公开(公告)号：US11748873B2

公开(公告)日：2023-09-05

申请号：US17250263

申请日：2020-08-26

Applicant: GOERTEK INC.

Inventor： Jie Liu ,  Li Ma ,  Liang Zhang

IPC: G06T7/00 ,  G06T7/136 ,  G06T7/11 ,  G06T7/70 ,  G01N21/88 ,  G06N3/08 ,  G06F18/214 ,  G06F18/2431 ,  G06F18/2413 ,  G06V10/42 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06T7/001 ,  G01N21/8851 ,  G06F18/214 ,  G06F18/2431 ,  G06F18/24133 ,  G06N3/08 ,  G06T7/0004 ,  G06T7/11 ,  G06T7/136 ,  G06T7/70 ,  G06V10/431 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G01N2021/8854 ,  G01N2021/8887 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A product defect detection method, device and system are disclosed. The product defect detection method comprises: constructing a defect detection framework including a classification network, a locating detection network and a judgment network; training the classification network by using a sample image of a product containing different defect types to obtain a classification network capable of classifying the defect types existing in the sample image; training the locating detection network by using a sample image of a product containing different defect types to obtain a locating detection network capable of locating a position of each type of defect in the sample image; inputting an acquired product image into the defect detection framework, inputting a classification result and a detection result obtained into the judgment network to judge whether the product has a defect, and detecting a defect type and a defect position when the product has a defect.

公开(公告)号：US20230274537A1

公开(公告)日：2023-08-31

申请号：US18094933

申请日：2023-01-09

Applicant: Google LLC

Inventor： Dmitry Lagun ,  Junfeng He ,  Pingmei Xu

IPC: G06V10/82 ,  G06T7/73 ,  G06T7/80 ,  G06F3/01 ,  G06V40/19 ,  G06F18/211 ,  G06F18/2413 ,  G06V10/764

CPC classification number: G06V10/82 ,  G06F3/013 ,  G06F18/211 ,  G06F18/24133 ,  G06T7/74 ,  G06T7/80 ,  G06V10/764 ,  G06V40/19 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201 ,  G06V40/161

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for characterizing a gaze position of a user in a query image. One of the methods includes obtaining a query image of a user captured by a camera of a mobile device; obtaining device characteristics data specifying (ii) characteristics of the mobile device, (ii) characteristics of the camera of the mobile device, or (iii) both; and processing a neural network input comprising (i) one or more images derived from the query image and (ii) the device characteristics data using a gaze prediction neural network, wherein the gaze prediction neural network is configured to, at run time and after the gaze prediction neural network has been trained, process the neural network input to generate a neural network output that characterizes a gaze position of the user in the query image.

公开(公告)号：US11740321B2

公开(公告)日：2023-08-29

申请号：US15926557

申请日：2018-03-20

Applicant: Apple Inc.

Inventor： Oleg Naroditsky ,  Kuen-Han Lin ,  Dimitrios Kottas

IPC: G01S5/16 ,  G06T7/246 ,  G01S19/47 ,  G06F18/21 ,  G06F18/2413 ,  G06N3/042 ,  G06V10/764 ,  G01S19/52

CPC classification number: G01S5/16 ,  G01S19/47 ,  G06F18/217 ,  G06F18/24133 ,  G06N3/042 ,  G06T7/251 ,  G06V10/764 ,  G01S19/52 ,  G06F2218/12 ,  G06V2201/03

Abstract: Systems, methods, and computer readable media to track and estimate the accuracy of a visual inertial odometry (VIO) system. Various embodiments are able to receive one or more VIO feature measurements associated with a set of image frames from a VIO system and generate a plurality of feature models to estimate health values for the VIO system. The various embodiments determine a plurality of feature health values with the feature models based on the VIO feature measurements and compare the feature health values with ground truth health scores associated with the set of image frames to determine one or more errors. The feature model parameters are updated based on the comparison with the feature health values with ground truth health scores.

公开(公告)号：US11672611B2

公开(公告)日：2023-06-13

申请号：US17346911

申请日：2021-06-14

Applicant: Medtronic Navigation, Inc.

Inventor： Joseph Moctezuma ,  Craig Drager ,  Joseph Thomas Cilke ,  Victor D. Snyder ,  Wei-Shyang Yang ,  Justin Kemp ,  Andrew Wald ,  Jerald Lamont Redmond ,  Shai Ronen ,  Nikhil Mahendra

IPC: A61B34/20 ,  A61B90/98 ,  A61B90/96 ,  A61B34/00 ,  A61B90/00 ,  A61B90/92 ,  A61B34/10 ,  A61B5/06 ,  A61B90/94 ,  G06V10/44 ,  G06V20/00 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/82

CPC classification number: A61B34/20 ,  A61B5/06 ,  A61B34/25 ,  A61B90/361 ,  A61B90/37 ,  A61B90/92 ,  A61B90/94 ,  A61B90/96 ,  A61B90/98 ,  G06F18/24133 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V20/00 ,  A61B2034/107 ,  A61B2034/2051 ,  A61B2034/2055 ,  A61B2034/2065 ,  A61B2034/254 ,  A61B2034/256 ,  A61B2090/365 ,  A61B2090/374 ,  A61B2090/376 ,  A61B2090/3762 ,  G06V2201/034

Abstract: A system and apparatus is disclosed to automatically determine the identification and selected information relating to instruments. The identification information may be read or determined by various reader systems and then transferred for various purposes. The identification information may be stored on the instrument with a storage system or printing and/or recalled from a memory once the identification is made.

公开(公告)号：US20240346815A1

公开(公告)日：2024-10-17

申请号：US18638289

申请日：2024-04-17

Applicant: TuSimple, Inc.

Inventor： Panqu WANG ,  Pengfei CHEN

IPC: G06V10/82 ,  G06F18/2413 ,  G06T7/194 ,  G06V10/20 ,  G06V10/44 ,  G06V10/764 ,  G06V20/56 ,  G06V20/58

CPC classification number: G06V10/82 ,  G06F18/24133 ,  G06T7/194 ,  G06V10/255 ,  G06V10/454 ,  G06V10/764 ,  G06V20/56 ,  G06V20/58 ,  G06T2207/20081 ,  G06T2207/30252

Abstract: A system and method for vehicle wheel detection is disclosed. A particular embodiment can be configured to: receive training image data from a training image data collection system; obtain ground truth data corresponding to the training image data; perform a training phase to train one or more classifiers for processing images of the training image data to detect vehicle wheel objects in the images of the training image data; receive operational image data from an image data collection system associated with an autonomous vehicle; and perform an operational phase including applying the trained one or more classifiers to extract vehicle wheel objects from the operational image data and produce vehicle wheel object data.

公开(公告)号：US20240289930A1

公开(公告)日：2024-08-29

申请号：US18634115

申请日：2024-04-12

Applicant: Intel Corporation

Inventor： Wenlong Yang ,  Tomer Rider ,  Xiaopei Zhang

IPC: G06T5/77 ,  G05B13/02 ,  G05D1/00 ,  G06F18/214 ,  G06F18/24 ,  G06F18/2413 ,  G06F18/25 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/084 ,  G06N5/04 ,  G06T7/00 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V10/98

CPC classification number: G06T5/77 ,  G05B13/0265 ,  G06F18/214 ,  G06F18/24 ,  G06F18/24133 ,  G06F18/251 ,  G06N3/045 ,  G06N3/08 ,  G06N3/084 ,  G06N5/04 ,  G06T7/0002 ,  G06V10/764 ,  G06V10/803 ,  G06V10/82 ,  G06V10/993 ,  G05D1/00 ,  G06N3/044 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30168

Abstract: A mechanism is described for facilitating deep learning-based real-time detection and correction of compromised sensors in autonomous machines according to one embodiment. An apparatus of embodiments, as described herein, includes detection and capturing logic to facilitate one or more sensors to capture one or more images of a scene, where an image of the one or more images is determined to be unclear, where the one or more sensors include one or more cameras. The apparatus further comprises classification and prediction logic to facilitate a deep learning model to identify, in real-time, a sensor associated with the image.

公开(公告)号：US20240257500A1

公开(公告)日：2024-08-01

申请号：US18605307

申请日：2024-03-14

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Lawrence R. Frank ,  Vitaly L. Galinsky

IPC: G06V10/77 ,  A61B5/00 ,  A61B5/055 ,  G01R33/48 ,  G01R33/56 ,  G01R33/563 ,  G06F18/2135 ,  G06F18/2413 ,  G06T7/00

CPC classification number: G06V10/7715 ,  A61B5/00 ,  A61B5/055 ,  G01R33/5608 ,  G06F18/2135 ,  G06F18/24133 ,  G06T7/0012 ,  G01R33/4806 ,  G01R33/56341 ,  G06F2218/12 ,  G06T7/0016 ,  G06T2207/10044 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/20048 ,  G06T2207/30016

Abstract: Analysis of complex spatio-temporal data within a dynamic system that includes spatial positions and fields, at least a portion of which are interacting, includes determining values of mean field at every spatial position, determining spatio-temporal eigenmodes in spatial-frequency space assuming interacting fields, and determining spatial and temporal interactions between the eigenmodes. The resulting display indicates space/time localization patterns that are indicative of connectivity within the dynamic system.

公开(公告)号：US12026219B2

公开(公告)日：2024-07-02

申请号：US16828216

申请日：2020-03-24

Applicant: TripleBlind, Inc.

Inventor： Greg Storm ,  Riddhiman Das ,  Babak Poorebrahim Gilkalaye

IPC: H04L9/40 ,  G06F17/16 ,  G06N3/045 ,  G06N3/048 ,  G06Q20/12 ,  G06Q30/0601 ,  H04L9/06 ,  G06F18/2113 ,  G06F18/24 ,  G06F18/2413 ,  G06N3/04 ,  G06N3/082 ,  G06N3/084 ,  G06Q20/40 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  H04L9/00 ,  H04L9/08

CPC classification number: G06F17/16 ,  G06N3/045 ,  G06N3/048 ,  G06Q20/1235 ,  G06Q30/0623 ,  H04L9/0625 ,  H04L63/0428 ,  G06F18/2113 ,  G06F18/24 ,  G06F18/24133 ,  G06N3/04 ,  G06N3/082 ,  G06N3/084 ,  G06Q20/401 ,  G06Q2220/00 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  H04L9/008 ,  H04L9/085 ,  H04L2209/46

Abstract: The disclosed concepts achieve privacy for data operated on by an algorithm in an efficient manner A method includes receiving a first algorithm subset, receiving a second algorithm subset, generating two shares of a first mathematical set based on the first algorithm subset and transmitting the two shares of the first mathematical set from a first entity to a second entity. The method can include generating two shares of a second mathematical set based on the second algorithm subset, transmitting the two shares of the second mathematical set from the second entity to the first entity, receiving first split data subset of a full data set and receiving a second split data subset of the full data set. The system, based on these subsets of data, generates a first output subset and a second output subset which are combined for the final output.

公开(公告)号：US12020160B2

公开(公告)日：2024-06-25

申请号：US15875575

申请日：2018-01-19

Applicant: International Business Machines Corporation

Inventor： Takeshi Inagaki

IPC: G06N3/082 ,  G06F18/214 ,  G06F18/2413 ,  G06N3/045 ,  G06N3/088 ,  G06V10/82

CPC classification number: G06N3/082 ,  G06F18/214 ,  G06F18/24133 ,  G06N3/045 ,  G06N3/088 ,  G06V10/82

Abstract: A method, computer program product and system for generating a neural network. Initial neural networks are prepared, each of which includes an input layer containing one or more input nodes, a middle layer containing one or more middle nodes, and an output layer containing one or more output nodes. A new neural network is generated that includes a new middle layer containing one or more middle nodes based on the middle nodes of the middle layers of the initial neural networks.

公开(公告)号：US12019704B2

公开(公告)日：2024-06-25

申请号：US18168001

申请日：2023-02-13

Applicant: TripleBlind, Inc.

Inventor： Greg Storm ,  Riddhiman Das ,  Babak Poorebrahim Gilkalaye

IPC: G06F17/16 ,  G06F18/2113 ,  G06F18/24 ,  G06F18/2413 ,  G06N3/04 ,  G06N3/045 ,  G06N3/048 ,  G06N3/082 ,  G06N3/084 ,  G06Q20/12 ,  G06Q20/40 ,  G06Q30/0601 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  H04L9/00 ,  H04L9/06 ,  H04L9/08 ,  H04L9/40

CPC classification number: G06F17/16 ,  G06N3/045 ,  G06N3/048 ,  G06Q20/1235 ,  G06Q30/0623 ,  H04L9/0625 ,  H04L63/0428 ,  G06F18/2113 ,  G06F18/24 ,  G06F18/24133 ,  G06N3/04 ,  G06N3/082 ,  G06N3/084 ,  G06Q20/401 ,  G06Q2220/00 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  H04L9/008 ,  H04L9/085 ,  H04L2209/46

Abstract: Systems, methods, and computer-readable media for achieving privacy for both data and an algorithm that operates on the data. A system can involve receiving an algorithm from an algorithm provider and receiving data from a data provider, dividing the algorithm into a first algorithm subset and a second algorithm subset and dividing the data into a first data subset and a second data subset, sending the first algorithm subset and the first data subset to the algorithm provider and sending the second algorithm subset and the second data subset to the data provider, receiving a first partial result from the algorithm provider based on the first algorithm subset and first data subset and receiving a second partial result from the data provider based on the second algorithm subset and the second data subset, and determining a combined result based on the first partial result and the second partial result.