知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

16 records (took 0.014 seconds)

    Virtual environment development method and system
    1.
    发明授权
    Virtual environment development method and system 有权

    公开(公告)号：US12138542B2

    公开(公告)日：2024-11-12

    申请号：US17867896

    申请日：2022-07-19

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Guy Moss ,  Timothy Bradley ,  Maria Chiara Monti

    IPC: A63F13/56 ,  A63F13/69 ,  G06N3/08

    Abstract: A method of controlling at least a first non-player object within a virtual environment of an application includes: selecting a template non-player object behavioural AI model, the AI model being previously trained separately to the application using reinforcement learning to characterise behaviour of a respective non-player object type, from among a plurality of template AI models, associating one or more non-player objects of the application with the selected template AI model, and for the or each associated non-player object, inputting application state information to an input interface of the template AI model for receiving state information relevant to the associated non-player object's type, and receiving from an output interface of the template AI model non-player object state information, and then updating the state of the respective non-player object for the virtual environment of the application responsive to the received non-player object state information.

    METHOD AND SYSTEM FOR ESTIMATING THE GEOMETRY OF A SCENE
    2.
    发明申请
    METHOD AND SYSTEM FOR ESTIMATING THE GEOMETRY OF A SCENE 有权

    公开(公告)号：US20210125398A1

    公开(公告)日：2021-04-29

    申请号：US17075243

    申请日：2020-10-20

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Timothy Bradley ,  Fabio Cappello

    IPC: G06T15/20 ,  G06T7/70 ,  G06T19/00 ,  G06T7/62 ,  G06T19/20

    Abstract: A method of obtaining real world scale information for a scene comprises includes obtaining at least one image of a plurality of objects in a scene; detecting at least some of the objects in the at least one image as corresponding to pre-determined objects; generating a 3D reconstruction of the scene based on the image content of the at least one image; determining a relative size of each object in the 3D reconstruction of the scene in at least one dimension, the relative size being defined in dimensions of the generated 3D reconstruction; wherein where the relative size of each object is determined based on a distance between at least two points corresponding to that object as transformed into 3D space; obtaining a size probability distribution function for each object detected in the at least one image, each size probability distribution function defining a range of sizes in at least one dimension that a corresponding object is likely to possess in real world units; resealing the size probability distribution function for each detected object based on a corresponding relative size of that object in the 3D reconstruction; and estimating a geometry of the scene in real world units by combining the re-scaled probability distribution function for at least one detected object with the re-scaled probability distribution function for at least one other detected object.

    APPARATUS FOR GENERATING DATASETS FOR TRAINING MACHINE LEARNING MODELS, AND A METHOD THEREOF
    4.
    发明公开
    APPARATUS FOR GENERATING DATASETS FOR TRAINING MACHINE LEARNING MODELS, AND A METHOD THEREOF 审中-公开

    公开(公告)号：US20240265679A1

    公开(公告)日：2024-08-08

    申请号：US18430733

    申请日：2024-02-02

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Ryan Spick ,  Timothy Bradley ,  Guy Moss ,  Pierluigi Vito Amadori ,  Ayush Raina

    IPC: G06V10/774

    CPC classification number: G06V10/774

    Abstract: An apparatus for generating datasets for training machine learning models includes: a receiving unit configured to receive video data comprising sequential image frames; a storage unit configured to store a plurality of the sequential image frames; and a selecting unit configured to select, for a target image frame, a subset of stored image frames, the subset providing contextual data relating to the target image frame for the machine learning model. The selecting unit is configured to successively generate sampling values, wherein a difference between successive sampling values increases with each successively generated sampling value; and the selecting unit is configured to select a given image frame from the stored image frames in dependence upon whether a number of sequential image frames between the given image frame and the target image frame coincides with one of the successively generated sampling values.

    SYSTEM AND METHOD FOR TRAINING A MACHINE LEARNING MODEL
    6.
    发明公开
    SYSTEM AND METHOD FOR TRAINING A MACHINE LEARNING MODEL 审中-公开

    公开(公告)号：US20240185135A1

    公开(公告)日：2024-06-06

    申请号：US18513849

    申请日：2023-11-20

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Ryan Spick ,  Guy Moss ,  Timothy Bradley ,  Pierluigi Vito Amadori

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: A system for generating a training dataset for a machine learning process, and training a machine learning model, the system comprising a data obtaining unit configured to obtain training data comprising a plurality of events of interest and the behaviour of an agent corresponding to those events, an event identifying unit configured to identify, based upon one or more corresponding indicators, the occurrence of an event of interest in the training data, a list generating unit configured to generate a list of identified events in the training data, wherein identified events are added to the list with a probability that is inversely proportional to the frequency of the occurrence of that event within the training data, a dataset generating unit configured to generate a dataset comprising information about the events contained in the generated list, and a training unit configured to train a machine learning model using the generated dataset, wherein the machine learning model is trained to generate behaviour for an agent corresponding to events within the generated dataset.

    Method and system for estimating the geometry of a scene
    8.
    发明授权
    Method and system for estimating the geometry of a scene 有权

    公开(公告)号：US11250618B2

    公开(公告)日：2022-02-15

    申请号：US17075243

    申请日：2020-10-20

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Timothy Bradley ,  Fabio Cappello

    IPC: G06T15/00 ,  G06T15/20 ,  G06T7/62 ,  G06T7/70 ,  G06T19/00 ,  G06T19/20

    Abstract: A method of obtaining real world scale information for a scene includes obtaining at least one image of a plurality of objects in a scene; detecting at least some of the objects in the at least one image as corresponding to pre-determined objects; generating a 3D reconstruction of the scene based on the image content of the at least one image; determining a relative size of each object in the 3D reconstruction of the scene in at least one dimension, the relative size being defined in dimensions of the generated 3D reconstruction; where the relative size of each object is determined based on a distance between at least two points corresponding to that object as transformed into 3D space; obtaining a size probability distribution function for each object detected in the at least one image, each size probability distribution function defining a range of sizes in at least one dimension that a corresponding object is likely to possess in real world units; resealing the size probability distribution function for each detected object based on a corresponding relative size of that object in the 3D reconstruction; and estimating a geometry of the scene in real world units by combining the re-scaled probability distribution function for at least one detected object with the re-scaled probability distribution function for at least one other detected object.

    Image acquisition system and method
    9.
    发明授权
    Image acquisition system and method 有权

    公开(公告)号：US11568893B2

    公开(公告)日：2023-01-31

    申请号：US16877619

    申请日：2020-05-19

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Patrick John Connor ,  Timothy Bradley ,  Andrew William Walker

    IPC: G11B20/10 ,  G11B27/30

    Abstract: A method of capturing free viewpoint content at a location includes recording video on each of a plurality of portable video recording devices at the location; each portable video recording device detecting a wireless synchronisation signal transmitted at the location; and each portable video recording device periodically adding a timestamp to its respective recorded video; where the timestamp is responsive to the detected wireless synchronisation signal, thereby enabling synchronisation of a plurality of recorded videos responsive to the timestamps.

    VIRTUAL ENVIRONMENT DEVELOPMENT METHOD AND SYSTEM
    10.
    发明申请
    VIRTUAL ENVIRONMENT DEVELOPMENT METHOD AND SYSTEM 有权

    公开(公告)号：US20230023980A1

    公开(公告)日：2023-01-26

    申请号：US17867896

    申请日：2022-07-19

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Guy Moss ,  Timothy Bradley ,  Maria Chiara Monti

    IPC: A63F13/56 ,  A63F13/69 ,  G06N3/08

    Abstract: A method of controlling at least a first non-player object within a virtual environment of an application includes: selecting a template non-player object behavioural AI model, the AI model being previously trained separately to the application using reinforcement learning to characterise behaviour of a respective non-player object type, from among a plurality of template AI models, associating one or more non-player objects of the application with the selected template AI model, and for the or each associated non-player object, inputting application state information to an input interface of the template AI model for receiving state information relevant to the associated non-player object's type, and receiving from an output interface of the template AI model non-player object state information, and then updating the state of the respective non-player object for the virtual environment of the application responsive to the received non-player object state information.

Patent Agency Ranking