公开(公告)号：US11941878B2

公开(公告)日：2024-03-26

申请号：US17358850

申请日：2021-06-25

申请人： Raytheon Company

发明人： Grant B. Boroughs ,  John J. Coogan ,  Lisa A. McCoy

IPC分类号： G06V20/58 ,  G06V10/75 ,  G06V20/10 ,  G06V10/58

CPC分类号： G06V20/182 ,  G06V10/751 ,  G06V20/176 ,  G06V20/584 ,  G06V10/58 ,  G06V20/194

摘要： A fully-automated computer-implemented system and method for generating a road network map from a remote sensing (RS) image in which the classification accuracy is satisfactory combines moving vehicle detection with spectral classification to overcome the limitations of each. Moving vehicle detections from an RS image are used as seeds to extract and characterize image-specific spectral roadway signatures from the same RS image. The RS image is then searched and the signatures matched against the scene to grow a road network map. The entire process can be performed using the radiance measurements of the scene without having to perform the complicated geometric and atmospheric conversions, thus improving computational efficiency, the accuracy of moving vehicle detection (location, speed, heading) and ultimately classification accuracy.

公开(公告)号：US20240098283A1

公开(公告)日：2024-03-21

申请号：US18471047

申请日：2023-09-20

申请人： Microchip Technology Incorporated

发明人： Thorsten Kummermehr ,  Martin Miller ,  Jan Huber

IPC分类号： H04N19/186 ,  G06V10/75

CPC分类号： H04N19/186 ,  G06V10/751

摘要： One or more examples relate to selectively line-based encoding pixels of an image via run-length encoding or gradient encoding. A method includes, for at least a portion of an image, determining a highest number of: a number of pixels in a run compressible via run-length encoding, and a number of pixels in a run compressible via gradient encoding; and selectively encoding at least some pixels of an image via the one of run-length encoding or gradient encoding corresponding to the determined highest number.

公开(公告)号：US11935376B2

公开(公告)日：2024-03-19

申请号：US17465276

申请日：2021-09-02

申请人： TRAX TECHNOLOGY SOLUTIONS PTE LTD.

发明人： Yair Adato ,  Youval Bronicki ,  Ziv Mhabary

IPC分类号： G06Q30/00 ,  G06F18/21 ,  G06N20/00 ,  G06Q10/0631 ,  G06Q10/0637 ,  G06Q10/087 ,  G06Q20/20 ,  G06Q30/0201 ,  G06Q30/0207 ,  G06Q30/0242 ,  G06Q30/0251 ,  G06Q30/0601 ,  G06T7/00 ,  G06T7/70 ,  G06V10/75 ,  G06V20/00 ,  G06V20/13 ,  G06V20/20 ,  G06V20/52 ,  G08B13/196 ,  H02J7/00 ,  H02J9/06 ,  H04N7/18 ,  H04N23/51 ,  H04N23/54 ,  H04N23/65 ,  G06V20/68 ,  G06V30/10

CPC分类号： G08B13/19632 ,  G06F18/21 ,  G06N20/00 ,  G06Q10/06312 ,  G06Q10/06315 ,  G06Q10/06375 ,  G06Q10/087 ,  G06Q20/203 ,  G06Q20/208 ,  G06Q30/0201 ,  G06Q30/0207 ,  G06Q30/0223 ,  G06Q30/0242 ,  G06Q30/0261 ,  G06Q30/0639 ,  G06Q30/0641 ,  G06Q30/0643 ,  G06T7/0006 ,  G06T7/001 ,  G06T7/70 ,  G06V10/751 ,  G06V20/00 ,  G06V20/13 ,  G06V20/20 ,  G06V20/52 ,  G08B13/19641 ,  H02J7/00036 ,  H02J7/0013 ,  H02J7/0048 ,  H02J7/0068 ,  H02J9/06 ,  H04N7/18 ,  H04N7/181 ,  H04N23/51 ,  H04N23/54 ,  H04N23/65 ,  G06T2207/10016 ,  G06T2207/30232 ,  G06V20/68 ,  G06V30/10 ,  G06V2201/07

摘要： A system for processing images captured in a retail store and automatically identifying products displayed on shelving units, includes at least one processor configured to: receive a first image depicting a shelving unit with a plurality of products of differing product types displayed thereon and a first plurality of labels coupled to the shelving unit; receive a set of second images depicting a second plurality of labels; correlate a first label depiction of a specific label included in the first image to a second label depiction of the same specific label included in a second image; use information derived from the second label depiction to determine a type of products displayed in the first image in proximity to the specific label; and initiate an action based on the determined type of products displayed in proximity to the specific label.

公开(公告)号：US11935315B2

公开(公告)日：2024-03-19

申请号：US18169332

申请日：2023-02-15

申请人： Capital One Services, LLC

发明人： Austin Walters ,  Jeremy Goodsitt ,  Galen Rafferty

IPC分类号： G06V30/40 ,  G06F3/04842 ,  G06F3/04845 ,  G06F18/22 ,  G06F40/166 ,  G06F40/205 ,  G06N3/045 ,  G06N3/08 ,  G06V10/75

CPC分类号： G06V30/40 ,  G06F3/04842 ,  G06F3/04845 ,  G06F18/22 ,  G06F40/166 ,  G06F40/205 ,  G06N3/045 ,  G06N3/08 ,  G06V10/751

摘要： In some implementations, a system may obtain document lineage training data associated with a plurality of historical documents and corresponding lineage data of independent historical documents of the plurality of historical documents. The system may train, based on the document lineage training data, a lineage analysis model to determine a lineage of edited sections of a source document. The system may receive a plurality of document files that correspond to a plurality of versions of a document. The system may determine, using a similarity analysis model, that a first section from a first version of the plurality of versions corresponds to a second section from a second version of the plurality of versions. The system may determine, using the lineage analysis model, a lineage of a corresponding section of the document that is associated with the first section and the second section.

公开(公告)号：US11935055B2

公开(公告)日：2024-03-19

申请号：US17207893

申请日：2021-03-22

申请人： Bank of America Corporation

发明人： Srilekha Mudumbai Srinivasa ,  Brandon Sloane ,  Jinyoung Nathan Kim ,  Regina Yee Cadavid ,  Nia Mack ,  Ramkumar Korlepara ,  Elliott Leonard Lillard ,  Philip Lone Mintac ,  Michael Jacob Richardson ,  Gloria Youngsook Joo

IPC分类号： G06Q20/40 ,  G06K7/10 ,  G06K7/14 ,  G06Q20/10 ,  G06Q20/20 ,  G06Q20/32 ,  G06Q40/02 ,  G06V10/75 ,  G06V40/16 ,  H04L9/40 ,  H04N7/18

CPC分类号： G06Q20/40145 ,  G06K7/10782 ,  G06K7/1417 ,  G06K7/1447 ,  G06Q20/1085 ,  G06Q20/204 ,  G06V10/751 ,  G06V40/168 ,  G06V40/172 ,  H04L63/083 ,  H04L63/0861 ,  H04N7/188 ,  G06Q20/3274 ,  G06Q20/4012 ,  G06Q40/02 ,  H04L2463/082

摘要： An Automated Teller Machine (ATM) terminal receives a transaction request from a user. The ATM terminal triggers a camera to capture a first image of the authentication media item presented by the user, where the first image of the authentication media item is embedded with a first unique code. The ATM terminal compares the first image of the authentication media item with a second image of the authentication media item that is associated with the user, where the second image of the authentication media item is embedded with a second unique code for verifying the user. The ATM terminal determines whether the first unique code corresponds to the second unique code. The ATM terminal conducts the transaction request if it is determined that the first unique code corresponds to the second unique code.

公开(公告)号：US11932394B2

公开(公告)日：2024-03-19

申请号：US17475055

申请日：2021-09-14

申请人： Honeywell International Inc.

发明人： Alberto Speranzon ,  Carl A. Dins ,  Naman Rawal

IPC分类号： B64C39/02 ,  G06F18/23 ,  G06N3/02 ,  G06T7/50 ,  G06V10/10 ,  G06V10/75 ,  G06V20/17 ,  B64U70/00 ,  B64U101/30

CPC分类号： B64C39/024 ,  G06F18/23 ,  G06N3/02 ,  G06T7/50 ,  G06V10/10 ,  G06V10/751 ,  G06V20/17 ,  B64U70/00 ,  B64U2101/30 ,  B64U2201/104 ,  G06T2207/10028 ,  G06T2207/10032 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V10/16

摘要： A system for localization of a safe landing zone comprises at least one image-capture device onboard an aerial vehicle, and an onboard processor coupled to the image-capture device. The processor is operative to execute instructions to perform a method that comprises: receive, from the image-capture device, two or more overlapping images of a landscape underneath the aerial vehicle; generate, based on the overlapping images, a landing zone heatmap of the landscape; identify, based on the landing zone heatmap, one or more regions of the landscape having potential landing zones and obstacles; and determine a location of a safe landing zone using a distance transform of the one or more regions of the landscape. The location of the safe landing zone is in an area within one of the potential landing zones that is farthest from the obstacles. The location of the safe landing zone is then stored in a database.

公开(公告)号：US20240087228A1

公开(公告)日：2024-03-14

申请号：US18464022

申请日：2023-09-08

申请人： Guangxi Zhuang Autonomous Region Natural Resources Remote Sensing Institute

发明人： Rundong Liu ,  Ruibo Chen ,  Shuhong Mei ,  Qing Liu ,  Chanling Pan ,  Mincan He ,  Jinyun Chen ,  Lijuan He ,  Shuai Wu ,  Ziyuan Bao

IPC分类号： G06T17/05 ,  G06T7/11 ,  G06T11/20 ,  G06V10/75

CPC分类号： G06T17/05 ,  G06T7/11 ,  G06T11/20 ,  G06V10/751

摘要： A method for scheduling and displaying three-dimensional annotations is provided, relating to the field of realistic three-dimensional visualization technology. The present disclosure covers data services, data scheduling schemes, data storage schemes, annotation avoidance schemes, and annotation efficient display schemes. Users can use this disclosure to schedule and display massive three-dimensional annotations in WebGL at high frame rates while consuming extremely low performance. It solves the problem of text inversion and non-hierarchical zooming of three-dimensional maps in traditional annotation and slicing services which can cause text to appear larger or smaller, breaking through the technical bottleneck that traditional annotation and slicing services that cannot be superposition displayed on 3D models. By using this disclosure, massive annotation data can be displayed without slicing, and rich annotation styles can be customized and displayed by users, providing a more advanced annotation display solution for realistic three-dimensional visualization technology.

公开(公告)号：US20240086517A1

公开(公告)日：2024-03-14

申请号：US18511297

申请日：2023-11-16

申请人： Capital One Services, LLC

发明人： Clayton Johnson ,  Daniel Tesser ,  Luis De La Rosa ,  Jeffrey Wieker

IPC分类号： G06F21/36 ,  B42D25/23 ,  B42D25/309 ,  B42D25/333 ,  G06V10/22 ,  G06V10/60 ,  G06V10/75 ,  G06V30/40

CPC分类号： G06F21/36 ,  B42D25/23 ,  B42D25/309 ,  B42D25/333 ,  G06V10/22 ,  G06V10/60 ,  G06V10/751 ,  G06V30/40

摘要： Aspects described herein may provide detection of a physical characteristic of a credential, thereby allowing for authentication of the credential. According to some aspects, these and other benefits may be achieved by detecting the physical characteristic with the credential. An image of a credential may be received. An optical characteristic of a secure feature of the credential may be determined. An expected optical characteristic of the secure feature may be determined based on known properties of the secure feature. A determination as to whether the credential is authentic may be based on a comparison of the determined optical characteristic of the secure feature to the expected optical characteristic of the secure feature.

公开(公告)号：US11923069B2

公开(公告)日：2024-03-05

申请号：US17074543

申请日：2020-10-19

申请人： FUJIFILM Corporation

发明人： Keigo Nakamura ,  Shinnosuke Hirakawa ,  Yohei Momoki

IPC分类号： G16H30/40 ,  G06F18/21 ,  G06F40/10 ,  G06N20/00 ,  G06T7/00 ,  G06V10/20 ,  G06V10/40 ,  G06V10/75 ,  G06V10/764 ,  G06V10/82 ,  G16H15/00 ,  G16H30/20

CPC分类号： G16H30/40 ,  G06F18/21 ,  G06F40/10 ,  G06N20/00 ,  G06T7/0016 ,  G06V10/255 ,  G06V10/40 ,  G06V10/751 ,  G06V10/764 ,  G06V10/82 ,  G16H15/00 ,  G16H30/20 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V2201/03

摘要： A feature information acquisition unit acquires the first feature information on the first medical image and second feature information on the second medical image having an imaging time different from an imaging time of the first medical image. A sentence creation unit compares the first feature information and the second feature information generated by the feature information acquisition unit, and creates a sentence representing a change between the first medical image and the second medical image. A display control unit causes the display unit to display a sentence representing a change.

公开(公告)号：US11921817B2

公开(公告)日：2024-03-05

申请号：US17449184

申请日：2021-09-28

申请人： Robert Bosch GmbH

发明人： Mehdi Noroozi ,  Nadine Behrmann

IPC分类号： G06F18/214 ,  G06N3/04 ,  G06N3/088 ,  G06V10/75 ,  G06V10/94 ,  G06V20/40

CPC分类号： G06F18/214 ,  G06N3/04 ,  G06N3/088 ,  G06V10/751 ,  G06V10/95 ,  G06V20/46

摘要： A computer-implemented unsupervised learning method of training a video feature extractor. The video feature extractor is configured to extract a feature representation from a video sequence. The method uses training data representing multiple training video sequences. From a training video sequence of the multiple training video sequences, a current subsequence; a preceding subsequence preceding the current subsequence; and a succeeding subsequence succeeding the current subsequence are selected. The video feature extractor is applied to the current subsequence to extract a current feature representation of the current subsequence. A training signal is derived from a joint predictability of the preceding and succeeding subsequences given the current feature representation. The parameters of the video feature extractor are updated based on the training signal.