公开(公告)号：US20230162520A1

公开(公告)日：2023-05-25

申请号：US17534704

申请日：2021-11-24

申请人： ABBYY Development Inc.

发明人： Stanislav Semenov ,  Ivan Zagaynov ,  Dmitry Solntsev ,  Aleksey Kalyuzhny

IPC分类号： G06K9/00 ,  G06K9/32 ,  G06T7/11 ,  G06K9/62 ,  G06T7/77 ,  G06N3/04

CPC分类号： G06K9/00469 ,  G06K9/00979 ,  G06K9/3233 ,  G06K9/6232 ,  G06K9/6298 ,  G06N3/0472 ,  G06T7/11 ,  G06T7/77 ,  G06T2207/20021 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30176

摘要： Systems and methods for identifying writing systems utilized in documents. An example method comprises: receiving a document image; splitting the document image into a plurality of image fragments; generating, by a neural network processing the plurality of image fragments, a plurality of probability vectors, wherein each probability vector of the plurality of probability vectors is produced by processing a corresponding image fragments and contains a plurality of numeric elements, and wherein each numeric element of the plurality of numeric elements reflects a probability of the image fragment containing a text associated with a respective writing system; computing an aggregated probability vector by aggregating the plurality of probability vectors, wherein each numeric element of the aggregated probability vector reflects a probability of the image containing a text associated with a writing system that is identified by an index of the numeric element within the aggregated probability vector; and responsive to determining that a maximum numeric element of the aggregated probability vector exceeds a predefined threshold value, concluding that the document image contains one or more symbols associated with a respective writing system.

公开(公告)号：US20190087656A1

公开(公告)日：2019-03-21

申请号：US16133654

申请日：2018-09-17

申请人： GOOGLE LLC

发明人： Martin T. King ,  Dale L. Grover ,  Clifford A. Kushler ,  James Q. Stafford-Fraser

IPC分类号： G06K9/00 ,  G06Q30/00 ,  G06F17/30 ,  G06K9/22 ,  H04N1/32 ,  H04N1/107 ,  G06Q10/10 ,  H04N1/00

CPC分类号： G06K9/00483 ,  G06F16/5846 ,  G06K9/00422 ,  G06K9/00469 ,  G06K9/00979 ,  G06K9/228 ,  G06K2209/01 ,  G06Q10/10 ,  G06Q30/00 ,  H04N1/00241 ,  H04N1/00307 ,  H04N1/00488 ,  H04N1/0049 ,  H04N1/107 ,  H04N1/32101 ,  H04N2201/0041 ,  H04N2201/0055 ,  H04N2201/0058 ,  H04N2201/0081 ,  H04N2201/0084 ,  H04N2201/0096 ,  H04N2201/3249 ,  H04N2201/3264 ,  H04N2201/3269

摘要： A device for capturing rendered text is described. The device incorporates one or more visual sensors that receive visual information as a part of capturing rendered text. The visual sensors are collectively capable of capturing both text that is permanently printed on a page, and text that is displayed transitorily on a dynamic device. The device further incorporates a visual information disposition subsystem for disposing of visual information received by the visual sensors. The device further incorporates a package that bears the visual sensors and the visual information disposition subsystem, and is suitable to be held in a human hand.

公开(公告)号：US20190066328A1

公开(公告)日：2019-02-28

申请号：US15683367

申请日：2017-08-22

申请人： HERE GLOBAL B.V.

发明人： Richard KWANT ,  Anish MITTAL ,  David LAWLOR

IPC分类号： G06T7/73

CPC分类号： G06T7/74 ,  G06K9/00228 ,  G06K9/00791 ,  G06K9/00979 ,  G06K9/6215 ,  G06T7/75 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30201 ,  G06T2207/30232 ,  G06T2207/30236 ,  G06T2207/30252 ,  G06T2207/30256

摘要： An approach is provided for a vertex-based evaluation of polygon similarity. The approach, for instance, involves processing, by a computer vision system, an image to generate a first set of vertices of a first polygon representing an object depicted in the image. The approach also involves for each vertex in the first set of vertices, determining a closest vertex in a second set of vertices of a second polygon, and determining a distance between said each vertex in the first set of vertices and the closest vertex in the second set of vertices. The approach further involves calculating a polygon similarity of the first polygon with respect to the second polygon based on a total of the distance determined for said each vertex in the first set of vertices normalized to a number of vertices in the first set of vertices.

公开(公告)号：US20190065861A1

公开(公告)日：2019-02-28

申请号：US16109533

申请日：2018-08-22

申请人： Bossa Nova Robotics IP, Inc.

发明人： Marios Savvides ,  An Pang Lin ,  Shreyas Venugopalan ,  Ajmal Thanikkal ,  Karanhaar Singh ,  Gavriel Adler ,  Kyle Neblett ,  Christopher Palmer

IPC分类号： G06K9/00 ,  G06F17/30

CPC分类号： G06K9/00771 ,  G06F16/784 ,  G06K9/00362 ,  G06K9/00369 ,  G06K9/00979

摘要： A method for processing arrival or removal of packages within the field of view of a video camera includes providing a database for recording packages placed in the field of view. Based on real-time analysis of successive image frames in the camera, a human person's entry and exit from the field of view of the camera is also detected. Delivery or removal of objects is recorded in the database. In one embodiment, the method also determines whether or not a newly arrived package is placed alongside or on top of an existing package.

公开(公告)号：US20190051143A9

公开(公告)日：2019-02-14

申请号：US15904399

申请日：2018-02-25

申请人： RING Inc.

发明人： John Modestine ,  Joshua Roth

IPC分类号： G08B27/00 ,  G06T7/70 ,  G06T7/292

CPC分类号： G06T7/292 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/0488 ,  G06F17/28 ,  G06K9/00201 ,  G06K9/00221 ,  G06K9/00288 ,  G06K9/00771 ,  G06K9/00979 ,  G06K9/2018 ,  G06K9/2027 ,  G06K2009/00738 ,  G06T7/70 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/30232 ,  G08B3/10 ,  G08B13/19645 ,  G08B13/19656 ,  G08B13/19671 ,  G08B13/19682 ,  G08B13/19684 ,  G08B13/19695 ,  G08B15/001 ,  G08B15/004 ,  G08B25/08 ,  G08B27/001 ,  G08B27/003 ,  G08B27/005 ,  G10L17/005 ,  G10L25/57 ,  H04L65/1069 ,  H04L65/4076 ,  H04L65/4084 ,  H04L67/10 ,  H04L67/12 ,  H04N5/2252 ,  H04N5/23206 ,  H04N5/77 ,  H04N5/91 ,  H04N7/147 ,  H04N7/186 ,  H04W4/021 ,  H04W4/08

摘要： The present embodiments relate to improvements to audio/video (A/V) recording and communication devices, including improved approaches to using a neighborhood alert mode for triggering multi-device recording, to a multi-camera motion tracking process, and to a multi-camera event stitching process to create a series of “storyboard” images for activity taking place across the fields of view of multiple cameras, within a predetermined time period, for the A/V recording and communication devices.

公开(公告)号：US20190042846A1

公开(公告)日：2019-02-07

申请号：US16073200

申请日：2017-01-25

申请人： Robert Bosch GmbH

发明人： Darno Alexander Ketterer

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/22

CPC分类号： G06K9/00671 ,  G06K9/00208 ,  G06K9/00979 ,  G06K9/22 ,  G06K9/4652

摘要： A method for detecting objects, in particular three-dimensional objects, includes carrying out a digital scan of at least one image section of an image of at least one object to be detected in order to digitally detect points of the image. The digital detection at least of individual points of the image is carried out at least on the basis of a deviation of at least one characteristic of at least two points, in particular on the basis of a deviation of at least one characteristic of the last digitally detected point in comparison to a characteristic of at least one point to be detected digitally.

公开(公告)号：US10063716B2

公开(公告)日：2018-08-28

申请号：US15229812

申请日：2016-08-05

申请人： Textron Innovations Inc.

发明人： Robert Lloyd Steadman

IPC分类号： G06K9/00 ,  H04N1/00 ,  H04N7/18 ,  H04W84/18 ,  H04W88/04 ,  F42C13/00 ,  G06T11/00 ,  H04N1/411 ,  G08B13/196

CPC分类号： H04N1/00103 ,  F42C13/00 ,  G06K9/00 ,  G06K9/00771 ,  G06K9/00979 ,  G06T11/003 ,  G06T2207/10032 ,  G06T2207/20132 ,  G06T2207/30212 ,  G06T2207/30232 ,  G08B13/19656 ,  H04N1/4115 ,  H04N7/181 ,  H04N2201/0039 ,  H04N2201/0043 ,  H04N2201/0055 ,  H04W84/18 ,  H04W88/04

摘要： A system includes nodes deployable across an area and self-forming a mobile ad-hoc network. The nodes include (1) imaging circuitry for capturing an image of a local sub-area based on a triggering event, (2) image-transfer circuitry for partitioning a captured image into sub-images or image segments and transmitting them to other nodes, (3) image-transmission circuitry for transmitting a sub-image from another node on an uplink to a relay such as a satellite. The relay (1) receives transmissions of respective sub-images, in parallel on independent channels, from the nodes via respective uplinks, and (2) retransmits the sub-images to the remote location via a downlink. A central control station at the remote location (1) receives the sub-images from the relay via the downlink, (2) re-creates the captured image by combining the received sub-images, and (3) utilizes the re-created image in a monitoring or control operation of the central control station.

公开(公告)号：US20180234420A1

公开(公告)日：2018-08-16

申请号：US15432831

申请日：2017-02-14

申请人： Jumio Corporation

发明人： Daniel Mattes ,  Chad Starkey

IPC分类号： H04L29/06 ,  G06Q20/40 ,  G06K9/00

CPC分类号： G06K9/00892 ,  G06K9/00006 ,  G06K9/00281 ,  G06K9/00288 ,  G06K9/00597 ,  G06K9/00979 ,  G06Q20/12 ,  G06Q20/32 ,  G06Q20/3224 ,  G06Q20/40145 ,  H04L63/083 ,  H04L63/0861 ,  H04L63/107 ,  H04L2463/102 ,  H04L2463/121

摘要： The various embodiments described herein include methods, devices, and systems for identifying users. In one aspect, a method includes (1) receiving from a server a request to identify a user; (2) in response to the identification request, sending a request for encoded image data corresponding to one or more features of the first user, the request specifying a particular encoding for the image data; (3) receiving encoded image data corresponding to the one or more features of the first user; (4) obtaining stored image data for an authorized user corresponding to one or more features of the authorized user; (5) determining whether the first user is the authorized user based on a comparison of the received encoded image data and the stored image data; and (6) providing to the remote server an identification indicator based on the determination of whether the first user is the authorized user.

公开(公告)号：US20180233025A1

公开(公告)日：2018-08-16

申请号：US15904399

申请日：2018-02-25

申请人： RING Inc.

发明人： John Modestine ,  Joshua Roth

IPC分类号： G08B27/00 ,  G06T7/70 ,  G06T7/292

CPC分类号： G06T7/292 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/0488 ,  G06F17/28 ,  G06K9/00201 ,  G06K9/00221 ,  G06K9/00288 ,  G06K9/00771 ,  G06K9/00979 ,  G06K9/2018 ,  G06K9/2027 ,  G06K2009/00738 ,  G06T7/70 ,  G06T2207/10004 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/30232 ,  G08B3/10 ,  G08B13/19645 ,  G08B13/19656 ,  G08B13/19671 ,  G08B13/19682 ,  G08B13/19684 ,  G08B13/19695 ,  G08B15/001 ,  G08B15/004 ,  G08B25/08 ,  G08B27/001 ,  G08B27/003 ,  G08B27/005 ,  G10L17/005 ,  G10L25/57 ,  H04L65/1069 ,  H04L65/4076 ,  H04L65/4084 ,  H04L67/10 ,  H04L67/12 ,  H04N5/2252 ,  H04N5/23206 ,  H04N5/77 ,  H04N5/91 ,  H04N7/147 ,  H04N7/186 ,  H04W4/021 ,  H04W4/08

摘要： The present embodiments relate to improvements to audio/video (A/V) recording and communication devices, including improved approaches to using a neighborhood alert mode for triggering multi-device recording, to a multi-camera motion tracking process, and to a multi-camera event stitching process to create a series of “storyboard” images for activity taking place across the fields of view of multiple cameras, within a predetermined time period, for the A/V recording and communication devices.

公开(公告)号：US20180203880A1

公开(公告)日：2018-07-19

申请号：US15409497

申请日：2017-01-18

申请人： Fyusion, Inc.

发明人： Stefan Johannes Josef Holzer ,  Abhishek Kar ,  Pantelis Kalogiros ,  Ioannis Spanos ,  Luke Parham ,  Radu Bogdan Rusu

IPC分类号： G06F17/30 ,  G06K9/62 ,  G06K9/72

CPC分类号： G06F16/532 ,  G06F16/583 ,  G06F16/5866 ,  G06K9/00664 ,  G06K9/00979 ,  G06K9/22

摘要： Provided are mechanisms and processes for performing live search using multi-view digital media representations. In one example, a process includes receiving a visual search query from a device for an object to be searched, where the visual search query includes a first set of viewpoints of the object obtained during capture of a first surround view of the object during a live search session. Next, additional recommended viewpoints of the object are identified for the device to capture, where the additional recommended viewpoints are chosen to provide more information about the object. A first set of search results based on the first set of viewpoints and additional recommended viewpoints of the object are transmitted to the device. In response, a second set of viewpoints of the object captured using image capture capabilities of the device are received. A second set of search results with enhanced matches for the object based on the first and second sets of viewpoints are then transmitted to the device. This process may continue iteratively until a desired set of search results is obtained.