公开(公告)号：US20240370716A1

公开(公告)日：2024-11-07

申请号：US18769906

申请日：2024-07-11

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Hao ZHAO ,  Ming LU ,  Yiwen GUO ,  Yurong CHEN

IPC: G06N3/063 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V10/94 ,  G06V20/10 ,  G06V20/40 ,  G06V20/70

Abstract: Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.

公开(公告)号：US20240370022A1

公开(公告)日：2024-11-07

申请号：US18774184

申请日：2024-07-16

Applicant: Brain Corporation

Inventor： David Ross ,  Botond Szatmary

IPC: G05D1/00 ,  B25J9/16 ,  B25J13/08 ,  G06V10/22 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V10/94 ,  G06V20/10 ,  G06V20/52 ,  G06V20/68

Abstract: Systems and methods for detection of features within data collected by a plurality of robots by a centralized server are disclosed herein. According to at least one non-limiting exemplary embodiment, a plurality of robots may be utilized to collect a substantial amount of feature data using one or more sensors coupled thereto, wherein use of the plurality of robots to collect the feature data yields accurate localization of the feature data and consistent acquisition of the feature data. Systems and methods disclosed herein further enable a cloud server to identify a substantial number of features within the acquired feature data for purposes of generating insights. The substantial number of features far exceed a practical number of features of which a single neural network may be trained to identify.

公开(公告)号：US12136262B2

公开(公告)日：2024-11-05

申请号：US18379532

申请日：2023-10-12

Applicant: Google LLC

Inventor： Weicheng Kuo ,  Anelia Angelova ,  Tsung-Yi Lin

IPC: G06V10/82 ,  G06T7/10 ,  G06V10/25 ,  G06V10/26 ,  G06V10/44 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V20/10

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing instance segmentation by detecting and segmenting individual objects in an image. In one aspect, a method comprises: processing an image to generate data identifying a region of the image that depicts a particular object; obtaining data defining a plurality of example object segmentations; generating a respective weight value for each of the example object segmentations; for each of a plurality of pixels in the region of the image, determining a score characterizing a likelihood that the pixel is included in the particular object depicted in the region of the image using: (i) the example object segmentations, and (ii) the weight values for the example object segmentations; and generating a segmentation of the particular object depicted in the region of the image using the scores for the pixels in the region of the image.

公开(公告)号：US12136068B2

公开(公告)日：2024-11-05

申请号：US17303064

申请日：2021-05-19

Applicant: Tractable Ltd

Inventor： Razvan Ranca ,  Marcel Horstmann ,  Bjorn Mattsson ,  Janto Oellrich ,  Yih Kai Teh ,  Ken Chatfield ,  Franziska Kirschner ,  Rusen Aktas ,  Laurent Decamp ,  Mathieu Ayel ,  Julia Peyre ,  Shaun Trill ,  Crystal Van Oosterom

IPC: G06Q10/20 ,  G06F16/2457 ,  G06F18/20 ,  G06F18/214 ,  G06F18/231 ,  G06F18/24 ,  G06F18/2415 ,  G06F18/243 ,  G06F18/2431 ,  G06F40/20 ,  G06N3/04 ,  G06N3/045 ,  G06N3/049 ,  G06N3/08 ,  G06N20/00 ,  G06N20/20 ,  G06Q10/0631 ,  G06Q10/0875 ,  G06Q30/0283 ,  G06T7/00 ,  G06T7/11 ,  G06V10/20 ,  G06V10/22 ,  G06V10/25 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V20/10 ,  G06Q30/016 ,  G06Q40/08

Abstract: A method, system and apparatus for determining requirements for painting a vehicle, including receiving images of the vehicle, determining, using classifiers, one or more classifications for parts of the vehicle based on the images, wherein each classifier processes the same images and is trained to identify damage to only one part of the parts of the vehicle, wherein each classifier is trained to identify a different part of the vehicle and be generic with respect to a make and model and year of the vehicle, determining, for at least one of the parts of the vehicle, one or more paint areas, wherein each paint area is an area of damage to the vehicle requiring painting, determining one or more operations and materials required to paint at least one of the one or more paint areas and outputting the determined one or more operations and materials required.

公开(公告)号：US20240362909A1

公开(公告)日：2024-10-31

申请号：US18692725

申请日：2022-09-14

Applicant: DIGIFARM AS

Inventor： Alexei MELNITCHOUCK ,  Nils Solum HELSET ,  Yosef AKHTMAN ,  Konstantin VARIK

IPC: G06V20/13 ,  G06V10/26 ,  G06V10/32 ,  G06V10/776 ,  G06V10/82 ,  G06V20/10

CPC classification number: G06V20/13 ,  G06V10/26 ,  G06V10/32 ,  G06V10/776 ,  G06V10/82 ,  G06V20/188

Abstract: A computer-based system (210) for delineating agricultural fields based on satellite images includes a first subsystem (201) configured to receive at least one multitemporal, multispectral satellite image sequence (101) and pre-processing the images in the at least one multitemporal, multispectral satellite image sequence to generate a pre-processed image sequence (303) of multitemporal multispectral images covering a specific geographical region; a second subsystem (202) configured to perform a super-resolution method on the images in the pre-processed image sequence to generate a high-resolution image sequence (403) of multitemporal multispectral images where corresponding pixel positions in images in the sequence relate to the same geographical ground position; and a third subsystem (203) including a delineating artificial neural network (501) trained to classify pixel positions in the high-resolution image sequence (403) as being associated with a geographical ground position that is part of an agricultural field (104) or not part of an agricultural field.

公开(公告)号：US12131529B2

公开(公告)日：2024-10-29

申请号：US18098625

申请日：2023-01-18

Applicant: TOYOTA RESEARCH INSTITUTE, INC.

Inventor： Jeremy Ma ,  Josh Petersen ,  Umashankar Nagarajan ,  Michael Laskey ,  Daniel Helmick ,  James Borders ,  Krishna Shankar ,  Kevin Stone ,  Max Bajracharya

IPC: B25J9/16 ,  G06F18/214 ,  G06F18/28 ,  G06N3/08 ,  G06T7/246 ,  G06T7/33 ,  G06T7/55 ,  G06T7/73 ,  G06T19/20 ,  G06V10/75 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V20/10 ,  G06V20/20

CPC classification number: G06V20/10 ,  B25J9/1605 ,  B25J9/1661 ,  B25J9/1664 ,  B25J9/1671 ,  B25J9/1697 ,  G06F18/214 ,  G06F18/28 ,  G06N3/08 ,  G06T7/248 ,  G06T7/33 ,  G06T7/55 ,  G06T7/74 ,  G06T19/20 ,  G06V10/751 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V20/20 ,  B25J9/163 ,  G05B2219/37567 ,  G05B2219/40543 ,  G05B2219/40564 ,  G06T2200/04 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20104

Abstract: A method for performing a task by a robotic device includes mapping a group of task image pixel descriptors associated with a first group of pixels in a task image of a task environment to a group of teaching image pixel descriptors associated with a second group of pixels in a teaching image based on positioning the robotic device within the task environment. The method also includes determining a relative transform between the task image and the teaching image based on mapping the plurality of task image pixel descriptors. The relative transform indicates a change in one or more of points of 3D space between the task image and the teaching image. The method also includes performing the task associated with the set of parameterized behaviors based on updating one or more parameters of a set of parameterized behaviors associated with the teaching image based on determining the relative transform.

公开(公告)号：US12131523B2

公开(公告)日：2024-10-29

申请号：US17182951

申请日：2021-02-23

Applicant: Meta Platforms, Inc.

Inventor： Xiaohu Liu ,  Baiyang Liu ,  Rajen Subba

IPC: G06V10/82 ,  G06F3/01 ,  G06F3/16 ,  G06F7/14 ,  G06F9/451 ,  G06F16/176 ,  G06F16/22 ,  G06F16/23 ,  G06F16/242 ,  G06F16/2455 ,  G06F16/2457 ,  G06F16/248 ,  G06F16/33 ,  G06F16/332 ,  G06F16/338 ,  G06F16/903 ,  G06F16/9032 ,  G06F16/9038 ,  G06F16/904 ,  G06F16/951 ,  G06F16/9535 ,  G06F18/2411 ,  G06F40/205 ,  G06F40/295 ,  G06F40/30 ,  G06F40/40 ,  G06N3/006 ,  G06N3/08 ,  G06N7/01 ,  G06N20/00 ,  G06Q50/00 ,  G06V10/764 ,  G06V20/10 ,  G06V40/20 ,  G10L15/02 ,  G10L15/06 ,  G10L15/07 ,  G10L15/16 ,  G10L15/18 ,  G10L15/183 ,  G10L15/187 ,  G10L15/22 ,  G10L15/26 ,  G10L17/06 ,  G10L17/22 ,  H04L5/02 ,  H04L12/28 ,  H04L41/00 ,  H04L41/22 ,  H04L43/0882 ,  H04L43/0894 ,  H04L51/02 ,  H04L51/18 ,  H04L51/216 ,  H04L51/52 ,  H04L67/306 ,  H04L67/50 ,  H04L67/5651 ,  H04L67/75 ,  H04W12/08 ,  G10L13/00 ,  G10L13/04 ,  H04L51/046 ,  H04L67/10 ,  H04L67/53

CPC classification number: G06V10/82 ,  G06F3/011 ,  G06F3/013 ,  G06F3/017 ,  G06F3/167 ,  G06F7/14 ,  G06F9/453 ,  G06F16/176 ,  G06F16/2255 ,  G06F16/2365 ,  G06F16/243 ,  G06F16/24552 ,  G06F16/24575 ,  G06F16/24578 ,  G06F16/248 ,  G06F16/3323 ,  G06F16/3329 ,  G06F16/3344 ,  G06F16/338 ,  G06F16/90332 ,  G06F16/90335 ,  G06F16/9038 ,  G06F16/904 ,  G06F16/951 ,  G06F16/9535 ,  G06F18/2411 ,  G06F40/205 ,  G06F40/295 ,  G06F40/30 ,  G06F40/40 ,  G06N3/006 ,  G06N3/08 ,  G06N7/01 ,  G06N20/00 ,  G06Q50/01 ,  G06V10/764 ,  G06V20/10 ,  G06V40/28 ,  G10L15/02 ,  G10L15/063 ,  G10L15/07 ,  G10L15/16 ,  G10L15/1815 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/187 ,  G10L15/22 ,  G10L15/26 ,  G10L17/06 ,  G10L17/22 ,  H04L5/02 ,  H04L12/2816 ,  H04L41/20 ,  H04L41/22 ,  H04L43/0882 ,  H04L43/0894 ,  H04L51/02 ,  H04L51/18 ,  H04L51/216 ,  H04L51/52 ,  H04L67/306 ,  H04L67/535 ,  H04L67/5651 ,  H04L67/75 ,  H04W12/08 ,  G06F2216/13 ,  G10L13/00 ,  G10L13/04 ,  G10L2015/223 ,  G10L2015/225 ,  H04L51/046 ,  H04L67/10 ,  H04L67/53

Abstract: In one embodiment, a method includes by a client system associated with a user, receiving, at the client system, a user input from the user, parsing, by the client system, the first user input to identify a request to execute a function to be performed by an assistant system of several assistant systems associated with the client system, determining whether the user is authorized to access the assistant system by comparing a voiceprint of the user to several voiceprints stored on the client system, sending, from the client system to the assistant system in response to determining the user is authorized to access the assistant system, a request to set an assistant xbot of the assistant system into a listening mode, and receiving, at the client system from the assistant system, an indication that the assistant xbot is in listening mode.

公开(公告)号：US20240354863A1

公开(公告)日：2024-10-24

申请号：US18756780

申请日：2024-06-27

Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

Inventor： Nathan L. Tofte ,  Timothy W. Ryan ,  Nathan W. Baumann ,  Michael Shawn Jacob ,  Joshua David Lillie ,  Brian N. Harvey ,  Roxane Lyons ,  Rosemarie Geier Grant

IPC: G06Q40/08 ,  B64C39/02 ,  B64D47/08 ,  B64U10/00 ,  B64U10/14 ,  B64U101/00 ,  B64U101/30 ,  G01C11/02 ,  G06F18/22 ,  G06Q40/00 ,  G06T7/00 ,  G06T7/20 ,  G06T7/246 ,  G06T7/73 ,  G06T11/60 ,  G06T17/05 ,  G06V10/42 ,  G06V20/10 ,  G06V20/40 ,  H04N5/44 ,  H04N7/18

CPC classification number: G06Q40/08 ,  B64C39/024 ,  B64D47/08 ,  G01C11/02 ,  G06F18/22 ,  G06Q40/00 ,  G06T7/00 ,  G06T7/20 ,  G06T7/246 ,  G06T7/75 ,  G06T11/60 ,  G06T17/05 ,  G06V10/42 ,  G06V20/10 ,  G06V20/41 ,  H04N5/44 ,  H04N7/185 ,  B64U10/00 ,  B64U10/14 ,  B64U2101/00 ,  B64U2101/30 ,  B64U2201/102 ,  B64U2201/104 ,  G06T2207/10032 ,  G06T2207/30232 ,  G06T2207/30236 ,  G06T2207/30252 ,  G06T2215/16 ,  G06V20/44

Abstract: Various techniques are described utilizing one or more unmanned aerial vehicles (UAVs, or “drones”) for various disaster and/or catastrophe-related purposes. UAVs may collect data in an attempt to predict the occurrence and/or extent of a catastrophe and/or to mitigate the impact of a catastrophe before and, if not at that time, once it has occurred. The UAVs may perform various tasks such that the damage to property caused by a catastrophe (or potential catastrophe) may be eliminated or mitigated. A UAV may receive a flight path based on an energy consumption related condition and operate based on the flight path. Operating based on the flight path includes docking the UAV with a power supply device for charging a power source of the UAV.

公开(公告)号：US20240346308A1

公开(公告)日：2024-10-17

申请号：US18540335

申请日：2023-12-14

Applicant: Aon Benfield Inc.

Inventor： Takeshi Okazaki

IPC: G06N3/08 ,  G06F18/241 ,  G06N20/20 ,  G06T7/00 ,  G06V10/46 ,  G06V10/764 ,  G06V10/82 ,  G06V20/10 ,  G06V20/13

CPC classification number: G06N3/08 ,  G06F18/241 ,  G06N20/20 ,  G06T7/0002 ,  G06V10/462 ,  G06V10/764 ,  G06V10/82 ,  G06V20/13 ,  G06V20/176

Abstract: In an illustrative embodiment, methods and systems for automatically categorizing a condition of a property characteristic may include obtaining aerial imagery of a geographic region including the property, identifying features of the aerial imagery corresponding to the property characteristic, analyzing the features to determine a property characteristic classification, and analyzing a region of the aerial imagery including the property characteristic to determine a condition classification.

公开(公告)号：US20240341227A1

公开(公告)日：2024-10-17

申请号：US18298485

申请日：2023-04-11

Applicant: DEERE & COMPANY

Inventor： Nathan R. Vandike ,  Martin Franz Unterpaintner ,  Benjamin Peschel

IPC: A01D41/12 ,  A01D41/127 ,  G06T5/50 ,  G06T7/50 ,  G06T7/62 ,  G06T17/00 ,  G06V10/44 ,  G06V20/10

CPC classification number: A01D41/1243 ,  A01D41/127 ,  G06T5/50 ,  G06T7/50 ,  G06T7/62 ,  G06T17/00 ,  G06V10/44 ,  G06V20/188 ,  G06T2207/20221

Abstract: One or more sensors can capture images of at least a portion of crop residue, which can be shown in real time on a display. Information captured by the sensors can be used to determine crop residue parameter information. The crop residue information can pertain to either or both the processing of crop residue by, or the distribution of crop residue from, the agricultural machine. Virtual representations of the crop residue parameter information can overlay at least a portion of, or otherwise be presented in connection with, the captured image shown on the display. The virtual representation can have an appearance that can visually convey the crop residue parameter information to an operator. Such visual representations can include the use of parameter identifiers, graphical shapes, or text, as well as combinations thereof. The virtual representation of the crop residue parameter information can also provide an indication as to whether the crop residue parameter information satisfies a predetermined threshold.