公开(公告)号：US20230351261A1

公开(公告)日：2023-11-02

申请号：US18245995

申请日：2021-09-07

Applicant: SONY GROUP CORPORATION

Inventor： YUKI YAMAMOTO ,  YUJI TOKOZUME

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: For example, learning data used for machine learning is efficiently generated. A learning data generating device configured to generate learning data used for learning of a machine learning model, the device including: a data acquisition unit that acquires input data; and a conversion unit that converts the input data into learning data by performing processing on the input data on the basis of a characteristic difference between a characteristic corresponding to a first condition and a characteristic corresponding to a second condition different from the first condition.

公开(公告)号：US20230289980A1

公开(公告)日：2023-09-14

申请号：US18005902

申请日：2021-07-16

Applicant: SONY GROUP CORPORATION

Inventor： YUKI YAMAMOTO

IPC: G06T7/246 ,  G06V10/77

CPC classification number: G06T7/248 ,  G06V10/7715 ,  G06T2207/20081

Abstract: The present technology relates to a learning model generation method, an information processing device, and an information processing system capable of constructing a recognizer with less erroneous detection. A target object is tracked in a reverse direction in time series, the target object being recognized by recognition processing using a recognizer to which a learning model for performing recognition processing on input data is applied, and relearning of the learning model is performed by using data generated on the basis of a result of the tracking. The data is generated by tracking the target object in the reverse direction in time series and adding a label to the target object tracked. The present technology can be applied to, for example, an information processing device that performs relearning of a recognizer that recognizes a predetermined object.

公开(公告)号：US20220019813A1

公开(公告)日：2022-01-20

申请号：US17309362

申请日：2019-11-21

Applicant: SONY GROUP CORPORATION

Inventor： RYUTA SATOH ,  YUSUKE HIEIDA ,  YUKI YAMAMOTO ,  KEITARO YAMAMOTO ,  SEUNGHA YANG

IPC: G06K9/00

Abstract: A device and a method that enable safe driving by performing object recognition using image analysis and inter-vehicle communication information are implemented. Provided are an image analysis unit that analyzes an image captured by a vehicle-mounted camera and performs object recognition in the image, an unknown object identification unit that identifies an unknown object in an image area determined to be an unknown object area as a result of analysis by the image analysis unit, and a communication unit that transmits information to an unknown object such as a second vehicle identified by the unknown object identification unit. The unknown object identification unit identifies the second vehicle, which is an unknown object in the image area determined to be the unknown object area, using the peripheral object information received through the communication unit. The communication unit transmits unknown object information or control information for travel control of the second vehicle to the second vehicle.

公开(公告)号：US20230215151A1

公开(公告)日：2023-07-06

申请号：US17998929

申请日：2021-05-14

Applicant: SONY GROUP CORPORATION

Inventor： YUKI YAMAMOTO ,  CHRISTOPHER WRIGHT ,  BERNADETTE ELLIOTT-BOWMAN ,  NICHOLAS WALKER

IPC: G06V10/776 ,  G06V10/778 ,  G06V10/98 ,  G06V10/24

CPC classification number: G06V10/776 ,  G06V10/778 ,  G06V10/993 ,  G06V10/24 ,  G06V20/58

Abstract: The present disclosure relates to an information processing apparatus, an information processing method, an information processing system, and a program capable of appropriately evaluating an object recognition filter by simpler processing. A generation unit that generates teacher data of a preprocessing filter provided in a preceding stage of the object recognition filter is generated by a cyclic generative adversarial network (Cyclic GAN) that is unsupervised learning. The teacher data generated by the generated generation unit is applied to the object recognition filter, an evaluation image is generated from a difference between object recognition result images, and an evaluation filter that generates an evaluation image from the evaluation image and the teacher data is generated. The evaluation filter is applied to an input image to generate an evaluation image, and the object recognition filter is evaluated by the generated evaluation image. The present disclosure can be applied to an object recognition device.

公开(公告)号：US20230005510A1

公开(公告)日：2023-01-05

申请号：US17782970

申请日：2020-12-04

Applicant: SONY GROUP CORPORATION

Inventor： YUKI YAMAMOTO ,  TORU CHINEN

IPC: G11B27/34 ,  G11B27/30

Abstract: The present technology relates to an information processing device and a method, and a program capable of improving creation efficiency of content.
An information processing device includes a determination unit that, in a case where time-series display information regarding an audio signal of each of a plurality of tracks is arranged and displayed, determines a display sequence of the display information of the plurality of tracks or a time position of a marker indicating switching of a scene in the audio signal of the plurality of tracks on the basis of the audio signal of each of the plurality of tracks or audio related information regarding each of the plurality of the audio signals. The present technology can be applied to a creation tool for content.

公开(公告)号：US20210326378A1

公开(公告)日：2021-10-21

申请号：US17228953

申请日：2021-04-13

Applicant: SONY GROUP CORPORATION

Inventor： MITSUHIRO HIRABAYASHI ,  YUKI YAMAMOTO ,  TORU CHINEN ,  RUNYU SHI

IPC: G06F16/683 ,  G06F16/16 ,  G06F16/18 ,  G06F16/11 ,  G11B27/00 ,  G11B20/12 ,  G10L19/00 ,  H04N21/439 ,  H04N21/845 ,  H04N21/2343 ,  H04N21/233 ,  H04N21/218

Abstract: The present disclosure relates to an information processing apparatus and an information processing method that enable easy reproduction of audio data of a predetermined kind, of audio data of a plurality of kinds. A file generation device generates an audio file in which audio streams of a plurality of groups is divided into tracks for each one or more of the groups and arranged, and information related to the plurality of groups is arranged. The present disclosure can be applied to an information processing system configured from the file generation device that generates a file, a web server that records the file generated by the file generation device, and a moving image reproduction terminal that reproduces the file, for example.

公开(公告)号：US20240290099A1

公开(公告)日：2024-08-29

申请号：US18572378

申请日：2021-09-16

Applicant: SONY GROUP CORPORATION

Inventor： YUKI YAMAMOTO ,  TAKAYOSHI TAKAYANAGI ,  KAZUMI AOYAMA

IPC: G06V20/50 ,  B25J9/16 ,  G06T7/20 ,  G06V10/764 ,  G06V10/774 ,  G06V20/70

CPC classification number: G06V20/50 ,  B25J9/1697 ,  G06T7/20 ,  G06V10/764 ,  G06V10/774 ,  G06V20/70 ,  G06T2207/10016 ,  G06T2207/20081

Abstract: An information processing apparatus includes: a determination unit that determines that a first object has been detected by a detection model from a first image included in a series of time-series images, the first object having not been detected from one or more second images that are included in the time-series images and chronologically earlier than the first image; a tracking unit that extracts, from the one or more second images, the first object that has been occluded by a second object under a predetermined condition; a labeling unit that adds a label to the first object extracted from the one or more second images; a learning unit that learns the one or more second images including the first object to which the label is added; an update unit that updates the detection model on the basis of a learning result of the learning unit; and a detection unit that detects, from a third image, a third object occluded under the predetermined condition by executing the updated detection model.

公开(公告)号：US20230311953A1

公开(公告)日：2023-10-05

申请号：US18297391

申请日：2023-04-07

Applicant: SONY GROUP CORPORATION ,  SONY SEMICONDUCTOR SOLUTIONS CORPORATION

Inventor： YUKI YAMAMOTO ,  EIJI OBA

IPC: B60W60/00 ,  G06N20/00 ,  B60W40/08 ,  B60W50/14 ,  G05D1/00

CPC classification number: B60W60/0053 ,  G06N20/00 ,  B60W60/0015 ,  B60W60/0059 ,  B60W60/0057 ,  B60W40/08 ,  B60W50/14 ,  G05D1/0061 ,  B60W2540/225 ,  B60W2540/221 ,  B60W2050/146 ,  B60W2420/42 ,  B60W2420/52 ,  G05D2201/0213

Abstract: A configuration is achieved in which driver information and environmental information are input and a safety index value indicating whether or not a driver who is performing automatic driving is in a state of being able to perform safe manual driving or a manual driving recovery available time is estimated. The configuration includes: a driver information acquisition unit that acquires driver information of a movement device such as an automobile; an environmental information acquisition unit that acquires environmental information of the movement device; and a safety determination unit that receives, as an input, the driver information and the environmental information, and learns and calculates a safety index value indicating whether or not a driver in the movement device during automatic driving is in a state of being able to perform safe manual driving. The safety determination unit further estimates a manual driving recovery available time including a time required until the driver in the movement device during the automatic driving becomes able to start the safe manual driving.

公开(公告)号：US20230282226A1

公开(公告)日：2023-09-07

申请号：US18005801

申请日：2021-07-21

Applicant: SONY GROUP CORPORATION

Inventor： YUKI YAMAMOTO

IPC: G10L25/60 ,  G10L21/0364 ,  G06F3/04847 ,  G10L25/30 ,  G10L25/84

CPC classification number: G10L25/60 ,  G10L21/0364 ,  G06F3/04847 ,  G10L25/30 ,  G10L25/84

Abstract: The present technique relates to a signal processing device, method, and program which are capable of reducing the production cost of content.
The signal processing device includes: a voice detection unit that, based on a mixed audio signal containing a sound of a target sound source and a sound of a non-target sound source different from the target sound source, detects a time segment of the sound of the target sound source from the mixed audio signal; and a voice determination unit that, based on (i) label information indicating the time segment of the sound of the target sound source in an audio signal of the target sound source and (ii) a detection result for the time segment of the sound of the target sound source, performs determination processing for determining whether the sound of the target sound source in the mixed audio signal is easy to hear. The present technique can be applied in a signal processing device.

公开(公告)号：US20230254655A1

公开(公告)日：2023-08-10

申请号：US18004507

申请日：2021-06-30

Applicant: SONY GROUP CORPORATION

Inventor： YUKI YAMAMOTO

IPC: H04S7/00 ,  H04S1/00 ,  G10L19/008

CPC classification number: H04S7/302 ,  H04S1/007 ,  G10L19/008 ,  H04S7/305 ,  H04S2400/11

Abstract: The present technology relates to signal processing apparatus and method, and a program which can perform audio reproduction with a realistic feeling. A signal processing apparatus includes a sound source separation unit that extracts, from an input audio signal including a plurality of sound source signals, one or a plurality of the sound source signals by sound source separation; a position information generation unit that generates position information of the extracted sound source signal on the basis of a result of the sound source separation; and an output unit that outputs the extracted sound source signal and the position information as data of an audio object. The present technology can be applied to a signal processing apparatus.