公开(公告)号：US20240242505A1

公开(公告)日：2024-07-18

申请号：US18414229

申请日：2024-01-16

Applicant: RadiusAI, Inc.

Inventor： Abhinav Yarlagadda ,  Enis Dengi ,  Sai Krishna Bashetty ,  Alexander Magsam ,  Sharan Raja ,  Stephen McCracken ,  Xaio Liu ,  Raghavendra Nakka ,  Nathan Kelly ,  Tarik Temur ,  Siva Naga Raju Balusu ,  Uday Bhargav Reddy Murikinati ,  Girisha Lakshmi Nakka ,  Marek Niemyjski ,  Todd Ellering ,  Jeffrey Kershner ,  Dana Altier ,  Paul Mills

IPC: G06V20/52 ,  G06V10/12 ,  G06V10/82 ,  G06V10/94 ,  G06V20/40 ,  G06V40/10

CPC classification number: G06V20/52 ,  G06V10/12 ,  G06V10/82 ,  G06V10/95 ,  G06V20/41 ,  G06V40/10 ,  G06V2201/10

Abstract: Visual analytics systems can use video data from cameras placed throughout a location (e.g., a store or a hospital) to determine poses, gestures, tracks, journeys, and actions, and thereby to provide broader analytics useful in realizing efficiencies and improving human behaviors. Data from visual analytics systems can be used to generate alerts, make useful predictions, and run simulations to test hypotheses.

公开(公告)号：US12041337B2

公开(公告)日：2024-07-16

申请号：US17635936

申请日：2020-06-12

Applicant: Sony Group Corporation

Inventor： Taichi Saito

IPC: H04N23/611 ,  G06T7/70 ,  G06V10/22 ,  G06V20/60 ,  G06V40/10

CPC classification number: H04N23/611 ,  G06T7/70 ,  G06V10/22 ,  G06V20/60 ,  G06V40/113 ,  G06T2207/30196 ,  G06V2201/10

Abstract: An imaging control apparatus includes an identification unit that identifies an object to be introduced and an object introducer who introduces the object to be introduced individually as subjects on the basis of captured image data obtained by an imaging unit of an imaging device, a selection unit that selects one of the object to be introduced and the object introducer as a target subject on the basis of a positional relationship between at least any two of the object to be introduced, the object introducer, and the imaging device, and an imaging control unit that performs imaging control on a subject selected as the target subject by the selection unit.

公开(公告)号：US20240233337A9

公开(公告)日：2024-07-11

申请号：US17969444

申请日：2022-10-19

Applicant: Mineral Earth Sciences LLC

Inventor： Yueqi Li

IPC: G06V10/774 ,  G06V10/764 ,  G06V10/776 ,  G06V20/10 ,  G06V20/13 ,  G06V20/70

CPC classification number: G06V10/774 ,  G06V10/764 ,  G06V10/776 ,  G06V20/13 ,  G06V20/188 ,  G06V20/70 ,  G06V2201/10

Abstract: Implementations are described herein for utilizing the spectral-, spatial-, and temporal-information of a satellite image time series to facilitate crop control or monitoring. In various implementations, a plurality of training examples may be assembled for a generative model. Each training example of the plurality of training examples may include a respective high-resolution image capturing a respective region and a corresponding low-resolution satellite image time series capturing the respective region. The plurality of training examples can be used to train the generative model, to acquire a trained generative model. A high-resolution image depicting one or more agricultural conditions for a given region, can be received and processed using the trained generative model, to generate a synthetic low-resolution satellite image time series, where the synthetic low-resolution satellite image time series represent the one or more agricultural conditions.

公开(公告)号：US12015865B2

公开(公告)日：2024-06-18

申请号：US17832624

申请日：2022-06-04

Applicant: Jeshurun de Rox

Inventor： Jeshurun de Rox

IPC: H04N5/222 ,  G06V10/764 ,  G10L15/22 ,  G10L15/26 ,  H04N23/60 ,  H04N23/611 ,  H04N23/62

CPC classification number: H04N5/2222 ,  G06V10/764 ,  H04N23/611 ,  H04N23/62 ,  H04N23/64 ,  G06V2201/10 ,  G10L15/22 ,  G10L2015/223 ,  G10L15/26

Abstract: A system for a user taking photographs or videos to help evoke genuine emotions of one or a plurality of live camera subjects, comprising a digital device with a processor, a display, and system memory, a software application with a graphical user interface installed on the digital device or a remote server, wherein said application is used to store, manage, access, and view metadata tagged prompts, a pre-loaded library of metadata tagged prompts, wherein said prompts being emotive phrase(s), direction(s), image(s), sound(s), and/or animation(s), wherein said application has a two-stage filter to successively refine the list of prompts to be presented to the user, and a prompt delivery system to convey prompts to one or a plurality of live camera subjects.

公开(公告)号：US12003732B2

公开(公告)日：2024-06-04

申请号：US17963924

申请日：2022-10-11

Applicant: Alibaba Group Holding Limited

Inventor： Tae Meon Bae ,  Minghai Qin ,  Guanlin Wu ,  Yen-Kuang Chen ,  Qinggang Zhou ,  Shaolin Xie

IPC: H04N19/136 ,  A63F13/355 ,  G06V20/40 ,  H04N19/103 ,  H04N19/179

CPC classification number: H04N19/136 ,  A63F13/355 ,  G06V20/41 ,  G06V20/46 ,  H04N19/103 ,  H04N19/179 ,  A63F2300/534 ,  A63F2300/538 ,  G06V2201/10

Abstract: Scene aware video content encoding techniques can determine if video content is a given content type and is one of one or more given titles that include one or more given scenes. The one or more given scenes of the video content of the given type and given one of the titles can be encoded using corresponding scenes specific encoding parameter values, and the non-given scenes can be encoded using one or more general encoding parameter values. The one or more given titles can be selected based on a rate of streaming of various video content titles of the given type.

公开(公告)号：US11989758B2

公开(公告)日：2024-05-21

申请号：US17898671

申请日：2022-08-30

Applicant: ROVI GUIDES, INC.

Inventor： Ankur Anil Aher ,  Jeffry Copps Robert Jose ,  Reda Harb

IPC: G06Q30/00 ,  G06Q30/0241 ,  G06Q30/0273 ,  G06V10/774

CPC classification number: G06Q30/0273 ,  G06Q30/0276 ,  G06V10/774 ,  G06Q30/0277 ,  G06V2201/10

Abstract: A computer-implemented method and an apparatus are provided for presenting an option to purchase an NFT based on a scene of a media asset to an advertiser. One example computer-implemented method includes obtaining, from a first source, a scene of a media asset, determining that the scene comprises a product, obtaining, from a second source, a non-fungible token (NFT) based on the scene, matching the NFT to an advertiser based on the product, and presenting an option to purchase the matched NFT to the advertiser.

公开(公告)号：US11978260B2

公开(公告)日：2024-05-07

申请号：US17412018

申请日：2021-08-25

Applicant: Axon Enterprise, Inc.

Inventor： Matti Suksi ,  Jesse Hakanen ,  Juha Alakarhu

IPC: G06V30/24 ,  G06V10/24 ,  G06V20/56 ,  G06V10/62 ,  G06V20/62 ,  G06V30/10

CPC classification number: G06V20/56 ,  G06V10/245 ,  G06V30/2504 ,  G06V10/62 ,  G06V20/625 ,  G06V30/10 ,  G06V2201/10

Abstract: System and methods are disclosed for rapid license plate reading. A first image having a first resolution may be generated. A location of a license plate in the first image may be detected. The license plate may be read from a second image in accordance with the location of the license plate. The second image may have a second resolution greater than the first resolution. In embodiments, reading the license plate may comprise tracking the license plate across a plurality of license plate images.

公开(公告)号：US20240144473A1

公开(公告)日：2024-05-02

申请号：US18277249

申请日：2022-02-11

Applicant: King's College London

Inventor： Reza Razavi ,  Andrew P. King ,  Bram Ruijsink ,  Esther Puyol Anton

IPC: G06T7/00 ,  G06V10/82

CPC classification number: G06T7/0012 ,  G06V10/82 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30048 ,  G06V2201/031 ,  G06V2201/10

Abstract: The present disclosure relates to a method for automated characterisation of images obtained using a medical imaging modality, in particular, the present disclosure relates to a method for analysis of cine cardiac magnetic resonance (CMR) images using an artificial intelligence (AI) framework.

公开(公告)号：US20240135687A1

公开(公告)日：2024-04-25

申请号：US18402528

申请日：2024-01-02

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Santle Camilus Kulandai Samy ,  Rajkiran Kumar Gottumukkal ,  Yohai Falik ,  Rajiv Ramanasankaran ,  Prantik Sen ,  Deepak Chembakassery Rajendran

IPC: G06V10/774 ,  G06T7/246 ,  G06V10/764 ,  G06V20/40 ,  G06V20/70 ,  G06V40/10

CPC classification number: G06V10/774 ,  G06T7/248 ,  G06V10/764 ,  G06V20/41 ,  G06V20/70 ,  G06V40/10 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06V2201/10

Abstract: Disclosed herein is an object detection system, including apparatuses and methods for object detection. An implementation may include receiving a first class of a first object depicted in an image frame from a classification model and subsequently receiving a second image frame. The implementation further includes predicting, using a classification tracking model, that the classification model will output the first class for the second image frame and then detecting whether the first class is in fact outputted. The implementation includes determining that the second image frame should be added to a training dataset for the classification model when detecting that the classification model did not generate the first class for the second image frame as predicted and re-training the classification model using the training dataset.

公开(公告)号：US20240135683A1

公开(公告)日：2024-04-25

申请号：US17969444

申请日：2022-10-18

Applicant: Mineral Earth Sciences LLC

Inventor： Yueqi Li

IPC: G06V10/774 ,  G06V10/764 ,  G06V10/776 ,  G06V20/10 ,  G06V20/13 ,  G06V20/70

CPC classification number: G06V10/774 ,  G06V10/764 ,  G06V10/776 ,  G06V20/13 ,  G06V20/188 ,  G06V20/70 ,  G06V2201/10

Abstract: Implementations are described herein for utilizing the spectral-, spatial-, and temporal-information of a satellite image time series to facilitate crop control or monitoring. In various implementations, a plurality of training examples may be assembled for a generative model. Each training example of the plurality of training examples may include a respective high-resolution image capturing a respective region and a corresponding low-resolution satellite image time series capturing the respective region. The plurality of training examples can be used to train the generative model, to acquire a trained generative model. A high-resolution image depicting one or more agricultural conditions for a given region, can be received and processed using the trained generative model, to generate a synthetic low-resolution satellite image time series, where the synthetic low-resolution satellite image time series represent the one or more agricultural conditions.