a frame of video segmented into a plurality of sub-regions. A local luminance histogram is generated for each sub-region. A global luminance histogram is generated for the entire frame of video and a global tone mapping curve is generated based on the global luminance histogram. A tone mapping LUT is generated for each sub-region based on the global tone mapping curve and the corresponding local luminance histogram for the sub-region. The frame of video is then modified using the tone mapping LUTs generated for each sub-region and sent to an output device.

公开(公告)号：US11889096B2

公开(公告)日：2024-01-30

申请号：US16914083

申请日：2020-06-26

Applicant: INTEL CORPORATION

Inventor： Chen Wang ,  Ximin Zhang ,  Huan Dou ,  Yi-Jen Chiu ,  Sang-Hee Lee

IPC: G06T9/00 ,  G06T3/40 ,  H04N19/44 ,  H04N19/30 ,  G06N3/08 ,  H04N19/159 ,  H04N19/184 ,  H04N19/176 ,  H04N19/132 ,  G06F18/25 ,  G06V10/82

CPC classification number: H04N19/44 ,  G06F18/251 ,  G06N3/08 ,  G06T3/4007 ,  G06T3/4053 ,  G06T9/002 ,  G06V10/82 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/184 ,  H04N19/30

Abstract: Techniques related to accelerated video enhancement using deep learning selectively applied based on video codec information are discussed. Such techniques include applying a deep learning video enhancement network selectively to decoded non-skip blocks that are in low quantization parameter frames, bypassing the deep learning network for decoded skip blocks in low quantization parameter frames, and applying non-deep learning video enhancement to high quantization parameter frames.

公开(公告)号：US11435819B2

公开(公告)日：2022-09-06

申请号：US17161014

申请日：2021-01-28

Applicant: Intel Corporation

Inventor： Robert J. Johnston ,  Satyanarayana Avadhanam ,  Changliang Wang ,  Narayan Biswal ,  Archie Sharma ,  Richmond Hicks ,  Joydeep Ray ,  Abhishek R. Appu ,  Stanley J. Baran ,  Sang-Hee Lee ,  Atthar H. Mohammed ,  Jong Dae Oh ,  Hiu-Fai Chan ,  Sumit Mohan ,  Jill M. Boyce ,  Yi-Jen Chiu

IPC: G06F3/01 ,  G06T15/10

Abstract: Systems, apparatuses and methods may provide for technology to improve user experience when viewing simulated 3D objects on a display. Head and upper-body movements may be tracked and recognized as gestures to alter the displayed viewing angle. The technology provides for a very natural way to look around, under, or over objects.

公开(公告)号：US20220109853A1

公开(公告)日：2022-04-07

申请号：US17553449

申请日：2021-12-16

Applicant: Intel Corporation

Inventor： Ximin Zhang ,  Yi-Jen Chiu ,  Keith Rowe

IPC: H04N19/147 ,  G06N20/00 ,  H04N19/117 ,  H04N19/127 ,  H04N19/107

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve video encoding. An example apparatus includes at least one memory, instructions, and processor circuitry to generate a pool of clipping index set candidates by executing a machine learning model, select a clipping index set from the pool of the clipping index set candidates based on a rate distortion cost associated with the clipping index set, the clipping index set including clipping coefficients, and filter a video frame based on the clipping coefficients.

公开(公告)号：US10979728B2

公开(公告)日：2021-04-13

申请号：US15495535

申请日：2017-04-24

Applicant: Intel Corporation

Inventor： Jason Tanner ,  Wen-Fu Kao ,  Ping Liu ,  Yi-Jen Chiu ,  Ya-Ti Peng

IPC: H04N19/436 ,  H04N19/53 ,  H04N19/593

Abstract: Systems, apparatuses and methods may include technology to bundle on demand video frames together in clusters having similar encode times based on predicted performance determined by weighted heuristics.

公开(公告)号：US20210099727A1

公开(公告)日：2021-04-01

申请号：US17094742

申请日：2020-11-10

Applicant: Intel Corporation

Inventor： Zhipin Deng ,  Iole Moccagatta ,  Lidong Xu ,  Wenhao Zhang ,  Yi-Jen Chiu

IPC: H04N19/51 ,  G06T7/238 ,  H04N19/57 ,  H04N19/176 ,  H04N19/593

Abstract: Techniques related to motion estimation with neighbor block pattern for video coding.

公开(公告)号：US10923084B2

公开(公告)日：2021-02-16

申请号：US16369469

申请日：2019-03-29

Applicant: Intel Corporation

Inventor： Jong Dae Oh ,  Yi-Jen Chiu

IPC: H04N7/01 ,  G06T7/20 ,  G09G5/393 ,  G06T7/13 ,  G06T7/246

Abstract: Methods, articles, and systems are described for de-interlacing for image processing with reduced artifacts.

公开(公告)号：US20200219229A1

公开(公告)日：2020-07-09

申请号：US16822686

申请日：2020-03-18

Applicant: INTEL CORPORATION

Inventor： Vijay Sundaram ,  Yi-Jen Chiu

IPC: G06T3/40 ,  G06T7/13 ,  G06T7/00 ,  G06K9/62

Abstract: An apparatus for edge aware upscaling is described herein. The apparatus comprises a potential edge detector, a thin-edge detector, a one-directional edge detector, a correlation detector, and a corrector. The potential edge detector identifies potential edge pixels in an input image, and the thin-edge detector detects thin edges in the potential edge pixels of the input image. The one-directional edge detector detects one-directional edges in the potential edge pixels of the input image, and the correlation detector detects strongly correlated edges in the potential edge pixels of the input image. The corrector derives a target output value based on an edge type and classification of a corresponding input pixel as identified by a source map point.