中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

35 records (took 0.019 seconds)

    OBJECT DETECTION DEVICE, LEARNED MODEL GENERATION METHOD, AND RECORDING MEDIUM
    14.
    发明公开
    OBJECT DETECTION DEVICE, LEARNED MODEL GENERATION METHOD, AND RECORDING MEDIUM 审中-公开

    公开(公告)号：US20230334837A1

    公开(公告)日：2023-10-19

    申请号：US18026631

    申请日：2020-09-24

    Applicant: NEC Corporation

    Inventor： Katsuhiko TAKAHASHI ,  Yuichi NAKATANI ,  Tetsuo INOSHITA ,  Asuka ISHII

    IPC: G06V10/776 ,  G06V10/74

    CPC classification number: G06V10/776 ,  G06V10/761

    Abstract: In an object detection device, the plurality of object detection units output a score indicating a probability that a predetermined object exists for each partial region set with respect to inputted image data. The weight computation unit uses weight computation parameters to compute a weight for each of the plurality of object detection units on a basis of the image data and outputs of the plurality of object detection units, the weight being used when the scores outputted by the plurality of object detection units are merged. The merging unit merges the scores outputted by the plurality of object detection units for each partial region according to the weights computed by the weight computation unit. The first loss computation unit computes a difference between a ground truth label of the image data and the score merged by the merging unit as a first loss. Then, the first parameter correction unit corrects the weight computation parameters so as to reduce the first loss.

    OBJECT SENSING DEVICE, LEARNING METHOD, AND RECORDING MEDIUM
    16.
    发明申请
    OBJECT SENSING DEVICE, LEARNING METHOD, AND RECORDING MEDIUM 有权

    公开(公告)号：US20220277552A1

    公开(公告)日：2022-09-01

    申请号：US17624906

    申请日：2019-07-11

    Applicant: NEC Corporation

    Inventor： Katsuhiko TAKAHASHI ,  Yuichi NAKATANI ,  Tetsuo INOSHITA ,  Asuka ISHII ,  Gaku NAKANO

    IPC: G06V10/776 ,  G06V10/22 ,  G06V10/80

    Abstract: In an object detection device, a plurality of object detection units output a score indicating the probability that a predetermined object exists for each partial region set with respect to inputted image data. On the basis of the image data, a weight computation unit uses weight computation parameters to compute weights for each of the plurality of object detection units, the weights being used when the scores outputted by the plurality of object detection units are merged. A merging unit merges the scores outputted by the plurality of object detection units for each partial region according to the weights computed by the weight computation unit. A loss computation unit computes a difference between a ground truth label of the image data and the scores merged by the merging unit as a loss. Then, a parameter correction unit corrects the weight computation parameters so as to reduce the computed loss.

    INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM
    17.
    发明申请
    INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM 有权

    公开(公告)号：US20220058395A1

    公开(公告)日：2022-02-24

    申请号：US17414015

    申请日：2018-12-26

    Applicant: NEC Corporation

    Inventor： Katsuhiko TAKAHASHI

    IPC: G06K9/00 ,  G06K9/62

    Abstract: An information processing apparatus (10) includes an event detection unit (110), an input reception unit (120), and a processing execution unit (130). The event detection unit (110) detects a specific event from video data. The input reception unit (120) receives, from a user, input for specifying processing to be executed. The processing execution unit (103) executes first processing specified by input received by the input reception unit (120), and executes second processing of generating learning data used for machine learning and storing the generated learning data in a learning data storage unit (40). The processing execution unit (130) discriminates, in the second processing, based on a classification of the first processing specified by input received by the input reception unit (120), whether a detection result of a specific event is correct, and generates learning data including at least a part of video data, category information indicating a category of a specific event detected by the event detection unit (110), and correct/incorrect information indicating whether a detection result of an specific event is correct or incorrect.

    SURVEILLANCE SYSTEM, SURVEILLANCE METHOD, AND PROGRAM
    18.
    发明申请
    SURVEILLANCE SYSTEM, SURVEILLANCE METHOD, AND PROGRAM 有权

    公开(公告)号：US20220006979A1

    公开(公告)日：2022-01-06

    申请号：US17480629

    申请日：2021-09-21

    Applicant: NEC CORPORATION

    Inventor： Ryoma OAMI ,  Katsuhiko TAKAHASHI ,  Yuusuke KONISHI ,  Hiroo IKEDA ,  Junko NAKAGAWA ,  Kosuke YOSHIMI ,  Yukie EBIYAMA ,  Ryo KAWAI ,  Takuya OGAWA

    IPC: H04N7/18 ,  G08B25/10 ,  H04M11/00 ,  G08B21/22 ,  G06Q10/06 ,  G08B25/04

    Abstract: A surveillance system (1) includes an area information acquisition unit (101), a position information acquisition unit (102), a candidate determination unit (103), and a notification unit (104). The area information acquisition unit (101) acquires information of a surveillance-desired area. The position information acquisition unit (102) acquires pieces of position information of a plurality of portable terminals (20), each portable terminal performing surveillance using an image capturing unit. The candidate determination unit (103) determines a candidate portable terminal (20) to be moved to the surveillance-desired area from among the plurality of portable terminals (20) based on the acquired pieces of position information of the plurality of portable terminals (20). The notification unit (104) outputs a notification to the candidate portable terminal requesting to move to the surveillance-desired area.

Patent Agency Ranking