-
公开(公告)号：US11971955B1
公开(公告)日：2024-04-30
申请号：US17381833
申请日：2021-07-21
Applicant: Amazon Technologies, Inc.
Inventor： Ria Chakraborty , Madhur Popli , Rachit Lamba , Santosh Kumar Sahu , Rishi Kishore Verma
IPC: G06V10/00 , G06F18/21 , G06F18/214 , G06F18/22 , G06F18/2413 , G06F18/40 , G06N3/04 , G06N3/08 , G06T7/73 , G06V10/75 , G06F3/0482
CPC classification number: G06F18/2148 , G06F18/2155 , G06F18/2163 , G06F18/2178 , G06F18/22 , G06F18/2413 , G06F18/40 , G06N3/04 , G06N3/08 , G06T7/73 , G06V10/751 , G06F3/0482 , G06T2207/20081 , G06T2207/20084 , G06V2201/09
Abstract: Techniques are generally described for machine learning exampled-based annotation of image data. In some examples, a first machine learning model may receive a query image comprising a first depiction of an object-of-interest. In some examples, the first machine learning model may receive a target image representing a scene in which a second depiction of the object-of-interest is visually represented. In various examples, the first machine learning model may generate annotated output image data that identifies a location of the second depiction of the object-of-interest within the target image. In some examples, an object detection model may be trained based at least in part on the annotated output image data.
-
公开(公告)号：US20240087314A1
公开(公告)日：2024-03-14
申请号：US18508334
申请日：2023-11-14
Applicant: The Nielsen Company (US), LLC
Inventor： Kevin Keqiang Deng , Barry Greenberg
CPC classification number: G06V20/40 , G06V20/635 , G06V20/44 , G06V2201/09
Abstract: Methods and apparatus to measure brand exposure in media streams are disclosed. Example apparatus disclosed herein are to determine a first histogram based on at least one of luminance components or chrominance components of a first frame of video, and determine a second histogram based on at least one of luminance components or chrominance components of a second frame of the video. Disclosed example apparatus are also to detect a transition in the video based on the first histogram and the second histogram, and responsive to the detection of the transition in the video. Disclosed example apparatus are further to process a region of interest within at least one of the first frame or the second frame to detect a logo in the region of interest.
-
33.发明授权公开(公告)号：US11888635B2
公开(公告)日：2024-01-30
申请号：US17514477
申请日：2021-10-29
Applicant: MOTOROLA MOBILITY LLC
Inventor： Amit Kumar Agrawal , Jyothsna Bandameedipalli
CPC classification number: H04L12/1831 , G06V10/255 , G06V10/60 , G09B7/02 , H04L12/1822 , H04L65/4015 , G06V2201/09
Abstract: An electronic device, computer program product, and method are provided that automatically manages compliance by a participant during a video communication session. The electronic device communicatively connects over a network to second electronic device(s) during a video communication session. The electronic device receives image stream(s) produced respectively by an image capturing device of a corresponding second electronic device. The electronic device identifies person(s) within the image stream(s) and compares to a roster of at least one person expected to join the video communication session to produce attendance data. The electronic device determines participation data related to an amount of time that the person(s) gaze toward the image capturing device of the corresponding second electronic device. The electronic device communicates, to a host output device, the attendance data and the participation data of the person(s) during a duration of the video communication session.
-
公开(公告)号：US11812912B2
公开(公告)日：2023-11-14
申请号：US16469572
申请日：2017-12-07
Applicant: Henkel AG & Co. KGaA
Inventor： Arnd Kessler , Thomas Weber , Johannes Zipfel , Christian Nitsch , Lars Zuechner , Nadine Franke , Georg Wawer , Alexander Mueller , Clemens Arth
CPC classification number: A47L15/0055 , A47L15/006 , A47L15/0063 , A47L15/4445 , A47L15/4463 , D06F33/37 , D06F39/024 , A47L2401/03 , A47L2401/34 , A47L2501/07 , G06V2201/09
Abstract: A method for the dosing of cleaning agents in cleaning machines, including the steps: receiving control information items, wherein the control information items are dependent on information about a cleaning machine; determining the progress of a cleaning operation; dosing of cleaning agent depending on the received control information items and the determined progress of the cleaning operation; wherein the information about the cleaning machine can be determined via a sensor-based automatic recognition.
-
35.发明公开公开(公告)号：US20230360595A1
公开(公告)日：2023-11-09
申请号：US18143266
申请日：2023-05-04
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Kamal Jnawali , Joonsoo Kim , Chenguang Liu , Chang Su
IPC: G09G3/3208 , G06V20/40 , G06T5/40 , G06T5/00
CPC classification number: G09G3/3208 , G06V20/41 , G06T5/40 , G06T5/002 , G06V2201/09 , G06T2207/10024 , G06T2207/10016 , G09G2320/046 , G09G2320/0257 , G09G2320/0233 , G09G2320/0266
Abstract: One embodiment provides a computer-implemented method that includes receiving region information from a stationary region detection process for a video. A processor performs a flat region ghosting artifact removal process that updates the region information with a flat region indicator utilizing the region information and the video. The processor further performs a region based luminance reduction process utilizing the updated region information with the flat region indicator for display ghosting artifact removal and burn-in protection.
-
Patent Agency Ranking
公开(公告)号：US20230282026A1
公开(公告)日：2023-09-07
申请号：US18116081
申请日：2023-03-01
Applicant: ObjectVideo Labs, LLC
Inventor： Donald Gerard Madden , Ethan Shayne
IPC: G06V40/16 , G06V20/52 , G06V20/40 , G06Q10/083
CPC classification number: G06V40/172 , G06V20/52 , G06V20/44 , G06Q10/083 , G06V2201/09
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for automated package management. One of the methods includes for an image that depicts a package at a property and a person retrieving the package, determining, using data from the image or from a device for the person, whether the person is authorized to retrieve the package; and in response to determining that the person is authorized to retrieve the package, determining to skip performing an automated action that would have been performed if the person was not authorized to retrieve the package.
-
公开(公告)号：US11748785B2
公开(公告)日：2023-09-05
申请号：US16720708
申请日：2019-12-19
Applicant: SLING MEDIA PVT LTD
Inventor： Avinash Chandra Lohumi , Arun Lokman Gangotri
IPC: G06V10/44 , G06V10/764 , G06V10/82 , G06V20/40 , H04N21/44 , H04N21/442 , H04N21/81 , H04N21/234 , G06Q30/0272 , G06F18/211 , G06F18/214 , G06F18/2411 , G06F18/2451
CPC classification number: G06Q30/0272 , G06F18/211 , G06F18/214 , G06F18/2411 , G06F18/2451 , G06V10/454 , G06V10/764 , G06V10/82 , G06V20/41 , G06V20/46 , H04N21/44008 , H04N21/44204 , H04N21/812 , G06V2201/09
Abstract: A method for brand recognition in video by implementing a brand recognition application coupled to a streaming media player, for identifying an observed set of brands streamed in a broadcast video; receiving, by the brand recognition application, a broadcast video stream of a series of images contained in consecutive frames about an object of interest; extracting a set of brand features from each of image received by applying a trained brand recognition model with neural networks in order to detect one or more features related to each displayed object of interest in each frame, wherein the object of interest is associated with a brand image contained video content displayed to a viewer; and displaying, by a graphic user interface, information from the brand recognition application comprising at least time detected of the brand image in the video content of the broadcast video.
-
公开(公告)号：US20230177267A1
公开(公告)日：2023-06-08
申请号：US18103538
申请日：2023-01-31
Applicant: IQVIA Inc.
Inventor： Gary Douglas Shorter , Barry Matthew Ahrens , Cara Elizabeth Willoughby , Yatesh Dass Midha
IPC: G06F40/279 , G06F40/30 , G06V30/413 , G06V30/414 , G06V30/19 , G06V30/416
CPC classification number: G06F40/279 , G06F40/30 , G06V30/413 , G06V30/414 , G06V30/19167 , G06V30/416 , G06V2201/09 , G06V2201/10
Abstract: A computer-implemented tool for automated classification and interpretation of documents, such as life science documents supporting clinical trials, is configured to perform a combination of raw text, document construct, and image analyses to enhance classification accuracy by enabling a more comprehensive machine-based understanding of document content. The combination of analyses provides context for classification by leveraging relative spatial relationships among text and image elements, identifying characteristics and formatting of elements, and extracting additional metadata from the documents as compared to conventional automated classification tools, wherein natural language processing (NLP) is applied to associate text with tokens, and relevant differences and similarities between protocols are identified.
-
39.发明公开公开(公告)号：US20230171372A1
公开(公告)日：2023-06-01
申请号：US17962591
申请日：2022-10-10
Applicant: Amine Arezki
Inventor： Amine Arezki
CPC classification number: H04N5/265 , G06T5/50 , G06T7/70 , G06V2201/09 , G06T2207/20044 , G06T2207/20221 , G06T2207/30196
Abstract: A purpose of the invention is to provide a method and a system for adding or superimposing predetermined pictures, especially advertisement pictures, on predetermined location(s) of moving object(s), especially the clothing of sports players during a match, in a video stream. More generally, the invention aims at superimposing, in a video stream, at least one predetermined image portion at a predetermined location of at least one moving object image, to simulate that the object carries the predetermined image portion on. The disclosure also provides a system for implementing a bidding process to determine which symbols, logos, or messages are overlaid for various simultaneous broadcasts.
-
40.发明公开公开(公告)号：US20240331427A1
公开(公告)日：2024-10-03
申请号：US18620495
申请日：2024-03-28
Applicant: Lucas Bertrand
Inventor： Lucas Bertrand
CPC classification number: G06V30/30 , G06T7/70 , G06V30/19013 , G06V30/191 , G06T2200/24 , G06V2201/02 , G06V2201/09
Abstract: A method, carried out by one or more processors, for analysing the placement in a user interface, by an electronic device, of digital assets, the method comprising scanning image data of a user interface of an electronic device, capturing image data of an instance of the user interface of the electronic device, identifying a parameter of one or more digital assets in the captured image data.
-
-
-
-
-
-
-
-
-
Search Results
81
records
(took 0.018 seconds)
