公开(公告)号：US11820383B2

公开(公告)日：2023-11-21

申请号：US17164868

申请日：2021-02-02

Applicant: DENSO CORPORATION

Inventor： Hiroto Banno ,  Takuhiro Omi ,  Yutaka Munaoka ,  Takeshi Enya

IPC: B60W40/08 ,  B60R11/04 ,  G06V20/59 ,  G06V40/16 ,  G06T7/292 ,  G06T7/73 ,  G06T7/593 ,  H04N13/204 ,  B60W30/09 ,  B60W30/14 ,  G08B21/02 ,  G08G1/16 ,  G08B21/06

CPC classification number: B60W40/08 ,  B60R11/04 ,  B60W30/09 ,  B60W30/14 ,  G06T7/292 ,  G06T7/593 ,  G06T7/73 ,  G06V20/597 ,  G06V40/161 ,  G06V40/171 ,  G08B21/02 ,  H04N13/204 ,  B60W2040/0818 ,  B60W2420/42 ,  B60W2540/043 ,  B60W2540/10 ,  B60W2540/12 ,  B60W2540/18 ,  B60W2540/223 ,  B60W2554/00 ,  B60W2554/80 ,  B60W2554/802 ,  B60W2554/804 ,  G06T2207/10012 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/30201 ,  G06T2207/30241 ,  G06T2207/30268 ,  G06V2201/10 ,  G06V2201/12 ,  G08B21/06 ,  G08G1/16

Abstract: Apparatus detecting driving incapability state of a driver includes: a head detection portion that successively detects a head portion, which is higher than a neck of the driver, based on an image of a driver's seat captured by an imaging device mounted in a vehicle; and an out-of-frame state detection portion that detects that the driver is incapable of driving, when the head portion detected by the head detection portion is out of a predetermined scope in the image during travelling of the vehicle.

公开(公告)号：US11812694B2

公开(公告)日：2023-11-14

申请号：US17039997

申请日：2020-09-30

Applicant: Deere & Company

Inventor： John A. Dighton ,  Bryan E. Dugas ,  Rahul Gunda ,  Peter A. Johnson

IPC: G06V20/56 ,  A01D41/14 ,  A01D41/127 ,  G06T7/73 ,  G06V20/10 ,  G06T7/80 ,  G06V10/10 ,  A01D41/12 ,  A01D43/073 ,  A01D43/08 ,  A01D43/063 ,  A01D63/04 ,  A01D47/00 ,  A01D90/02

CPC classification number: A01D41/141 ,  A01D41/127 ,  A01D41/1217 ,  A01D43/0631 ,  A01D43/073 ,  A01D43/087 ,  G06T7/74 ,  G06T7/80 ,  G06V10/10 ,  G06V20/188 ,  G06V20/56 ,  A01D47/00 ,  A01D63/04 ,  A01D90/02 ,  G06T2207/10028 ,  G06T2207/30252 ,  G06V2201/12

Abstract: A harvester including a mono-camera having a first field of view, where the camera outputs a first image representative of the first field of view, and where the first image is a two-dimensional representation of the first field of view. The harvester also includes a controller in operable communication with the mono-camera, where the controller establishes a second two-dimensional reference frame fixed relative to the first field of view, where the controller identifies a reference point within the first image, where the controller locates the reference point within the second two-dimensional reference frame, and where the controller calculates the location of the reference point relative to the first, three-dimensional reference frame based on the position of the reference point within the second two-dimensional reference frame.

公开(公告)号：US20230360380A1

公开(公告)日：2023-11-09

申请号：US18044443

申请日：2020-09-11

Applicant: Siemens Aktiengesellschaft

Inventor： Fan Bo Meng ,  Xiang Li ,  Xiao Feng Wang

IPC: G06V10/82 ,  G06V10/75 ,  G06V10/774

CPC classification number: G06V10/82 ,  G06V10/76 ,  G06V10/774 ,  G06V2201/12 ,  G06V2201/07

Abstract: The present disclosure provides methods and/or systems for identifying an object. An example method includes: generating a plurality of synthesized images according to a three-dimensional digital model, the plurality of synthesized images having different view angles; respectively extracting eigenvectors of the plurality of synthesized images; generating a first fused vector by fusing the eigenvectors of the plurality of synthesized images; inputting the first fused vector into a classifier to train the classifier; acquiring a plurality of pictures of the object, the plurality of pictures respectively having same view angles as at least a portion of the plurality of synthesized images; respectively extracting eigenvectors of the plurality of pictures; generating a second fused vector by fusing the eigenvectors of the plurality of pictures; and inputting the second fused vector into the trained classifier to obtain a classification result of the object.

公开(公告)号：US20230351741A1

公开(公告)日：2023-11-02

申请号：US18302230

申请日：2023-04-18

Applicant: Robert Bosch GmbH

Inventor： Maximilian Menke ,  Reiko Lettmoden ,  Thomas Wenzel

IPC: G06V10/82 ,  G06V10/75 ,  G06V20/58 ,  G06V20/40

CPC classification number: G06V10/82 ,  G06V10/751 ,  G06V20/58 ,  G06V20/49 ,  G06V2201/12 ,  G06V2201/07

Abstract: A computer-implemented method for training a machine learning system for transferring images of a source domain into a target domain. The method includes: ascertaining source patches based on source images of a source domain and target patches based on target images of a target domain, the source patches and the target patches each being assigned pixel-by-pixel pieces of meta-information; ascertaining tuples, each including one source patch and at least one target patch which characterizes a neighbor of the source patch nearest to k according to a similarity measure, k being a hyperparameter of the method and the similarity measure characterizing a similarity between a source patch and a target patch based on the pixel-by-pixel meta-information of the source patch and of the target patch; training the machine learning system based on the source patches of the tuples and on the target patches of the tuples.

公开(公告)号：US20230351724A1

公开(公告)日：2023-11-02

申请号：US17800688

申请日：2020-02-18

Applicant: Google LLC

Inventor： Tingbo Hou ,  Adel Ahmadyan ,  Jianing Wei ,  Matthias Grundmann

IPC: G06V10/75 ,  G06V10/80 ,  G06V20/40 ,  G06T7/70

CPC classification number: G06V10/751 ,  G06V10/817 ,  G06V20/46 ,  G06T7/70 ,  G06V2201/12 ,  G06V2201/07 ,  G06T2207/20081

Abstract: The present disclosure is directed to systems and methods for performing object detection and pose estimation in 3D from 2D images. Object detection can be performed by a machine-learned model configured to determine various object properties. Implementations according to the disclosure can use these properties to estimate object pose and size.

公开(公告)号：US11740474B2

公开(公告)日：2023-08-29

申请号：US17872443

申请日：2022-07-25

Applicant: Magic Leap, Inc.

Inventor： Gholamreza Amayeh ,  Adrian Kaehler ,  Douglas Lee

IPC: G02B27/01 ,  G02B27/00 ,  G06V20/64 ,  G06V40/16 ,  G06V40/19

CPC classification number: G02B27/0172 ,  G02B27/0093 ,  G02B27/0103 ,  G06V20/64 ,  G06V40/169 ,  G02B2027/0105 ,  G02B2027/0138 ,  G02B2027/0174 ,  G02B2027/0178 ,  G02B2027/0187 ,  G06V40/19 ,  G06V2201/12

Abstract: Systems and methods for generating a face model for a user of a head-mounted device are disclosed. The head-mounted device can include one or more eye cameras configured to image the face of the user while the user is putting the device on or taking the device off. The images obtained by the eye cameras may be analyzed using a stereoscopic vision technique, a monocular vision technique, or a combination, to generate a face model for the user.

公开(公告)号：US20230237801A1

公开(公告)日：2023-07-27

申请号：US17923883

申请日：2020-07-30

Applicant: Intel Corporation

Inventor： Longwei FANG ,  Qiang LI ,  Wenlong LI ,  Yikai FANG ,  Hang ZHENG

IPC: G06V20/40 ,  G06T7/292 ,  G06V10/26

CPC classification number: G06V20/42 ,  G06T7/292 ,  G06V10/267 ,  G06V2201/07 ,  G06V2201/12

Abstract: Techniques related to performing object or person association or correspondence in multi-view video are discussed. Such techniques include determining correspondences at a particular time instance based on separately optimizing correspondence sub-matrices for distance sub-matrices based on two-way minimum distance pairs between frame pairs, generating and fusing tracklets across time instances, and adjusting correspondence, after such tracklet processing, via elimination of outlier object positions and rearrangement of object correspondence.

公开(公告)号：US11704931B2

公开(公告)日：2023-07-18

申请号：US17302286

申请日：2021-04-29

Applicant: Google LLC

Inventor： Idris Syed Aleem ,  Daniel David Albin Balzerson

IPC: G06V40/16 ,  G02B27/01 ,  G06F3/01

CPC classification number: G06V40/165 ,  G02B27/0172 ,  G06F3/013 ,  G02B2027/0138 ,  G06V2201/12

Abstract: A system and method of detecting display fit measurements and/or ophthalmic measurements for a head mounted wearable computing device including a display device is provided. The system and method may include capturing image data including a face of a user to be fitted for the head mounted wearable computing device. A three-dimensional head pose and gaze measurements may be extracted and a three-dimensional model may be developed from the captured image data. The system may detect display fit measurements and/or ophthalmic fit measurements from the three-dimensional model, and may provide one or more head mounted wearable computing devices that meet the display fit and/or ophthalmic fit requirements.

公开(公告)号：US20240338931A1

公开(公告)日：2024-10-10

申请号：US18295358

申请日：2023-04-04

Applicant: Florida Power & Light Company

Inventor： Khamsouksavanh Sanvoravong ,  Mackenzie Vecchio ,  Kyle A. Bush ,  Eric Schwartz ,  Kent A. Logue ,  Michael Wenell ,  Sam Hammermaster ,  Jordan Wilkerson ,  Erin Murphy ,  Gage Irwin

IPC: G06V10/774 ,  G06T5/50 ,  G06V20/64

CPC classification number: G06V10/774 ,  G06T5/50 ,  G06V20/64 ,  G06T2207/20221 ,  G06V2201/12

Abstract: Systems and methods to generate synthetic images for use in a machine learning training set. The process begins with accessing a database of real-world 3-D images of equipment in a power grid, the 3-D images of equipment include 3-D measurements to create a dimensionally accurate and photorealistic model of the equipment. Optionally, the 3-D images could be aged or weathered using imaging editing software. Next, a database of real-world photographs of scenes in which the equipment is installed is accessed. Optionally, the identical scenes can be captured at different times of day, different times of the year, and at different perspectives. Next, using image editing software, the 3-D images of equipment is inserted into at least one of the scenes to form a synthetic image based on a combination of the equipment and the scene in which each of the equipment and the scene were previously captured independently of each other.

公开(公告)号：US12093363B2

公开(公告)日：2024-09-17

申请号：US17831644

申请日：2022-06-03

Applicant: Shopify Inc.

Inventor： Jonathan Wade ,  Stephan Leroux ,  Daniel Beauchamp ,  Andrew Ngo

IPC: G06F21/36 ,  G01S7/48 ,  G01S17/86 ,  G06F21/62 ,  G06V20/64

CPC classification number: G06F21/36 ,  G01S7/4802 ,  G01S17/86 ,  G06F21/629 ,  G06V20/647 ,  G06V2201/12

Abstract: The present disclosure provides a system and method for object verification. The method comprises obtaining sensor data, from one or more sensors, the sensor data including measurements of one or more physical properties of a given three-dimensional (3D) object, wherein the sensor data comprises a first measurement of the one or more physical properties from a first perspective and a second measurement of the one or more physical properties from a second perspective, the second perspective being different from the first perspective. The method further comprises comparing the sensor data with reference data, the reference data including measurements of one or more corresponding physical properties of a reference 3D object, and generating, based on the comparing, a verification signal indicating a determined match between the given 3D object and the reference 3D object.