公开(公告)号：US20240346798A1

公开(公告)日：2024-10-17

申请号：US18685425

申请日：2021-09-15

Applicant: YAMAHA HATSUDOKI KABUSHIKI KAISHA

Inventor： Atsushi YAMAMOTO

IPC: G06V10/25 ,  B25J19/02 ,  G06T7/55 ,  G06T7/73 ,  G06T11/60 ,  G06V10/82

CPC classification number: G06V10/25 ,  B25J19/023 ,  G06T7/55 ,  G06T7/74 ,  G06T11/60 ,  G06V10/82 ,  G06T2207/10028 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30164 ,  G06V2201/06

Abstract: A composite image is generated by combining a gray scale image, referred to as a luminance image, and a depth image respectively representing the plurality of components. In the generated composite image, the shape of the component at a relatively high position among the plurality of components easily remains, and the composite image is useful in confirming such a component.

公开(公告)号：US20240331424A1

公开(公告)日：2024-10-03

申请号：US18712731

申请日：2022-02-15

Applicant: Mitsubishi Electric Corporation

Inventor： Daiki ATA ,  Daisuke AMMI ,  Satoshi NAMEMATSU

IPC: G06V30/19 ,  G06V30/14 ,  G06V30/30

CPC classification number: G06V30/19147 ,  G06V30/14 ,  G06V30/1916 ,  G06V30/30 ,  G06V2201/06

Abstract: A training data acquirer acquires training data including article image data, image-filter-related data indicating a combination of a plurality of image filters used for image processing of the article image data and a value of a parameter for each of the plurality of image filters, and optical character recognition (OCR) score data indicating a score of character recognition output through OCR when image processing is performed on the article image data using the image filters based on the image-filter-related data. A trained model generator generates a trained model indicating a relationship between the article image data, the image-filter-related data, and the OCR score data through machine learning using the training data.

公开(公告)号：US20240321001A1

公开(公告)日：2024-09-26

申请号：US18645068

申请日：2024-04-24

Applicant: KEY TECHNOLOGY, INC.

Inventor： Peter Lodewyckx ,  Marc Van Daele ,  Timothy Justice

IPC: G06V40/12 ,  G06T7/00 ,  G06T7/593 ,  G06T7/80 ,  G06T15/00 ,  G06V20/52

CPC classification number: G06V40/1335 ,  G06T7/0004 ,  G06T7/596 ,  G06T7/85 ,  G06T15/005 ,  G06V20/52 ,  G06T2207/10021 ,  G06T2207/20221 ,  G06T2207/30128 ,  G06V2201/06

Abstract: A method and apparatus for sorting is described, and which includes providing a product stream formed of individual objects of interest having feature aspects which can be detected; generating multiple images of each of the respective objects of interest; classifying the feature aspects of the objects of interest; identifying complementary images by analyzing some of the multiplicity of images; fusing the complementary images to form an aggregated region representation of the complementary images; and sorting the respective objects of interest based at least in part upon the aggregated region representation which is formed.

公开(公告)号：US20240310796A1

公开(公告)日：2024-09-19

申请号：US18583658

申请日：2024-02-21

Applicant: MD Elektronik GmbH

Inventor： Josef OHNI ,  Martina OSSNER ,  Stefan GRANDL ,  Peter HOFINGER

IPC: G05B13/02 ,  G06V10/25 ,  G06V10/764 ,  G06V10/82

CPC classification number: G05B13/027 ,  G06V10/25 ,  G06V10/764 ,  G06V10/82 ,  G06V2201/06

Abstract: Embodiments herein relate to operating a cable processing device by processing at least one cable section by a cable processing unit from an initial configuration to an end configuration, capturing at least one image of the at least one end configuration, applying a trained neural network to the at least one captured image to determine at least one region of interest from the at least one captured image in a first step, and the same neural network being designed to, in a second step, perform a classification of the at least one determined region of interest with regard to the presence of at least one learned error pattern of the at least one end configuration and determining a result associated with the classification. Moreover, a control signal is generated depending on the determined region of interest or depending on the result of the classification.

公开(公告)号：US12080006B2

公开(公告)日：2024-09-03

申请号：US18145512

申请日：2022-12-22

Applicant: MUJIN, INC.

Inventor： Jinze Yu ,  Jose Jeronimo Moreira Rodrigue ,  Ahmed Abouelela

IPC: B25J9/00 ,  B25J9/16 ,  B25J13/08 ,  G06F18/241 ,  G06N20/00 ,  G06T7/41 ,  G06V10/22 ,  G06V10/44 ,  G06V10/56 ,  G06V20/10 ,  B65G61/00

CPC classification number: G06T7/41 ,  B25J9/163 ,  B25J9/1661 ,  B25J9/1664 ,  B25J9/1697 ,  B25J13/08 ,  G06F18/241 ,  G06N20/00 ,  G06V10/22 ,  G06V10/443 ,  G06V10/56 ,  G06V20/10 ,  B65G61/00 ,  G06V10/44 ,  G06V2201/06 ,  G06V2201/07

Abstract: Systems and methods for classifying at least a portion of an image as being textured or textureless are presented. The system receives an image generated by an image capture device, wherein the image represents one or more objects in a field of view of the image capture device. The system generates one or more bitmaps based on at least one image portion of the image. The one or more bitmaps describe whether one or more features for feature detection are present in the at least one image portion, or describe whether one or more visual features for feature detection are present in the at least one image portion, or describe whether there is variation in intensity across the at least one image portion. The system determines whether to classify the at least one image portion as textured or textureless based on the one or more bitmaps.

公开(公告)号：US20240227340A1

公开(公告)日：2024-07-11

申请号：US18558774

申请日：2022-06-10

Applicant: Bayerische Motoren Werke Aktiengesellschaft

Inventor： Bernhard GLUECK ,  Ingo HEINLE ,  Christian SCHEIDIG

IPC: B30B15/26 ,  B21C51/00 ,  B21D22/02 ,  B30B15/30 ,  G06V30/12 ,  G06V30/19

CPC classification number: B30B15/26 ,  B21C51/00 ,  B21D22/02 ,  B30B15/30 ,  G06V30/133 ,  G06V30/19 ,  G05B2219/2622 ,  G06V2201/06

Abstract: Methods, systems, and apparatuses are provided for operating a press in which circuit boards are reshaped. The circuit boards each have a unique serial number. An electronic computing device stores measured values characterizing the associated circuit board for the respective serial number. A capture device in a feed area in which the circuit boards are fed into the press is used to produce images of the serial number. A recognition unit is used to recognize the serial numbers in the images. A recognition rate is determined.

公开(公告)号：US12033345B2

公开(公告)日：2024-07-09

申请号：US17463771

申请日：2021-09-01

Applicant: KunShan Go-Visionox Opto-Electronics Co., Ltd

Inventor： Yuan Zhang ,  Naixi Chen

IPC: G06T7/70 ,  G06T7/00 ,  G06T7/13 ,  G06T7/50 ,  G06V10/22

CPC classification number: G06T7/70 ,  G06T7/0004 ,  G06T7/13 ,  G06T7/50 ,  G06V10/22 ,  G06T2207/30108 ,  G06V2201/06

Abstract: A positioning method including: acquiring a gray-scale image of an object to be measured to determine a gray-scale value of each pixel on the gray-scale image; determining a target area to be measured and a first gray-scale change area adjacent to the target area to be measured based on the gray-scale value of each pixel; determining a target gray-scale value based on a gray-scale value of the target area to be measured and a gray-scale value of each pixel in the first gray-scale change area; determining target pixels that conform to the target gray-scale value in the first gray-scale change area, to use the target pixels as actual edge pixels of the target area to be measured; and determining a relative distance between a center position of the target area to be measured and a reference position, to obtain position information of the target area.

公开(公告)号：US20240212372A1

公开(公告)日：2024-06-27

申请号：US18086976

申请日：2022-12-22

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Chih-Neng Liu ,  Hung-Chun Chou ,  Tsann-Tay Tang

IPC: G06V20/70 ,  G06T7/70 ,  G06V10/75 ,  G06V10/771

CPC classification number: G06V20/70 ,  G06T7/70 ,  G06V10/751 ,  G06V10/771 ,  G06V2201/06

Abstract: An automatic objects labeling method includes: capturing M consecutive image frames at one station of an assembly line. Performing an object detection step which includes selecting a detection image frame that displays an operation using a work piece against a target object from the M consecutive image frames; and calibrating the position range of the target object in the detection image frame; retracing from the detection image frame to select an Nth retraced image frame from the M consecutive image frames; obtaining a labeled image of the target object from the Nth retraced image frame according to the position range; comparing the labeled image with images of the M consecutive image frames to find at least one other labeled image similar to the target object; and storing both the labeled image and the at least one other labeled image as the same labeled data set.

公开(公告)号：US12016310B2

公开(公告)日：2024-06-25

申请号：US17582835

申请日：2022-01-24

Applicant: Bird's Eye Robotics, Inc.

Inventor： Scott Niewohner ,  Lucas Niewohner

IPC: A01K45/00 ,  G01S17/89 ,  G05D1/00 ,  G06V20/56 ,  G06V40/10

CPC classification number: A01K45/005 ,  G01S17/89 ,  G05D1/0214 ,  G05D1/0238 ,  G05D1/0246 ,  G05D1/0274 ,  G06V20/56 ,  G06V40/10 ,  G06V2201/06

Abstract: A mortality recovery device is described. The mortality recovery device provides for autonomous recovery of expired poultry within an environment, such as a poultry barn. The mortality recovery device includes a linkage assembly by which the expired poultry is conveyed to a container. The mortality recovery device includes one or more cameras for detecting the expired poultry. The mortality recovery device also includes one or more cameras for object detection purposes. The mortality recovery device also includes a camera or a LiDAR for mapping the position and orientation (pose) of the mortality recovery device within the environment. By the object detection and the pose information, the mortality recovery device autonomously travels within the environment. The mortality recovery device also includes a spinner assembly for deterring live poultry from the path of the mortality recovery device.

公开(公告)号：US20240066592A1

公开(公告)日：2024-02-29

申请号：US17767542

申请日：2020-10-12

Applicant: GIENANTH GMBH

Inventor： Hans-Juergen BRENNINGER ,  Simon Werner GEIB

IPC: B22D46/00 ,  B22C11/08 ,  B22C19/04 ,  B22D29/04 ,  G06T7/00 ,  G06V20/52

CPC classification number: B22D46/00 ,  B22C11/08 ,  B22C19/04 ,  B22D29/04 ,  G06T7/0004 ,  G06V20/52 ,  G06T2207/30136 ,  G06V2201/06

Abstract: The invention relates to a device and method for improving the quality of automated machine-based casting methods by identification of the cast parts by pattern recognition and structure recognition, said method having the following features: Once the desired casting moulds (12) have been filled and monitored by means of sensors and cameras, and once the casting mould has been broken open, each finished cast part is identified by pattern recognition and pattern tracking, any flashing is removed, and the cast parts are fed to a jet cleaning process.