公开(公告)号：US20240357241A1

公开(公告)日：2024-10-24

申请号：US18683971

申请日：2021-10-22

Applicant: FANUC CORPORATION

Inventor： Yuusuke OOTA

IPC: H04N23/72 ,  G06V10/147 ,  H04N23/71 ,  H04N23/73 ,  H04N23/76

CPC classification number: H04N23/72 ,  H04N23/71 ,  H04N23/73 ,  H04N23/76 ,  G06V10/147 ,  G06V2201/06

Abstract: One form of an imaging control device capable of improving recognition accuracy while ensuring processing speed comprises: an imaging processing unit that uses a camera to acquire an imaged image at an exposure time and gain that were set; an image processing unit that performs image processing on the imaged image and acquires information; a storage unit that stores set values for the exposure time and the gain, a processing time target value for the image processing in the image processing unit, and image processing results; and a setting adjustment unit that adjusts the set values for the exposure time and the gain such that the processing time in the image processing unit becomes at most the target value.

公开(公告)号：US12125264B1

公开(公告)日：2024-10-22

申请号：US18784389

申请日：2024-07-25

Applicant: INTER X Co., Ltd.

Inventor： Jung Ywn Park ,  Ha Il Jung ,  Jeong Hyun Park ,  Qing Tang

IPC: G06V10/77 ,  G06T7/00 ,  G06V10/56 ,  G06V10/75 ,  G06V10/20

CPC classification number: G06V10/7715 ,  G06T7/001 ,  G06V10/56 ,  G06V10/751 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/30108 ,  G06T2207/30168 ,  G06V10/20 ,  G06V2201/06

Abstract: Embodiments relate to a deep learning/AI-based product surface quality inspection system which is accurate and reliable in product quality inspection which is a core task in an injection process among various manufacturing fields. The system can provide, to a user, better performance than non-defective/defective manufactured product classification methodology which is an existing commonly used method through a method and a system considering characteristics of a factory environment and an actual product production process for all pipelines of product quality inspection by using only a non-defective manufactured product image unlike most injection process surface inspection AIs developed to date.

公开(公告)号：US20240308073A1

公开(公告)日：2024-09-19

申请号：US18603897

申请日：2024-03-13

Applicant: NVIDIA Corporation

Inventor： Riccardo Mariani ,  Sudesh Kamath ,  Bhanu Pisupati ,  Mathias Blake ,  Gary Hicok ,  Jacob Liberman ,  Tarun Rathor

IPC: B25J9/16 ,  G06V20/52

CPC classification number: B25J9/1674 ,  B25J9/1697 ,  G06V20/52 ,  G06V2201/06

Abstract: In various examples, providing proactive safety measures for robotic systems and equipment is described herein. For instance, systems and methods may monitor equipment (e.g., a machine) in order to proactively detect potential safety events that may occur with regard to the equipment and/or activate one or more proactive safety measures in order to mitigate and/or eliminate the safety events before occurring. For example, sensors that are external to the equipment may generate sensor data representing the environment at least partially surrounding the equipment. The sensor data may then be processed to determine when a potential safety event is occurring with regard to the equipment. One or more safety measures may then be activated based at least on detecting the potential safety event, such as activating a warning and/or causing an internal reactive safety measure of the equipment to activate.

公开(公告)号：US12093304B2

公开(公告)日：2024-09-17

申请号：US17279803

申请日：2019-08-19

Applicant: AMGEN INC.

Inventor： Killian Ryan

IPC: G06F16/50 ,  G06F16/51 ,  G06F18/214 ,  G06F18/28 ,  G06T1/00 ,  G06T7/00 ,  G06V10/772 ,  H04N1/00 ,  H04N5/00

CPC classification number: G06F16/50 ,  G06F16/51 ,  G06F18/2148 ,  G06F18/28 ,  G06T1/0007 ,  G06T7/0004 ,  G06V10/772 ,  H04N1/00 ,  H04N1/0009 ,  H04N5/00 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V2201/06

Abstract: A method for sampling images includes receiving a first image set generated by automated imaging equipment during a first inspection period, and storing in a memory an image library that initially consists of the first image set. A plurality of new image sets is then sequentially received (302) during respective inspection periods. While the new image sets are received (302), the image library stored in the memory is updated. Updating the image library includes, for each new image set, adding to the image library a certain number of images distributed among the new image set and removing from the image library the same number of images distributed among a current instance of the image library (308). The number of overwritten images in the image library decreases from one inspection period to the next.

公开(公告)号：US12092526B2

公开(公告)日：2024-09-17

申请号：US17465889

申请日：2021-09-03

Applicant: ABB Schweiz AG

Inventor： Ralf Gitzel ,  Subanatarajan Subbiah ,  Benedikt Schmidt

IPC: G01J5/80 ,  G01J5/00 ,  G06N3/08 ,  G06T5/70 ,  G06V10/143 ,  G06V10/30 ,  G06V10/764 ,  G06V10/82 ,  H02B13/025 ,  G06N3/045 ,  H02B3/00

CPC classification number: G01J5/80 ,  G01J5/0066 ,  G01J5/0096 ,  G06N3/08 ,  G06T5/70 ,  G06V10/143 ,  G06V10/30 ,  G06V10/764 ,  G06V10/82 ,  H02B13/025 ,  G01J2005/0077 ,  G06N3/045 ,  G06T2207/10048 ,  G06V2201/06 ,  H02B3/00

Abstract: An apparatus for monitoring a switchgear includes: an input unit; a processing unit; and an output unit. The input unit is provides the processing unit with a monitor infra-red image of the switchgear. The processing unit implements a machine learning classifier algorithm to analyse the monitor infra-red image and determine if there is one or more anomalous hot spots in the switchgear. The machine learning classifier algorithm has been trained based on a plurality of different training infra-red images. The plurality of training infra-red images include a plurality of modified infra-red images generated from a corresponding plurality of infra-red images, each of the modified infra-red images having been modified to remove an effect of obscuration in the image. The output unit outputs information relating to the one or more anomalous hot spots.

公开(公告)号：US12086214B2

公开(公告)日：2024-09-10

申请号：US17344203

申请日：2021-06-10

Applicant: Robert Bosch GmbH

Inventor： Benedikt Sebastian Staffler ,  Jan Hendrik Metzen

IPC: G06F18/20 ,  G06F18/21 ,  G06N5/04 ,  G06N20/00 ,  G06T7/11 ,  G06V20/58

CPC classification number: G06F18/285 ,  G06F18/217 ,  G06N5/04 ,  G06N20/00 ,  G06T7/11 ,  G06T2207/20072 ,  G06T2207/20081 ,  G06V20/58 ,  G06V2201/06

Abstract: A method for creating a machine learning system which is designed for segmentation and object detection in images. The method includes: providing a directed graph; selecting a path through the graph, at least one additional node being selected from this subset, a path through the graph from the input node along the edges via the additional node up to the output node being selected; creating a machine learning system as a function of the selected path; and training the machine learning system created.

公开(公告)号：US12056867B2

公开(公告)日：2024-08-06

申请号：US17465810

申请日：2021-09-02

Applicant: KLA Corporation

Inventor： Bjorn Brauer ,  Sangbong Park ,  Hucheng Lee

IPC: G06T7/00 ,  G06T7/33 ,  G06T7/80 ,  G06V10/24 ,  G06V10/75

CPC classification number: G06T7/001 ,  G06T7/337 ,  G06T7/80 ,  G06V10/24 ,  G06V10/751 ,  G06T2207/10148 ,  G06T2207/30148 ,  G06V2201/06

Abstract: Wafer-to-wafer and within-wafer image contrast variations can be identified and mitigated by extracting an image frame during recipe setup and then during runtime at the same location. Image contrast is determined for the two image frames. A ratio of the contrast for the two image frames can be used to determine contrast variations and focus variation.

公开(公告)号：US12056647B2

公开(公告)日：2024-08-06

申请号：US17963985

申请日：2022-10-11

Applicant: Team Conveyer Intellectual Properties, LLC

Inventor： John G. Gorman

IPC: G06F7/00 ,  B65G1/137 ,  B65G11/02 ,  B65G43/00 ,  G06K7/10 ,  G06Q10/04 ,  G06Q10/0631 ,  G06Q10/0639 ,  G06Q10/087 ,  G06V10/22

CPC classification number: G06Q10/0639 ,  B65G1/1371 ,  B65G1/1378 ,  B65G11/023 ,  B65G43/00 ,  G06K7/10415 ,  G06Q10/04 ,  G06Q10/06315 ,  G06Q10/087 ,  G06V10/22 ,  B65G2203/0216 ,  G06V2201/06

Abstract: Coordinated conveyors in an automated system. In an embodiment, the system comprises transport conveyor(s) and storage conveyors, wherein each storage conveyor comprises a plurality of segments configured to hold at least one item, and a portion that is aligned with a portion of a transport conveyor, such that items are moveable from the storage conveyor to the transport conveyor. Software module(s), executed by a processor, receive an instruction to collect item(s) at a single destination location, and, for each of the item(s), identify a segment on a storage conveyor on which the item is held, control that storage conveyor to align the segment with the transport conveyor, move the item from the segment onto the transport conveyor, control the transport conveyor to align the item with the destination location, and move the item from the transport conveyor to the destination location.

公开(公告)号：US20240257505A1

公开(公告)日：2024-08-01

申请号：US18161305

申请日：2023-01-30

Applicant: FANUC CORPORATION

Inventor： Te Tang ,  Tetsuaki Kato

IPC: G06V10/776 ,  B25J9/16 ,  G06V10/26 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06V10/776 ,  B25J9/1697 ,  G06V10/26 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/7747 ,  G06V10/82 ,  G06V2201/06

Abstract: A system and method for adapting a feature extraction neural network to only identify environment independent features in an image. The method includes modifying weights within a dataset classifier neural network to improve the accuracy of the ability of the dataset classifier neural network to identify that training features images are from training images and test features images are from test images. The method also includes modifying the weights within a feature extraction neural network to reduce the accuracy of the ability of the dataset classifier neural network to identify that the training features images are from the training images and the test features images are from the test images.

公开(公告)号：US20240246240A1

公开(公告)日：2024-07-25

申请号：US18557125

申请日：2022-05-12

Applicant: NANYANG TECHNOLOGICAL UNIVERSITY

Inventor： Yee Seng TEOH ,  Yadan ZENG ,  Boon Heng Elvin TOH ,  Choon Yue WONG ,  I-Ming CHEN ,  Guoniu ZHU

IPC: B25J9/16 ,  B25J11/00 ,  B65B5/12 ,  B65B57/14 ,  B65G47/90 ,  G06T7/50 ,  G06T7/70 ,  G06V10/764 ,  G06V10/82 ,  G06V20/68

CPC classification number: B25J9/1697 ,  B25J11/0045 ,  B65B5/12 ,  B65B57/14 ,  B65G47/90 ,  G06T7/50 ,  G06T7/70 ,  G06V10/764 ,  G06V10/82 ,  G06V20/68 ,  G06T2207/30128 ,  G06V2201/06

Abstract: Methods, systems and computer readable media are provided for automatic kitting of items. The system for automatic kitting of items includes a robotic device, a first imaging device, a computing device and a controller. The robotic device includes an arm with a robotic gripper at one end. The first imaging device is focused on a device conveying kitted items. The computing device is coupled to the first imaging device and is configured to process image data from the first imaging device. The computing device includes item arrangement verification software configured to determine whether each item desired to be in the kitted items is present or absent in the kitted items in response to the processed image data from the first imaging device and generates data based on whether an item desired to be in the kitted items is absent from the kitted items. The controller is coupled to the computing device to receive the data from the computer representing whether an item desired to be in the kitted items is absent from the kitted items. The controller is also coupled to the robotic device for providing instructions to the robotic device to control movement of the arm and the robotic gripper, wherein at least some of the instructions provided to the robotic device are generated in response to the item desired to be in the kitted items being absent from the kitted items.