公开(公告)号：US20240355019A1

公开(公告)日：2024-10-24

申请号：US18304181

申请日：2023-04-20

Applicant: Snap Inc.

Inventor： Avihay Assouline ,  Itamar Berger ,  Jonathan Heimann

IPC: G06T11/60 ,  G06F40/20 ,  G06F40/40 ,  G06T7/10 ,  G06T7/60 ,  G06T11/00 ,  G06V10/776 ,  G06V20/20

CPC classification number: G06T11/60 ,  G06F40/20 ,  G06F40/40 ,  G06T7/10 ,  G06T7/60 ,  G06T11/001 ,  G06V10/776 ,  G06V20/20 ,  G06T2200/24 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20092 ,  G06T2207/20132 ,  G06T2207/30201 ,  G06T2210/16 ,  G06T2210/22

Abstract: Methods and systems are disclosed for generating an extended reality (XR) try-on experience based on an image produced by a diffusion model. The system receives an image depicting a real-world object and generates a prompt comprising a textual description of a fashion item. The system analyzes the image and the textual description of the fashion item using a generative machine learning model to generate an artificial image that depicts an artificial object that resembles the real-world object wearing an artificial fashion item matching the textual description of the fashion item. The system identifies an object comprising a real-world product image that matches visual attributes of the artificial fashion item and replaces the artificial fashion item in the artificial image with the object to generate an output image.

公开(公告)号：US20240338839A1

公开(公告)日：2024-10-10

申请号：US18132145

申请日：2023-04-07

Applicant: Comcast Cable Communications, LLC

Inventor： Donald Tolley ,  Hongcheng Wang ,  Karen Chung ,  Sara Cuesta Gonzalez ,  Toufiq Parag

IPC: G06T7/579 ,  G06T7/246 ,  G06T7/73 ,  G06V20/52

CPC classification number: G06T7/579 ,  G06T7/248 ,  G06T7/74 ,  G06V20/52 ,  G06T2200/24 ,  G06T2207/10032 ,  G06T2207/20092 ,  G06T2207/30184 ,  G06T2207/30232

Abstract: Systems, apparatuses, and methods are described for detecting motion and/or objects in images using distance data. An image of an area to be monitored may be used to generate a distance map that maps distances between features in the area and a camera that took the image. Different reactions may be performed based on motion and/or objects detected in images from the camera and determined to be within different distance reaction zones relative to the camera. The different distance reaction zones and reactions may be based on customizable reaction rules. The distance reaction zones and/or reaction rules may be suggested based on similarities between the area to be monitored and other monitored areas.

公开(公告)号：US20240312050A1

公开(公告)日：2024-09-19

申请号：US18373573

申请日：2023-09-27

Applicant: Intel Corporation

Inventor： David Gonzalez Aguirre

IPC: G06T7/73 ,  G06F3/01 ,  G06F3/16 ,  G06V10/70 ,  G06V10/94 ,  G06V20/50 ,  G06V20/70 ,  G10L15/18 ,  G10L15/22

CPC classification number: G06T7/73 ,  G06F3/013 ,  G06F3/167 ,  G06V10/70 ,  G06V10/945 ,  G06V20/50 ,  G06V20/70 ,  G10L15/1815 ,  G10L15/22 ,  G06T2207/20081 ,  G06T2207/20092

Abstract: Various aspects of techniques, systems, and use cases may be used for human-robot collaboration for three-dimensional (3D) functional mapping. An example technique may include receiving identification of a direction or location based on a user gaze identified via an extended reality device, causing environmental data of an environment to be captured using a sensor of a robotic device corresponding to the direction or location based on receiving the identification, and detecting, within the environmental data, at least one physical feature of the environment. The example technique may include determining, from a user input, an annotation to apply to the at least one physical feature, and labeling the at least one physical feature with the annotation.

公开(公告)号：US20240303982A1

公开(公告)日：2024-09-12

申请号：US18443383

申请日：2024-02-16

Applicant: Keyence Corporation

Inventor： Kyosuke TAWARA ,  Tsuyoshi YAMAGAMI ,  Yasuhisa IKUSHIMA

IPC: G06V10/94 ,  G06F3/0484 ,  G06T7/00 ,  G06T7/73 ,  G06V10/764

CPC classification number: G06V10/945 ,  G06F3/0484 ,  G06T7/0004 ,  G06T7/73 ,  G06V10/764 ,  G06T2200/24 ,  G06T2207/20081 ,  G06T2207/20092 ,  G06T2207/30164

Abstract: The present disclosure is to allow both a rule-based tool and a machine learning tool to be set on a common interface, thereby reducing the time and effort of the user. An image processing device 1: generates a user interface screen for displaying a setting window; receives an input for arranging a machine learning tool and a rule-based tool in the setting window of the user interface screen, and an input of a common data set including a plurality of images to be referred to by the machine learning tool and the rule-based tool; and executes one of the image processing by the machine learning tool or the image processing by the rule-based tool on the data set, and executes the other image processing on the data set after the one image processing is executed.

公开(公告)号：US12081964B2

公开(公告)日：2024-09-03

申请号：US17641747

申请日：2020-08-21

Applicant: LG ELECTRONICS INC.

Inventor： Sungwon Jung ,  Tacksung Choi

IPC: H04S7/00 ,  G06T7/70 ,  G06V20/50 ,  H04M1/60 ,  H04S3/00 ,  H04S5/00

CPC classification number: H04S7/303 ,  G06T7/70 ,  G06V20/50 ,  H04S3/008 ,  G06T2207/20092 ,  H04S2400/01 ,  H04S2400/13

Abstract: A terminal for outputting multi-channel audio using a plurality of audio devices, the terminal can include a camera; a communication interface configured to communicate with a plurality of first audio devices; and a processor configured to receive device information about the plurality of first audio devices through the communication interface or the camera; configure a multi-channel audio system including at least two second audio devices selected from among the plurality of first audio devices based on the device information; and output audio data through the at least two second audio devices based on audio system information corresponding to the multi-channel audio system.

公开(公告)号：US20240282096A1

公开(公告)日：2024-08-22

申请号：US18583862

申请日：2024-02-22

Applicant: FENG-TSO SUN ,  YI-TING YEH ,  FENG-YU SUN ,  Kapito Inc.

Inventor： FENG-TSO SUN ,  YI-TING YEH ,  FENG-YU SUN ,  JYUN-TANG HUANG ,  RONG-HUA CHANG ,  MENG-TSE SHEN

IPC: G06V10/94 ,  G06T7/00 ,  G06V10/44 ,  G06V10/75 ,  G06V10/764 ,  G06V10/778 ,  H04N7/18

CPC classification number: G06V10/945 ,  G06T7/001 ,  G06V10/443 ,  G06V10/751 ,  G06V10/764 ,  G06V10/7788 ,  H04N7/181 ,  G06T2200/24 ,  G06T2207/20081 ,  G06T2207/20092 ,  G06T2207/30108

Abstract: An interactive user feedback system for enhancing the inspection accuracy of an automated visual inspection (AVI) system is disclosed. When working normally, the AVI system acquires an article image from a continuous article transferred by a transfer equipment, and then determines whether there is at least one defect feature existing in the article image or not. Subsequently, the interactive user feedback system enables a display of the electronic device show an inspection report region consisting of M×N sub-regions. As such, the display is enabled to show a zoom-in sub-image containing at least one defect after a sub-region is clicked. Therefore, by viewing the zoom-in sub-image, an inspector can determine whether a defect classification data made by the AVI system is correct or not. If not, the inspector is able to revise the defect classification data through the interactive user feedback system.

公开(公告)号：US12067684B2

公开(公告)日：2024-08-20

申请号：US17732128

申请日：2022-04-28

Applicant: Inter IKEA Systems B.V.

Inventor： Martin Enthed ,  Gustav Olsson

IPC: G06T19/00 ,  G06T7/10 ,  G06T15/08 ,  G06T15/20 ,  G06T19/20 ,  G06V20/64 ,  G06V20/70

CPC classification number: G06T19/006 ,  G06T7/10 ,  G06T15/08 ,  G06T15/20 ,  G06T19/20 ,  G06V20/64 ,  G06V20/70 ,  G06T2207/20092 ,  G06T2219/2004

Abstract: A computerized method comprising acquiring an image of a physical environment comprising one or more physical entities; generating a virtual view based on the acquired image, the virtual view being a 3D representation of the physical environment and comprising 3D data corresponding to the one or more physical entities of the physical environment; displaying the virtual view overlaid on the acquired image of the physical environment; obtaining bounding volumes for a plurality of 3D object models; merging said bounding volumes for the plurality of 3D object models into a virtual bounding volume, said merging occurring with respect to a particular 3D point within each one of the bounding volumes such that the particular 3D points coincide in the virtual bounding volume; and displaying the virtual bounding volume in the virtual view.

公开(公告)号：US20240273697A1

公开(公告)日：2024-08-15

申请号：US18167477

申请日：2023-02-10

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Florian Michael Scheidegger ,  Dhruti Nilesh Shah ,  Adelmo Cristiano Innocenza Malossi

IPC: G06T7/00 ,  G06T5/00 ,  G06T7/12 ,  G06T7/155 ,  G06T7/162 ,  G06T7/194 ,  G06T11/60 ,  G06V10/26 ,  G06V20/70

CPC classification number: G06T7/0002 ,  G06T5/70 ,  G06T7/12 ,  G06T7/155 ,  G06T7/162 ,  G06T7/194 ,  G06T11/60 ,  G06V10/26 ,  G06V20/70 ,  G06T2200/24 ,  G06T2207/20021 ,  G06T2207/20044 ,  G06T2207/20081 ,  G06T2207/20092 ,  G06T2207/30184

Abstract: According to embodiments, a method, computer system, and computer program product for obtaining boundaries of structural defects of materials in images of structures is provided. The present invention may include loading an image of a structure made of a material having one or more structural defects and running a pipeline according to certain processing parameters. Running the pipeline pre-processes the loaded image to obtain an initial segmentation mask, where the mask defines an initial boundary of the crack. Based on the initial segmentation mask obtained, a graph of a skeletal structure of the crack is generated, where the skeletal structure comprises a backbone and outer substructures. The graph is pruned by cutting away one or more outer subgraphs corresponding to respective outer substructures to obtain a revised skeletal structure. A revised boundary of the crack is obtained based on both the loaded image and the revised skeletal structure.

公开(公告)号：US20240242385A1

公开(公告)日：2024-07-18

申请号：US18562469

申请日：2021-05-28

Applicant: NEC Corporation

Inventor： Tingting Dong

IPC: G06T7/90 ,  G06F16/532 ,  G06F16/583 ,  G06V10/56 ,  G06V10/74 ,  G06V10/776 ,  G06V10/94

CPC classification number: G06T7/90 ,  G06F16/532 ,  G06F16/5838 ,  G06V10/56 ,  G06V10/761 ,  G06V10/776 ,  G06V10/945 ,  G06T2207/10024 ,  G06T2207/20092

Abstract: A color determination apparatus according to one example embodiment of this disclosure includes: at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: extract a first color feature value from an image based on color space information defining a color space, the first color feature value being a feature value with regard to a color of the image; convert a user's specified color to a second color feature value based on the color space information and a probability distribution model expressing color ambiguity, the second color feature value being a feature value with regard to the specified color; and calculate a degree of similarity between the first color feature value and the second color feature value.

公开(公告)号：US12039712B2

公开(公告)日：2024-07-16

申请号：US17186957

申请日：2021-02-26

Applicant: RedZone Robotics, Inc.

Inventor： Justin Starr ,  Galin Konakchiev ,  Foster J Salotti ,  Mark Jordan ,  Nate Alford ,  Thorin Tobiassen ,  Todd Kueny ,  Jason Mizgorski

IPC: G06K9/00 ,  G01M3/38 ,  G06F18/214 ,  G06F18/24 ,  G06F18/40 ,  G06T7/00 ,  G06T7/73 ,  G06V10/764 ,  G06V10/82 ,  G01M3/00

CPC classification number: G06T7/0004 ,  G01M3/38 ,  G06F18/2148 ,  G06F18/24 ,  G06F18/40 ,  G06T7/73 ,  G06V10/764 ,  G06V10/82 ,  G01M3/005 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20092 ,  G06T2207/30108 ,  G06T2207/30184 ,  G06V2201/10

Abstract: One aspect provides operating a mobile pipe inspection platform to obtain two or more types of sensor data for the interior of a pipe; analyzing, using a processor, the two or more types of sensor data using a trained model, where the trained model is trained using a dataset including training sensor data of pipe interiors; the analyzing including performing: identifying, using a processor, a pipe feature location using a first type of the two or more types of sensor data; and classifying, using a processor, an identified pipe feature using a second type of the two or more types of sensor data; and thereafter producing, using a processor, an output including an indication of the classified pipe feature. Other aspects are described and claimed.