公开(公告)号：US12094227B2

公开(公告)日：2024-09-17

申请号：US17614642

申请日：2019-06-12

申请人： OMRON Corporation

发明人： Yoshinori Konishi

IPC分类号： G06V20/64 ,  G06T11/00

CPC分类号： G06V20/647 ,  G06T11/00

摘要： An object recognition apparatus includes a three-dimensional data obtainer that obtains three-dimensional data including a plurality of points each having three-dimensional information, a parallel projection converter that generates a two-dimensional image by parallel projection of the plurality of points included in the three-dimensional data onto a projection plane, and a recognition processor that detects a target object in the two-dimensional image using template matching.

公开(公告)号：US12073609B2

公开(公告)日：2024-08-27

申请号：US18302780

申请日：2023-04-18

申请人： Matterport, Inc.

发明人： Gunnar Hovden ,  Mykhaylo Kurinnyy

IPC分类号： G06V10/778 ,  G06F18/21 ,  G06T15/04 ,  G06T15/20 ,  G06T17/00 ,  G06T19/00 ,  G06V20/00 ,  G06V20/10 ,  G06V20/64

CPC分类号： G06V10/7796 ,  G06F18/2193 ,  G06T15/04 ,  G06T15/205 ,  G06T17/00 ,  G06T19/003 ,  G06V20/10 ,  G06V20/35 ,  G06T2210/04 ,  G06V20/647

摘要： Techniques are provided for increasing the accuracy of automated classifications produced by a machine learning engine. Specifically, the classification produced by a machine learning engine for one photo-realistic image is adjusted based on the classifications produced by the machine learning engine for other photo-realistic images that correspond to the same portion of a 3D model that has been generated based on the photo-realistic images. Techniques are also provided for using the classifications of the photo-realistic images that were used to create a 3D model to automatically classify portions of the 3D model. The classifications assigned to the various portions of the 3D model in this manner may also be used as a factor for automatically segmenting the 3D model.

公开(公告)号：US20240278912A1

公开(公告)日：2024-08-22

申请号：US18435299

申请日：2024-02-07

申请人： Skydio, Inc.

发明人： Peter Henry ,  Jack Zhu ,  Brian Richman ,  Harrison Zheng ,  Hayk Martirosyan ,  Matthew Donahoe ,  Abraham Galton Bachrach ,  Adam Bry

IPC分类号： B64C39/02 ,  B64D47/08 ,  B64U10/13 ,  B64U101/30 ,  G01S13/89 ,  G01S17/89 ,  G05D1/223 ,  G05D1/224 ,  G05D1/606 ,  G06F3/04817 ,  G06F3/04845 ,  G06F3/04847 ,  G06T17/05 ,  G06T17/10 ,  G06T19/00 ,  G06V20/10 ,  G06V20/13 ,  G06V20/17 ,  G06V20/64 ,  G08G5/00 ,  G08G5/04 ,  H04N5/272 ,  H04N13/204

CPC分类号： B64C39/024 ,  B64D47/08 ,  G01S13/89 ,  G01S17/89 ,  G05D1/223 ,  G05D1/224 ,  G05D1/606 ,  G06F3/04817 ,  G06F3/04845 ,  G06F3/04847 ,  G06T17/05 ,  G06T17/10 ,  G06T19/006 ,  G06V20/13 ,  G06V20/17 ,  G06V20/176 ,  G06V20/647 ,  G08G5/003 ,  G08G5/04 ,  H04N5/272 ,  B64U10/13 ,  B64U2101/30 ,  B64U2201/00 ,  B64U2201/20 ,  H04N13/204

摘要： Described herein are systems for roof scan using an unmanned aerial vehicle. For example, some methods include capturing, using an unmanned aerial vehicle, an overview image of a roof of a building from above the roof; presenting a suggested bounding polygon overlaid on the overview image to a user; determining a bounding polygon based on the suggested bounding polygon and user edits; based on the bounding polygon, determining a flight path including a sequence of poses of the unmanned aerial vehicle with respective fields of view at a fixed height that collectively cover the bounding polygon; fly the unmanned aerial vehicle to a sequence of scan poses with horizontal positions matching respective poses of the flight path and vertical positions determined to maintain a consistent distance above the roof; and scanning the roof from the sequence of scan poses to generate a three-dimensional map of the roof.

公开(公告)号：US12061307B2

公开(公告)日：2024-08-13

申请号：US17419334

申请日：2020-01-27

申请人： SoundThinking, Inc.

发明人： Gregory Alton Holifield ,  Timothy Alton Holifield ,  Lawrence Edward Stallman

IPC分类号： G01V3/08 ,  G01V3/10 ,  G06V10/764 ,  G06V20/64 ,  G08B21/18 ,  H04N23/61

CPC分类号： G01V3/081 ,  G01V3/10 ,  G06V10/764 ,  G06V20/647 ,  G08B21/182 ,  H04N23/61

摘要： Systems and methods for weapon and destructive device detection based on electromagnetic field profile are disclosed herein. According to an aspect, a system includes one or more sensors configured to detect an electromagnetic field of one or more objects and to output an electrical signal representative of the electromagnetic field. The system also includes a computing device operably connected to the one or more sensors. Further, the computing device is configured to receive the electrical signal. The computing device is also configured to determine whether each of the one or more objects meets a predetermined electromagnetic field profile based on the electrical signal. Further, the computing device is configured to present a notification to a user in response to determining that one of the objects meet the predetermined electromagnetic field profile.

公开(公告)号：US12056820B2

公开(公告)日：2024-08-06

申请号：US17179344

申请日：2021-02-18

申请人： SDC U.S. SMILEPAY SPV

发明人： Jeffrey Huber ,  Aaron Thompson ,  Ricky Reusser ,  Dustin Dorroh ,  Eric Arnebäck ,  Garrett Spiegel

IPC分类号： G06T17/20 ,  G06N3/04 ,  G06T7/00 ,  G06T17/10 ,  G06V10/25 ,  G06V10/764 ,  G06V10/82 ,  G06V20/64 ,  G06V40/16

CPC分类号： G06T17/20 ,  G06N3/04 ,  G06T7/0012 ,  G06T17/10 ,  G06V10/25 ,  G06V10/764 ,  G06V10/82 ,  G06V20/647 ,  G06V40/171 ,  G06T2207/20084 ,  G06T2207/30036

摘要： A 3D scanning toolkit to perform operations that include: accessing a first data stream at a client device, wherein the first data stream comprises at least image data; applying a bit mask to the first data stream, the bit mask identifying a portion of the image data; accessing a second data stream at the client device, the second data stream comprising depth data associated with the portion of the image data; generating a point cloud based on the depth data, the point cloud comprising a set of data points that define surface features of an object depicted in the first data stream; and causing display of a visualization of the point cloud upon a presentation of the first data stream at the client device.

公开(公告)号：US12045687B2

公开(公告)日：2024-07-23

申请号：US18118659

申请日：2023-03-07

申请人： ZEBRA TECHNOLOGIES CORPORATION

发明人： Yuri Astvatsaturov ,  Edward Barkan ,  Mark Drzymala ,  Darran Michael Handshaw

IPC分类号： G06K7/10 ,  G06F18/214 ,  G06K7/14 ,  G06V10/10 ,  G06V10/22 ,  G06V10/56 ,  G06V10/82 ,  G06V20/64 ,  G06V40/10 ,  G06V40/16 ,  G08B13/196

CPC分类号： G06K7/1096 ,  G06F18/2148 ,  G06K7/1417 ,  G06K7/1443 ,  G06V10/17 ,  G06V10/22 ,  G06V10/56 ,  G06V10/82 ,  G06V20/647 ,  G06V40/107 ,  G06V40/161 ,  G06V40/166 ,  G06V40/172 ,  G08B13/19613

摘要： Methods and systems include using three-dimensional imaging apparatuses to capture three-dimensional images and analyze resulting three-dimensional image data to enhance captured two-dimensional images for scanning related processes such as object identification, symbology detection, object recognition model training, and identifying improper scan attempts or other actions performed by an operator. Imaging systems such as bi-optic readers, handheld scanners, and machine vision systems are described using three-dimensional imaging apparatuses and described capturing three-dimensional images and using with captured two-dimensional images.

公开(公告)号：US20240242337A1

公开(公告)日：2024-07-18

申请号：US18619720

申请日：2024-03-28

申请人： Fyusion, Inc.

发明人： Stefan Johannes Josef Holzer ,  Abhishek Kar ,  Matteo Munaro ,  Pavel Hanchar ,  Radu Bogdan Rusu

IPC分类号： G06T7/00 ,  G06T3/4038 ,  G06T5/50 ,  G06V10/44 ,  G06V10/80 ,  G06V20/20 ,  G06V20/64 ,  H04N23/45

CPC分类号： G06T7/001 ,  G06T3/4038 ,  G06T5/50 ,  G06T7/0004 ,  G06V10/44 ,  G06V10/454 ,  G06V10/803 ,  G06V20/20 ,  G06V20/647 ,  H04N23/45

摘要： A background scenery portion may be identified in each of a plurality of image sets of an object, where each image set includes images captured simultaneously from different cameras. A correspondence between the image sets may determined, where the correspondence tracks control points associated with the object and present in multiple images. A multi-view interactive digital media representation of the object that is navigable in one or more dimensions and that includes the image sets may be generated and stored.

公开(公告)号：US20240233410A1

公开(公告)日：2024-07-11

申请号：US18405185

申请日：2024-01-05

申请人： BrightAl Corporation

发明人： Ryan James Goss ,  Graham David Ferris ,  Mark Norgren ,  Robert Parker ,  Daniel John Benjamin ,  John Tafoya

IPC分类号： G06V20/64 ,  G01S17/86 ,  G01S17/89 ,  G06V10/147 ,  G06V20/05 ,  G06V20/20

CPC分类号： G06V20/647 ,  G01S17/86 ,  G01S17/89 ,  G06V10/147 ,  G06V20/05 ,  G06V20/20 ,  G06V2201/12

摘要： An improved measuring device has been developed by combining a visual detector such as a camera, digital distance measuring device, and a positional sensor. The system uses positional measurements of the device along with distance measurements to generate a point cloud and uses the visual image along with distance measurements to identify and label objects. The point cloud and labeled objects are combined to generate a schematic of the environment being measured and extract relevant measurements.

公开(公告)号：US11998849B2

公开(公告)日：2024-06-04

申请号：US18071191

申请日：2022-11-29

申请人： Sony Interactive Entertainment LLC

发明人： Elke Wiggeshoff

IPC分类号： A63F13/655 ,  A63F13/213 ,  G06N20/00 ,  G06T19/00 ,  G06V10/10 ,  G06V20/20 ,  G06V20/64 ,  G06V30/142

CPC分类号： A63F13/655 ,  A63F13/213 ,  G06N20/00 ,  G06T19/006 ,  G06V10/17 ,  G06V20/20 ,  G06V20/64 ,  G06V20/647 ,  G06V30/142

摘要： A method for inserting a virtual object into an augmented reality environment, is provided, including: capturing one or more images of a real world object; processing the one or more images to identify a type of the real world object; based on the identified type of the real world object, generating a virtual object that resembles the real world object; using the identified type of the real world object to assign a functionality to the virtual object, the functionality defining a utility of the virtual object in an augmented reality environment, wherein assigning the functionality enables an action capable of being performed by the virtual object in the augmented reality environment that provides said utility; deploying the virtual object in the augmented reality environment.

公开(公告)号：US11989830B2

公开(公告)日：2024-05-21

申请号：US17752522

申请日：2022-05-24

申请人： Covidien LP

发明人： Guy Alexandroni ,  Ron Barak ,  Ariel Birenbaum ,  Nicolas J. Merlet

IPC分类号： G06T15/00 ,  G06T5/20 ,  G06T5/70 ,  G06T5/77 ,  G06T7/00 ,  G06T11/00 ,  G06T15/08 ,  G06T17/10 ,  G06V20/64

CPC分类号： G06T17/10 ,  G06T5/20 ,  G06T5/70 ,  G06T5/77 ,  G06T7/0012 ,  G06T11/005 ,  G06T11/006 ,  G06T11/008 ,  G06T15/08 ,  G06V20/647 ,  G06T2207/10121 ,  G06T2211/421

摘要： The disclosure is directed to a method for generating a three dimensional (3D) volume including a treatment target including receiving a plurality of two dimensional (2D) input images of a patient, determining a metal artifact in each of the plurality of 2D input images, removing the metal artifacts from the plurality of 2D input images based on the determination of the metal artifact, and replacing metal artifacts with alternative pixel data to generate a plurality of filtered 2D images. A 3D volume is generated from the plurality of filtered 2D images. The plurality of 2D input images including a treatment target.