公开(公告)号：US10275890B2

公开(公告)日：2019-04-30

申请号：US15351821

申请日：2016-11-15

Applicant: Sony Interactive Entertainment Inc.

Inventor： Hiroyuki Segawa ,  Tetsugo Inada ,  Akio Ohba ,  Hirofumi Okamoto ,  Atsushi Kimura ,  Daisuke Tahara

IPC: G06K9/34 ,  G06T7/143 ,  G06T7/254 ,  G06T7/11 ,  G06T7/174 ,  G06T7/194

Abstract: Disclosed herein is an image processing device including a background model creation section adapted to create a plurality of background models based on statistical distribution of a plurality of image frame sets, the image frame sets differing in length of time, and each of the image frame sets including a plurality of input frames; and a background image creation section adapted to create a background image by referring to the plurality of background models.

公开(公告)号：US10235560B2

公开(公告)日：2019-03-19

申请号：US15712343

申请日：2017-09-22

Applicant: Sony Interactive Entertainment Inc.

Inventor： Akio Ohba ,  Hiroyuki Segawa ,  Tetsugo Inada

IPC: H04N13/341 ,  G06K9/00 ,  H04N7/14 ,  G06T11/00 ,  G06T19/20 ,  H04N13/239

Abstract: Methods and apparatus provide for: capturing an image of an object, which includes a face of a person wearing an optical display apparatus by which to observe a stereoscopic image that contains a first parallax image and a second parallax image obtained when the object in a three-dimensional (3D) space is viewed from different viewpoints; identifying the optical display apparatus included in the image of the object; and generating an image of the face of the person that does not include the optical display apparatus by excluding the identified optical display apparatus, and instead by adding features of the face of the person to a region in which the identified optical display apparatus is excluded.

公开(公告)号：US20180350362A1

公开(公告)日：2018-12-06

申请号：US15771720

申请日：2016-09-08

Applicant: SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Shinichi Honda ,  Hiroyuki Segawa ,  Shinichi Kariya

IPC: G10L15/22 ,  G10L25/78 ,  G10L25/63

Abstract: An information processing apparatus identifies, by using an audio signal acquired by collecting a user's voice, evaluation target time that includes at least either time not including the user's voice or time during which the user is producing a meaningless utterance and produces an output appropriate to the identified evaluation target time.

公开(公告)号：US10055815B2

公开(公告)日：2018-08-21

申请号：US15312210

申请日：2015-05-28

Applicant: SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Akio Ohba ,  Hidehiko Ogasawara ,  Hiroyuki Segawa ,  Tetsugo Inada

IPC: G06K9/00 ,  G06T3/40 ,  G06T5/00

CPC classification number: G06T3/4015 ,  G06T5/002 ,  H04N9/045 ,  H04N13/239 ,  H04N13/257 ,  H04N2209/046

Abstract: An imaging apparatus 12 acquires RAW images 202a and 202b by left and right cameras and performs a demosaicing process for and stepwise reduction of the RAW images 202a and 202b to generate and correct colored image groups 204a and 204b which represent picked up images with a plurality of resolutions (S10 and S12). Image process parameters 206 acquired in the course of the demosaicing process and the correction process are transmitted to a host terminal 20 together with part of colored images and data of a partial image 208 of the RAW image 202a. The host terminal 20 utilizes the image process parameters 206 transmitted from the imaging apparatus 12 to perform a demosaicing process for the partial image 208 to generate and correct a colored image 212 (S16). The host terminal 20 utilizes the colored image transmitted from the imaging apparatus 12 and the colored image 212 generated therein to generate an image 214 to be displayed (S18 and S20).

公开(公告)号：US20250165862A1

公开(公告)日：2025-05-22

申请号：US18841737

申请日：2022-03-15

Applicant: Sony Interactive Entertainment Inc.

Inventor： Shogo Sato ,  Tetsugo Inada ,  Hiroyuki Segawa

IPC: G06N20/00

Abstract: The accuracy of a machine learning model is improved while the maintenance of training data is facilitated. An information processing system outputs, on the basis of an output of a machine learning model being trained with training data when input data is received to the machine learning model as an input, reliability of the output for the input data, generates new training data on the basis of the input data in a case where the reliability satisfies a predetermined condition, and trains the machine learning model with the new training data.

公开(公告)号：US11455985B2

公开(公告)日：2022-09-27

申请号：US16092642

申请日：2017-02-09

Applicant: SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Shinichi Kariya ,  Shinichi Honda ,  Hiroyuki Segawa

IPC: G10L15/22 ,  G10L25/63 ,  G10L15/02

Abstract: An information processing apparatus determines, on the basis of a speech of a user to be evaluated, a reference feature quantity representing a feature of the user's speech at normal times, acquires audio feature quantity data of a target speech to be evaluated made by the user, and evaluates the feature of the target speech on the basis of a comparison result between the audio feature quantity of the target speech and the reference feature quantity.

公开(公告)号：US11450036B2

公开(公告)日：2022-09-20

申请号：US16960991

申请日：2018-01-30

Applicant: Sony Interactive Entertainment Inc.

Inventor： Akio Ohba ,  Takayuki Shinohara ,  Shinya Wada ,  Akihiko Sugawara ,  Takayuki Ishida ,  Hiroyuki Segawa

IPC: G06T11/00 ,  G06T7/246 ,  G06T3/40

Abstract: An input information acquiring section accepts a user's operation. A texture region acquiring section acquires a region of a display image to be presented by use of a texture. A velocity acquiring section acquires for each pixel a movement velocity vector of the texture on a plane of the display image. A texture referencing section adjusts a reference range in an axial direction of the velocity vector in keeping with a magnitude of the movement velocity, before sampling texel values. A pixel value determining section determines a pixel value on the basis of the texel values. An output section outputs the display image.

公开(公告)号：US10885656B2

公开(公告)日：2021-01-05

申请号：US15772935

申请日：2016-09-29

Applicant: Sony Corporation ,  Sony Interactive Entertainment Inc.

Inventor： Atsushi Kimura ,  Daisuke Tahara ,  Hiroyuki Segawa ,  Tetsugo Inada ,  Akio Ohba ,  Hirofumi Okamoto

IPC: G06T7/70 ,  G06T7/60 ,  G06T7/73 ,  G06K9/00

Abstract: [Object] To perform more stable and highly accurate attitude estimation.
[Solution] The attitude optimization unit optimizes the articulation position, the angle, the number of articulations, and the like which are attitude parameters of a human body model (tree structure) by a plurality of optimization techniques so as to match a region in which a human body can exist, and switches among a plurality of optimization techniques and uses an optimum technique. Note that optimization techniques include 1. initial value, 2. algorithm, and 3, restriction, and optimization is performed by switching among these three. For example, it is possible to apply the present disclosure to an image processing device that performs image processing of optimizing the articulation position and angle of a human body model.

公开(公告)号：US20200342636A1

公开(公告)日：2020-10-29

申请号：US16960991

申请日：2018-01-30

Applicant: Sony Interactive Entertainment Inc.

Inventor： Akio Ohba ,  Takayuki Shinohara ,  Shinya Wada ,  Akihiko Sugawara ,  Takayuki Ishida ,  Hiroyuki Segawa

IPC: G06T11/00 ,  G06T7/246 ,  G06T3/40

Abstract: An input information acquiring section accepts a user's operation. A texture region acquiring section acquires a region of a display image to be presented by use of a texture. A velocity acquiring section acquires for each pixel a movement velocity vector of the texture on a plane of the display image. A texture referencing section adjusts a reference range in an axial direction of the velocity vector in keeping with a magnitude of the movement velocity, before sampling texel values. A pixel value determining section determines a pixel value on the basis of the texel values. An output section outputs the display image.

公开(公告)号：US10755704B2

公开(公告)日：2020-08-25

申请号：US15771720

申请日：2016-09-08

Applicant: SONY INTERACTIVE ENTERTAINMENT INC.

Inventor： Shinichi Honda ,  Hiroyuki Segawa ,  Shinichi Kariya

IPC: G10L15/22 ,  G10L15/26 ,  G10L25/48 ,  G10L25/78 ,  G10L25/03 ,  G10L25/63 ,  G10L15/02

Abstract: An information processing apparatus identifies, by using an audio signal acquired by collecting a user's voice, evaluation target time that includes at least either time not including the user's voice or time during which the user is producing a meaningless utterance and produces an output appropriate to the identified evaluation target time.