中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

293 records (took 0.023 seconds)

    System and method for enriching a concept database
    1.
    发明授权
    System and method for enriching a concept database 有权

    公开(公告)号：US11704292B2

    公开(公告)日：2023-07-18

    申请号：US16583790

    申请日：2019-09-26

    Applicant: Cortica Ltd.

    Inventor： Igal Raichelgauz ,  Adam Harel ,  Karina Odinaev ,  Yehoshua Y Zeevi

    IPC: G06F16/215 ,  G06F16/41 ,  G06F16/483

    CPC classification number: G06F16/215 ,  G06F16/41 ,  G06F16/483

    Abstract: A system and method for enriching a concept database. The method includes determining, based on at least one signature of a first multimedia data element (MMDE) and signatures of a plurality of existing concepts in the concept database, at least one first concept among the plurality of existing concepts, wherein each of the at least one first concept matches a portion of the at least one signature of the first MMDE; generating a reduced representation of the first MMDE, wherein generating the reduced representation further comprises removing the portion of the first MMDE matching the at least one first concept; comparing the reduced representation of the first MMDE to signatures representing a plurality of second MMDEs to determine a plurality of matching second MMDEs; generating, based on the reduced representation of the first MMDE and the plurality of matching second MMDEs, at least one second concept; and adding the generated at least one second concept to the concept database.

    FUEL EFFICIENCY OPTIMIZATION BY PREDICTIVE DRIVING
    2.
    发明公开
    FUEL EFFICIENCY OPTIMIZATION BY PREDICTIVE DRIVING 审中-公开

    公开(公告)号：US20230159039A1

    公开(公告)日：2023-05-25

    申请号：US18052553

    申请日：2022-11-03

    Applicant: Cortica, Ltd.

    Inventor： Igal Raichelgauz ,  Karina Odinaev

    IPC: B60W50/00 ,  B60W40/09 ,  B60W40/105 ,  B60W40/02

    CPC classification number: B60W50/0097 ,  B60W40/02 ,  B60W40/09 ,  B60W40/105 ,  B60W2530/209 ,  B60W2554/408 ,  B60W2555/20

    Abstract: A method for fuel efficiency optimization by predictive driving, the method comprises: determining a current state of a vehicle and current state of an environment of the vehicle; estimating a future state of the vehicle and a future state of the environment of the vehicle; wherein a future state of each one of the vehicle and the environment is a state at a future point of time following a current point of time; evaluating, whether the vehicle has to change one or more vehicle progress parameters between the current point of time and the future point of time; selecting a future driving behavior out of multiple future driving behaviors, that will implement the change of the one or more vehicle progress parameters, wherein the selecting is based on a fuel consumption associated with the change of the one or more future driving parameters; and generating at least one of a selected future driving behavior suggestion, a selected future driving behavior alert, and a selected future driving behavior command.

    Dynamic matching a sensed signal to a concept structure
    3.
    发明授权
    Dynamic matching a sensed signal to a concept structure 有权

    公开(公告)号：US11481582B2

    公开(公告)日：2022-10-25

    申请号：US16729307

    申请日：2019-12-28

    Applicant: Cortica Ltd.

    Inventor： Igal Raichelgauz ,  Karina Odinaev

    IPC: G06K9/62 ,  G06N20/00 ,  G06T5/50 ,  G06T7/246 ,  G06T7/70 ,  G06T3/40 ,  G06V10/22 ,  G06V10/50 ,  G06V10/44 ,  G06V20/40

    Abstract: A method for matching a sensed signal to a concept structure, the method may include: receiving a sensed signal; generating a signature of the input image; comparing the signature of the input image to signatures of a concept structure; determining whether the signature of the input image matches any of the signatures of the concept structure based on signature matching criteria, wherein each signature of the concept structure is associated within a signature matching criterion that is determined based on an object detection parameter of the signature; and concluding that the input image comprises an object associated with the concept structure based on an outcome of the determining.

    Bootstrap unsupervised learning
    4.
    发明授权
    Bootstrap unsupervised learning 有权

    公开(公告)号：US11275971B2

    公开(公告)日：2022-03-15

    申请号：US16711494

    申请日：2019-12-12

    Applicant: Cortica Ltd.

    Inventor： Igal Raichelgauz ,  Karina Odinaev

    IPC: G06K9/00 ,  G06K9/62 ,  G06K9/46 ,  G06N20/00 ,  G06K9/20 ,  G06T5/50 ,  G06T7/246 ,  G06T7/70 ,  G06T3/40

    Abstract: Systems, and method and computer readable media that store instructions for motion based object detection. The method may include receiving or generating a video stream that comprises a sequence of images; generating image signatures of the images; wherein each image is associated with an image signature that comprises identifiers; wherein each identifier identifiers a region of interest within the image; generating movement information indicative of movements of the regions of interest within consecutive images of the sequence of images; searching, based on the movement information, for a first group of regions of interest that follow a first movement; wherein different first regions of interest are associated with different parts of an object; and linking between first identifiers that identify the first group of regions of interest.

    Identification of key points in multimedia data elements
    5.
    发明授权
    Identification of key points in multimedia data elements 有权

    公开(公告)号：US11037015B2

    公开(公告)日：2021-06-15

    申请号：US15336218

    申请日：2016-10-27

    Applicant: Cortica, Ltd.

    Inventor： Dan Elharrar ,  Marco Rossi ,  Yehoshua Y. Zeevi

    IPC: G06K9/46 ,  G06K9/64

    Abstract: A system and method for method for identifying key points in a multimedia data element (MMDE). The method includes: identifying, via a computer vision system, a plurality of candidate key points in the MMDE, wherein a size of each candidate key point is equal to a predetermined size, wherein a scale of each candidate key point is equal to a predetermined scale; analyzing the plurality of candidate key points to determine a set of properties for each candidate key point; comparing the sets of properties of the plurality of candidate key points; and selecting, based on the comparison, a plurality of key points from among the candidate key points.

    OBJECT DETECTOR HAVING SHALLOW NEURAL NETWORKS
    6.
    发明申请
    OBJECT DETECTOR HAVING SHALLOW NEURAL NETWORKS 审中-公开

    公开(公告)号：US20200311492A1

    公开(公告)日：2020-10-01

    申请号：US16681863

    申请日：2019-11-13

    Applicant: Cortica Ltd

    Inventor： Igal Raichelgauz ,  Roi Saida

    IPC: G06K9/68 ,  G06K9/32 ,  G06K9/36 ,  G06N3/04 ,  G06N3/08

    Abstract: A method that may include receiving or generating multiple versions of an input image, wherein the multiple versions differ from each other by resolution; feeding the multiple versions of the input image to multiple branches of an object detector; wherein the multiple branches comprise multiple shallow neural networks that are followed by multiple region units; calculating, by the multiple branches, candidate bounding boxes that are indicative of candidate objects that appear in the multiple versions of the input image; wherein the calculating comprises feeding intermediate results from shallow neural networks of lower resolution branches to shallow neural networks of higher resolution branches; and selecting bounding boxes out of the candidate bounding boxes, by a selection unit that follows the multiple branches

    METHOD FOR OBJECT DETECTION USING KNOWLEDGE DISTILLATION
    7.
    发明申请
    METHOD FOR OBJECT DETECTION USING KNOWLEDGE DISTILLATION 审中-公开

    公开(公告)号：US20200293904A1

    公开(公告)日：2020-09-17

    申请号：US16808408

    申请日：2020-03-04

    Applicant: CORTICA LTD.

    Inventor： Igal Raichelgauz ,  Eli Passov

    IPC: G06N3/08 ,  G06N3/04

    Abstract: A method that may include training a student ODNN to mimic a teacher ODNN. The training may include calculating a teacher student detection loss that is based on a pre-bounding-box output of the teacher ODNN. The pre-bounding-box output of the teacher ODNN is a function of pre-bounding-box outputs of different ODNNs that belong to the teacher ODNN. The method may also include detecting one or more objects in an image, by feeding the image to the trained student ODNN; outputting by the trained student ODNN a student pre-bounding-box output; and calculating one or more bounding boxes based on the student pre-bounding-box output.

Patent Agency Ranking