公开(公告)号：WO2023043592A2

公开(公告)日：2023-03-23

申请号：PCT/US2022/041327

申请日：2022-08-24

Applicant: MARTIN ENGINEERING COMPANY

Inventor： ANDRADE, Italo ,  CANAVERDE, Henrique ,  MACHADO, Luiz ,  HARRISON, Paul

IPC: B65G43/02 ,  G01N21/88 ,  G01N21/89 ,  G01N21/8851 ,  G01N21/95607 ,  G06T7/001 ,  G06T15/506 ,  G06T2207/30108 ,  G01B11/06

Abstract: A method includes emitting a laser including a plurality of laser points onto a surface of a conveyor belt, capturing a plurality of first images of the surface of the conveyor belt during a first cycle of the conveyor belt, creating a first three-dimensional image of the surface of the conveyor belt during the first cycle, each of a plurality of locations of the surface of the conveyor belt in the first three-dimensional image being assigned first position data, capturing a plurality of second images of the surface of the conveyor belt during a second cycle of the conveyor belt; creating a second three-dimensional image of the surface during the second cycle, each of the plurality of locations of the surface in the second three-dimensional image being assigned second position data; and determining whether a difference between the first and second position data exceeds a predetermined threshold.

公开(公告)号：WO2021191727A1

公开(公告)日：2021-09-30

申请号：PCT/IB2021/052150

申请日：2021-03-16

Applicant: RICOH COMPANY, LTD. ,  KOMOTO, Shotaro ,  OHMURA, Keiji ,  TAJIMA, Akito

Inventor： KOMOTO, Shotaro ,  OHMURA, Keiji ,  TAJIMA, Akito

IPC: G06T7/00 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/20092 ,  G06T2207/30136 ,  G06T7/001

Abstract: An image processing apparatus includes: a determining unit that determines, based on comparison and collation between a target image including an object to be inspected and a reference image registered in advance, whether the object is normal; an image acquiring unit that repeatedly acquires the target image; a retaining unit that retains an initial reference image; a collation value calculating unit that calculates a collation value indicating a degree of matching between the target image and the initial reference image; an extracting unit that extracts, as a candidate for the reference image, the target image having the calculated collation value not less than a first threshold and not greater than a second threshold; a presentation device that presents the candidate; an operation device that allows selection as to whether to register the candidate as the reference image; and a registering unit that registers the selected candidate as the reference image.

公开(公告)号：WO2021108233A2

公开(公告)日：2021-06-03

申请号：PCT/US2020/061411

申请日：2020-11-20

Applicant: BWXT ADVANCED TECHNOLOGIES LLC

Inventor： KITCHEN, Ryan Scott ,  FISHER, Benjamin D.

IPC: B05D7/22 ,  B05C13/02 ,  B29C64/129 ,  B29C64/268 ,  B29C64/393 ,  B33Y10/00 ,  B33Y50/02 ,  G06T2207/30164 ,  G06T7/0008 ,  G06T7/001 ,  G06T7/62

Abstract: Methods to in-situ monitor production of additive manufacturing products collects images from the deposition process on a layer-by-layer basis, including a void image of the pattern left in a slurry layer after deposition of a layer and a displacement image formed by immersing the just-deposited layer in a renewed slurry layer. Image properties of the void image and displacement image are corrected and then compared to a binary expected image from a computer generated model to identify defects in the just-deposited layer on a layer-by-layer basis. Additional methods use the output from the comparison to form a 3D model corresponding to at least a portion of the additive manufacturing product. Components to control the additive manufacturing operation based on digital model data and to in-situ monitor successive layers for manufacturing defects can be embodied in a computer system or computer-aided machine, such as a computer controlled additive manufacturing machine.

公开(公告)号：WO2022241104A2

公开(公告)日：2022-11-17

申请号：PCT/US2022/028971

申请日：2022-05-12

Applicant: ADTRAN, INC.

Inventor： BRANNEN, Donald Larry ,  MANLEY, James Todd

IPC: H04B17/00 ,  G06N3/02 ,  H04B17/11 ,  H04B17/21 ,  H04B17/23 ,  G06T2207/10004 ,  G06T2207/30164 ,  G06T7/001 ,  G09B5/06 ,  H04W16/22 ,  H04W24/02

Abstract: The present disclosure generally relates to systems and methods for ensuring proper installation of telecommunication equipment. A system in some embodiments has a mobile device equipped with an image sensor that is used to acquire one or more images of a telecommunication equipment component that has been installed. The mobile device may then evaluate at least one such image to determine whether the component has been correctly installed. In addition, the evaluation performed by the mobile device may also be used to ensure that a captured image of the component meets certain predefined criteria for helping the user to capture a quality image of the component for the purpose of proving that it has been correctly installed. Thus, it is more likely that the image will be later useful for establishing that the component has been correctly installed, thereby possibly preventing the need for a truck roll.

公开(公告)号：WO2021244816A1

公开(公告)日：2021-12-09

申请号：PCT/EP2021/061869

申请日：2021-05-05

Applicant: SEW-EURODRIVE GMBH & CO. KG

Inventor： WU, Zili

IPC: G06T7/00 ,  G06T2207/10028 ,  G06T2207/30136 ,  G06T2207/30164 ,  G06T7/001

Abstract: Verfahren und System zur Herstellung eines Teils aus einem Gussteil, wobei in einem ersten Verfahrensschritt ein 3D-Konstruktionsmodell für ein Teil, insbesondere Getriebegehäuseteil, erstellt wird und in einem Rechner abgespeichert wird, wobei in einem zweiten Verfahrensschritt das Gussteil durch Gießen hergestellt wird, dadurch gekennzeichnet, dass in einem dritten Verfahrensschritt das Gussteil mit einem 3D-Scanner gemessen wird und aus den dabei erfassten Messdaten ein 3D-Modell des Gussteils bestimmt wird, in einem vierten Verfahrensschritt Abweichungen zwischen dem 3D-Modell und dem 3D-Konstruktionsmodell bestimmt und dargestellt oder angezeigt werden, insbesondere auf einem Bildschirm oder durch Ausdrucken insbesondere auf einem Papier dargestellt oder angezeigt werden, insbesondere zweidimensional.

公开(公告)号：WO2020148085A1

公开(公告)日：2020-07-23

申请号：PCT/EP2020/000009

申请日：2020-01-14

Applicant: LUFTHANSA TECHNIK AG

Inventor： PETERS, Jan Oke ,  THIES, Michael ,  RASCHE, Sven ,  DOMASCHKE, Tomas ,  SCHÜPPSTUHL, Thorsten ,  NEDDERMEYER, Werner ,  BAHR, Sönke

IPC: G01N21/954 ,  G06T7/00 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/10068 ,  G06T2207/30164 ,  G06T7/001

Abstract: Die Erfindung betrifft ein Verfahren (100) sowie eine Vorrichtung zur Boroskopinspektion von Bauteilen, insbesondere von Turbinen- und/oder Kompressorschaufeln (87') in einer Gasturbine, wie bspw. einem Flugzeugtriebwerk (80). Das Verfahren (100) nutzt ein Stereoboroskop (10) zur Aufnahme des Bauteils und umfasst die Schritte: Erzeugen zweier stereoskopischer Teilbilder durch das Stereoboroskop (10) (Schritt 102); Berechnung von 3D-Triangulationsdaten aus den stereoskopischen Teilbildern (Schritt 105); Registrieren der 3D-Triangulationdaten auf ein 3D-CAD-Referenzmodell (30) des vom Stereoboroskop (10) erfassten Bauteils unter Ermittlung eines Projektionspunktes (31) (Schritte 106 und 107); Projektion von aus den stereoskopischen Teilbildern ermittelten 2D-Bilddaten auf das 3D-CAD-Referenzmodell (30) vom ermittelten Projektionspunkt (Schritt 108); und Ermitteln von Schäden durch Bildanalyse der projizierten 2D-Bilddaten und durch Feststellung von Abweichungen der registrierten 3D-Triagulationsdaten gegenüber dem 3D-CAD-Referenzmodell (30) (Schritte 112 und 113). Die Vorrichtung ist zur Durchführung des Verfahrens ausgebildet.

公开(公告)号：WO2022269470A1

公开(公告)日：2022-12-29

申请号：PCT/IB2022/055722

申请日：2022-06-20

Applicant: M31 ITALIA S.R.L.

Inventor： DEPPIERI, Francesco ,  FREZZA, Ruggero

IPC: G05B17/02 ,  G05B19/418 ,  G06F30/20 ,  G06T7/00 ,  G05B19/41875 ,  G06T7/001

Abstract: The present invention concerns a modular apparatus and a method for the inspection of industrial products. The apparatus and method operate according to the "Model Based Design" paradigm and are characterized in that the apparatus is associated with a digital clone of the real acquisition system. The digital clone reproduces in a virtual environment the features of said system and of the product affected by anomalies to be inspected. By generating virtual images of the product through simulations on said digital clone and processing virtual images through a vision system including a novel data fusion module, the invention makes possible to define the optimal architecture and parameterization of the real acquisition system that maximize the likelihood of identifying anomalies in products even in conditions that are difficult or expensive to replicate in the real world. The invention reduces time in designing and set-up as well as costs of an inspection apparatus. Furthermore it enables to reconfigure the apparatus to products and/or anomalies other than those for which it was initially designed.

公开(公告)号：WO2022028937A1

公开(公告)日：2022-02-10

申请号：PCT/EP2021/070853

申请日：2021-07-26

Applicant: COMPAGNIE GENERALE DES ETABLISSEMENTS MICHELIN

Inventor： CHATEAU, Thierry ,  PHUTANE, Priyanka ,  KONATE, Mohamed-Abbas

IPC: G06T7/00 ,  G06N3/0454 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T7/001

Abstract: The invention is directed to a computer-implemented process for training a model for automatically recognizing positions in tire product profiles, whereby an error term is calculated with respect to a label assigned in a reference of the interfaces searched in captured images of the tire product profiles that will serve as inputs to the neural network to be trained. The invention also relates to a system (100) for automatically recognizing interface variations captured in images of samples according to the disclosed process.

公开(公告)号：WO2022005916A1

公开(公告)日：2022-01-06

申请号：PCT/US2021/039247

申请日：2021-06-25

Applicant: APPLIED MATERIALS, INC.

Inventor： DHANDAPANI, Sivakumar ,  ALAHGHOLIPOUROMRANI, Arash ,  BENVEGNU, Dominic J. ,  QIAN, Jun ,  SHRESTHA, Kiran Lall

IPC: G01B11/06 ,  H01L21/66 ,  G06T7/00 ,  G06T7/62 ,  G06T7/90 ,  G06N3/04 ,  G06N3/08 ,  B24B37/013 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30148 ,  G06T7/001 ,  G06T7/60

Abstract: A neural network is trained for use in a substrate thickness measurement system by obtaining ground truth thickness measurements of a top layer of a calibration substrate at a plurality of locations, each location at a defined position for a die being fabricated on the substrate. A plurality of color images of the calibration substrate are obtained, each color image corresponding to a region for a die being fabricated on the substrate. A neural network is trained to convert color images of die regions from an in-line substrate imager to thickness measurements for the top layer in the die region. The training is performed using training data that includes the plurality of color images and ground truth thickness measurements with each respective color image paired with a ground truth thickness measurement for the die region associated with the respective color image.

公开(公告)号：WO2021252246A1

公开(公告)日：2021-12-16

申请号：PCT/US2021/035554

申请日：2021-06-02

Applicant: KLA CORPORATION

Inventor： BRAUER, Bjorn ,  JIN, Huan ,  LI, Xiaochun

IPC: H01L21/66 ,  G06T7/30 ,  G06T7/90 ,  G06K9/62 ,  G01N21/95 ,  G06T2207/10152 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30148 ,  G06T7/0004 ,  G06T7/001 ,  G06T7/32 ,  G06T7/344

Abstract: Methods and systems for determining one or more alignment parameters for use in a process performed on a specimen are provided. One method includes determining measures of similarity between images generated by an imaging system for corresponding locations in each of two or more pairs of dies on a specimen and performing cluster analysis based on the determined measures of similarity to identify the images that are most similar to each other and to assign different subsets of the images that are most similar to each other to different die clusters, respectively. The method also includes separately determining one or more alignment parameters for two or more of the different die clusters. The one or more alignment parameters are used for aligning images generated by the imaging system for the specimen or another specimen to a common reference.