公开(公告)号：US20240212352A1

公开(公告)日：2024-06-27

申请号：US18472672

申请日：2023-09-22

Applicant: Fujitsu Limited

Inventor： Yuka JO ,  Kentaro MURASE

IPC: G06V20/52 ,  G06T7/20 ,  G06V10/25 ,  G06V10/764 ,  G06V40/20

CPC classification number: G06V20/52 ,  G06T7/20 ,  G06V10/25 ,  G06V10/764 ,  G06V40/20 ,  G06T2207/30196 ,  G06V2201/07

Abstract: A non-transitory computer-readable recording medium stores an information output program for causing a computer to execute processing including: acquiring a video of an inside of a store; specifying, by analyzing the acquired video, a first area that includes a store clerk, a second area that includes an object customer who purchases a product, and a first relationship that identifies an interaction between the store clerk and the customer, from the video; determining that the store clerk included in the first area has performed service behavior with respect to the customer included in the second area based on the specified first relationship; and outputting a result of the determination to a display device.

公开(公告)号：US20240212306A1

公开(公告)日：2024-06-27

申请号：US18600189

申请日：2024-03-08

Applicant: Yamaha Corporation

Inventor： Takahiro Hara ,  Daichi Iseri ,  Takahiro Akabane ,  Satoshi Obata ,  Takahiro Yanagawa

IPC: G06V10/25

CPC classification number: G06V10/25 ,  G06V2201/07

Abstract: A performance recording system includes at least one memory and at least one processor. The at least one processor is configured to determine a plurality of candidate regions in a target capture area of a camera by use of first captured imagery generated by the camera configured to capture a plurality of players in a first playing of a piece of music. The at least one processor is configured to select a target area from among the plurality of candidate regions. The at least one processor is configured to extract, from a performance record, a portion corresponding to the target area, the performance record being obtained by capturing the plurality of players in a second playing of the piece of music or being obtained by receiving sounds produced in the second playing.

公开(公告)号：US20240212305A1

公开(公告)日：2024-06-27

申请号：US18595686

申请日：2024-03-05

Applicant: CANON KABUSHIKI KAISHA

Inventor： Ryosuke TSUJI

IPC: G06V10/25 ,  G06T5/50

CPC classification number: G06V10/25 ,  G06T5/50 ,  G06T2207/20221 ,  G06V2201/07

Abstract: An imaging system that performs object detection on the basis of a neural network includes: training data inputting unit configured to input training data for the object detection; network structure designation unit configured to designate a restriction of a network structure in the object detection; dictionary generation unit configured to generate dictionary data for the object detection on the basis of the training data and the restriction of the network structure; and an imaging device configured to perform the object detection on the basis of the dictionary data generated by the dictionary generation unit and performs predetermined imaging control on an object detected through the object detection.

公开(公告)号：US12020491B2

公开(公告)日：2024-06-25

申请号：US17276496

申请日：2019-10-10

Applicant: Mitsubishi Electric Corporation

Inventor： Masashi Watanabe ,  Yukako Takahashi ,  Takuma Kadoya

IPC: G06V20/56 ,  G06T7/13 ,  G06T7/181 ,  G06T7/70

CPC classification number: G06V20/588 ,  G06T7/13 ,  G06T7/181 ,  G06T7/70 ,  G06T2207/30256 ,  G06V2201/07

Abstract: A lane link generation device includes an acquisition unit, a lane link generation unit, and a connection unit. The connection unit acquires first and second sections representing vehicle traveling areas. The lane link generation unit generates lane links in the first section and the second section. When the lane link of the first section and the lane link of the second section have endpoints, the connection unit determines a connection destination endpoint which is an endpoint of a connection destination to be connected to an endpoint and which is an endpoint belonging to a different section, based on determination rule information. The connection unit generates a lane link that connects the endpoint to the determined connection destination endpoint.

公开(公告)号：US12020444B2

公开(公告)日：2024-06-25

申请号：US18462441

申请日：2023-09-07

Applicant: POWERARENA HOLDINGS LIMITED

Inventor： Kin Lun Law ,  Chi Hang Wong

IPC: G06T7/246 ,  G06T7/00 ,  G06T7/215 ,  G06V20/40

CPC classification number: G06T7/246 ,  G06T7/0004 ,  G06T7/215 ,  G06V20/49 ,  G06T2207/20081 ,  G06T2207/30232 ,  G06V2201/07

Abstract: A production line monitoring method and a monitoring system thereof are provided. The monitoring system is configured to obtain a plurality of images of an operator, determine a motion type of the operator in the plurality of images based on an image recognition model, determine a time of occurrence and a motion period of the motion type, and record the time of occurrence and the motion period of the motion type.

公开(公告)号：US20240202999A1

公开(公告)日：2024-06-20

申请号：US18480177

申请日：2023-10-03

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Yong-Ju LEE

IPC: G06T11/20 ,  G06V20/70

CPC classification number: G06T11/206 ,  G06V20/70 ,  G06V2201/07

Abstract: Disclosed herein is a method for organizing and merging scene understanding information of an AI agent. The method includes acquiring an image of a first space, recognizing objects in the image, structuring information about the relationship between the object and information about the states of the objects in the form of a graph, and merging the structured information with information received from a nearby AI agent.

公开(公告)号：US20240202960A1

公开(公告)日：2024-06-20

申请号：US18536582

申请日：2023-12-12

Applicant: CANON KABUSHIKI KAISHA

Inventor： Kazumasa KIMATA

IPC: G06T7/70 ,  G06T7/62 ,  G06V10/25 ,  G09G5/377

CPC classification number: G06T7/70 ,  G06T7/62 ,  G06V10/25 ,  G09G5/377 ,  G06V2201/07

Abstract: An image processing apparatus capable of notifying a user of the presence of a possibility that blur information of a desired subject has not been acquired or of displaying an indicator at a position with good visibility is provided. The image processing apparatus includes one or more processors and a memory storing instructions which, when executed by one or more processors, cause the apparatus to function as a detection unit that detects a subject from an LV image, and a display control unit that displays an indicator indicating blur information on the subject detected by the detection unit so as to be superimposed on the LV image. The display control unit controls a display of the indicator in the LV image based on first information related to a detection region in which the detection unit detects the subject and/or second information related to the subject detected by the detection unit.

公开(公告)号：US20240202889A1

公开(公告)日：2024-06-20

申请号：US18543727

申请日：2023-12-18

Applicant: Elektrobit Automotive GmbH

Inventor： Seyed Hami Nourbakhsh ,  Kavin Chandrasekaran

IPC: G06T5/80 ,  G06T7/246 ,  G06T7/70 ,  G06T7/80 ,  G06V10/74 ,  G06V10/764

CPC classification number: G06T5/80 ,  G06T7/246 ,  G06T7/70 ,  G06T7/80 ,  G06V10/761 ,  G06V10/764 ,  G06V2201/07

Abstract: A calibration matrix is determined for a camera for an automotive vehicle. In a first step, at least one object is detected, which moves in a sequence of camera images between image areas having different levels of distortion. In particular, feature tracking can be carried out for the at least one object. To determine the calibration matrix, first an expected perspective-related distortion of the at least one object is calculated. Moreover, an observed distortion of the at least one object is determined. A camera-related distortion of the at least one object is calculated from the observed distortion and the expected perspective-related distortion. A calibration matrix can then be calculated from the camera-related distortion. This matrix can be applied to the camera images. The method steps can then be iteratively repeated until a minimal camera-related distortion is achieved.

公开(公告)号：US20240196090A1

公开(公告)日：2024-06-13

申请号：US18063920

申请日：2022-12-09

Applicant: GEATER SHINE LIMITED

Inventor： YI-PIN CHANG

IPC: H04N23/67 ,  G06F3/01 ,  G06F3/0488 ,  G06F3/16 ,  G06T5/50 ,  G06T7/20 ,  G06T7/50 ,  G06V20/70

CPC classification number: H04N23/675 ,  G06F3/013 ,  G06F3/0488 ,  G06F3/167 ,  G06T5/50 ,  G06T7/20 ,  G06T7/50 ,  G06V20/70 ,  G06T2207/20221 ,  G06V2201/07

Abstract: The present application discloses an image-capturing system including a first image-sensing module, a second image-sensing module, a processor, and a display panel. The first image-sensing module senses a scene that a user is photographing. The processor detects objects in the scene and attaches labels to the detected objects. The display panel displays a preview image of the sensed scene with the labels of the detected objects for the user to select. The first image-sensing module further tracks and focuses on a first object selected by the user to capture a first image, and the second image-sensing module tracks and focuses on a second object selected by the user to capture a second image. The processor further fuses the first and second images into a resulting image in which the first and the second objects are in focus.

公开(公告)号：US20240193909A1

公开(公告)日：2024-06-13

申请号：US18535946

申请日：2023-12-11

Applicant: Meta Platforms Technologies, LLC

Inventor： Saransh SOLANKI ,  Gregg WYGONIK ,  Yu-Jen LIN ,  Nicci YIN ,  James TICHENOR

IPC: G06V10/70 ,  G02B27/01 ,  G06V10/44

CPC classification number: G06V10/70 ,  G02B27/0172 ,  G06V10/44 ,  G06V2201/07

Abstract: According to examples, an apparatus may include a memory on which is stored machine-readable instructions that when executed by a processor, cause the processor to identify an object of interest in at least one first image of an environment captured by a wearable eyewear device during a first time period and identify the object of interest in at least one second image of the environment captured by a wearable eyewear device during a second time period. The processor may also determine a pattern associated with the object of interest based on the at least one first image of the identified object of interest and the at least one second image. In one regard, the processor may determine patterns associated with the object of interest, which may be hidden to or otherwise undetected by a user of the wearable eyewear device.