知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

32 records (took 0.015 seconds)

    LEARNING APPARATUS, ESTIMATION APPARATUS, LEARNING METHOD, ESTIMATION METHOD AND PROGRAM
    2.
    发明公开
    LEARNING APPARATUS, ESTIMATION APPARATUS, LEARNING METHOD, ESTIMATION METHOD AND PROGRAM 审中-公开

    公开(公告)号：US20240005655A1

    公开(公告)日：2024-01-04

    申请号：US18247493

    申请日：2020-10-21

    Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

    Inventor： Mihiro UCHIDA ,  Jun SHIMAMURA ,  Shingo ANDO ,  Takayuki UMEDA

    IPC: G06V10/98 ,  G06V10/774 ,  G06V10/764 ,  G06V10/82

    CPC classification number: G06V10/98 ,  G06V10/774 ,  G06V10/764 ,  G06V10/82

    Abstract: A learning apparatus includes: a data generation unit that learns generation of data based on a class label signal and a noise signal; an unknown degree estimation unit that learns estimation of a degree to which input data is unknown using a training set and the data generated by the data generation unit; a first class likelihood estimation unit that learns estimation of a first likelihood of each class label for input data using the training set; a second class likelihood estimation unit that learns estimation of a second likelihood of each class label for input data using the training set and the data generated by the data generation unit; a class likelihood correction unit that generates a third likelihood by correcting the first likelihood on the basis of the unknown degree and the second likelihood; and a class label estimation unit that estimates a class label of data related to the third likelihood on the basis of the third likelihood, thereby automatically estimating a cause of an error by a deep model.

    CANDIDATE REGION ESTIMATION DEVICE, CANDIDATE REGION ESTIMATION METHOD, AND PROGRAM
    4.
    发明申请
    CANDIDATE REGION ESTIMATION DEVICE, CANDIDATE REGION ESTIMATION METHOD, AND PROGRAM 有权

    公开(公告)号：US20210304415A1

    公开(公告)日：2021-09-30

    申请号：US17265166

    申请日：2019-08-01

    Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

    Inventor： Yukito WATANABE ,  Shuhei TARASHIMA ,  Takashi HOSONO ,  Jun SHIMAMURA ,  Tetsuya KINEBUCHI

    IPC: G06T7/12 ,  G06T7/11 ,  G06T7/136

    Abstract: The present invention makes it possible to estimate, with high precision, a candidate region indicating each of multiple target objects included in an image. A parameter determination unit 11 determines parameters to be used when detecting a boundary line of an image 101 based on a ratio between a density of boundary lines included in an image 101 and a density of boundary lines in a region indicated by region information 102 indicating the region including at least one of the multiple target objects included in the image 101. A boundary line detection unit 12 detects the boundary line in the image 101 using the parameter. For each of the multiple target objects included in the image 101, the region estimation unit 13 estimates the candidate region of the target object based on the detected boundary line.

    ROAD BOUNDARY DETECTION DEVICE, ROAD BOUNDARY DETECTION METHOD, AND ROAD BOUNDARY DETECTION PROGRAM
    5.
    发明申请
    ROAD BOUNDARY DETECTION DEVICE, ROAD BOUNDARY DETECTION METHOD, AND ROAD BOUNDARY DETECTION PROGRAM 有权

    公开(公告)号：US20250052590A1

    公开(公告)日：2025-02-13

    申请号：US18717379

    申请日：2021-12-08

    Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

    Inventor： Taiga YOSHIDA ,  Yasuhiro YAO ,  Naoki ITO ,  Jun SHIMAMURA

    IPC: G01C21/00

    Abstract: A road boundary detection device is a road boundary detection device that acquires a set of lines corresponding to a road boundary from point cloud data as road boundary information. The road boundary detection device includes: a candidate point detection unit that detects each point of road boundary candidates corresponding to candidates of a road boundary from the point cloud data; a candidate point clustering unit that clusters each point of the road boundary candidates; an adjacent cluster reduction unit that reduces a cluster from a distribution of points in clusters in an adjacency relationship by using a predetermined cluster reduction method; a line fitting unit that fits one or more straight lines or curved lines to one or more of the clusters and output fitted lines as road boundary candidates; a line connecting unit that connects some of the fitted lines by using a predetermined analysis method; and an information output unit that outputs a calculated line as the road boundary information.

    LEARNING DEVICE, IDENTIFICATION DEVICE, LEARNING METHOD, IDENTIFICATION METHOD, LEARNING PROGRAM, AND IDENTIFICATION PROGRAM
    7.
    发明公开
    LEARNING DEVICE, IDENTIFICATION DEVICE, LEARNING METHOD, IDENTIFICATION METHOD, LEARNING PROGRAM, AND IDENTIFICATION PROGRAM 审中-公开

    公开(公告)号：US20230409964A1

    公开(公告)日：2023-12-21

    申请号：US18035090

    申请日：2020-11-05

    Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

    Inventor： Kana KURATA ,  Yasuhiro YAO ,  Naoki ITO ,  Shingo ANDO ,  Jun SHIMAMURA

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: An identification device acquires a plurality of identification target points by sampling a target point group that is a set of three-dimensional target points. The identification device calculates relative coordinates of a neighboring point of the identification target point with respect to the identification target point. The identification device inputs coordinates of the plurality of identification target points and relative coordinates of neighboring points with respect to each of the plurality of identification target points into a class label assigning learned model to acquire class labels of the plurality of identification target points and validity of the class labels with respect to the neighboring points for each of the plurality of identification target points. The identification device assigns the class labels to the plurality of identification target points, assigns the class labels to the neighboring points for each of the plurality of identification target points when the validity of the class label is included in a range determined by a predetermined threshold value, and identifies the class labels of the identification target point and the neighboring point.

    ACTION RECOGNITION LEARNING DEVICE, ACTION RECOGNITION LEARNING METHOD, ACTION RECOGNITION LEARNING DEVICE, AND PROGRAM
    8.
    发明申请
    ACTION RECOGNITION LEARNING DEVICE, ACTION RECOGNITION LEARNING METHOD, ACTION RECOGNITION LEARNING DEVICE, AND PROGRAM 有权

    公开(公告)号：US20220398868A1

    公开(公告)日：2022-12-15

    申请号：US17774113

    申请日：2020-10-30

    Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

    Inventor： Takashi HOSONO ,  Yongqing SUN ,  Kazuya HAYASE ,  Jun SHIMAMURA ,  Kiyohito SAWADA

    IPC: G06V40/20 ,  G06V10/774 ,  G06V10/24 ,  G06V10/77

    Abstract: The present invention makes it possible to cause an action recognizer capable of recognizing actions with high accuracy and with a small quantity of learning data to learn. An input unit 101 receives input of a learning video and an action label indicating an action of an object, a detection unit 102 detects a plurality of objects included in each frame image included in the learning video, a direction calculation unit 103 calculates a direction of a reference object, which is an object to be used as a reference among the plurality of detected objects, a normalization unit 104 normalizes the learning video so that a positional relationship between the reference object and another object becomes a predetermined relationship, and an optimization unit 106 optimizes parameters of an action recognizer to estimate the action of the object in the inputted video based on the action estimated by inputting the normalized learning video to the action recognizer and the action indicated by the action label.

    POSITION POSTURE ESTIMATION METHOD, POSITION POSTURE ESTIMATION DEVICE, AND PROGRAM
    9.
    发明申请
    POSITION POSTURE ESTIMATION METHOD, POSITION POSTURE ESTIMATION DEVICE, AND PROGRAM 有权

    公开(公告)号：US20250037402A1

    公开(公告)日：2025-01-30

    申请号：US18716509

    申请日：2021-12-06

    Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

    Inventor： Yasuhiro YAO ,  Kana KURATA ,  Shingo ANDO ,  Jun SHIMAMURA

    IPC: G06T19/20

    Abstract: A position and posture estimation device acquires three-dimensional point cloud data at each of times and position data at each of times, the three-dimensional point cloud data being measured every time a first time elapses, the position data being measured every time a second time longer than the first time elapses. The position and posture estimation device estimates a local position in a local coordinate system and a local posture in the local coordinate system. The position and posture estimation device estimates an estimated absolute position and an estimated absolute posture in an absolute coordinate system every time the position data is acquired. The position and posture estimation device generates provisional three-dimensional point cloud data in the absolute coordinate system every time the position data is acquired. The position and posture estimation device generates composite data obtained by integrating the provisional three-dimensional point cloud data and map point cloud data generated from three-dimensional point cloud data previously measured, and corrects the estimated absolute position and the estimated absolute posture to increase a degree of coincidence between the composite data and the map point cloud data.

    RECOGNIZER LEARNING DEVICE, RECOGNIZER LEARNING METHOD, AND RECOGNIZER LEARNING PROGRAM
    10.
    发明公开
    RECOGNIZER LEARNING DEVICE, RECOGNIZER LEARNING METHOD, AND RECOGNIZER LEARNING PROGRAM 审中-公开

    公开(公告)号：US20230245438A1

    公开(公告)日：2023-08-03

    申请号：US18012137

    申请日：2020-06-22

    Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

    Inventor： Kazuhiko MURASAKI ,  Shingo ANDO ,  Jun SHIMAMURA

    IPC: G06V10/82

    CPC classification number: G06V10/82

    Abstract: A training unit 24 performs leaning of a recognizer that recognizes labels of data based on a plurality of training data to which training labels are given. A score calculation unit 28 calculates a score output by the recognizer for each of the plurality of training data by using the trained recognizer. A threshold value determination unit 30 determines a threshold value for the score for determining the label, based on a shape of an ROC curve representing a correspondence between a true positive rate and a false positive rate, which is obtained based on the score calculated for each of the plurality of training data. A selection unit 32 selects the training data difficult to recognize by the recognizer based on the threshold value determined and the score calculated for each of the plurality of training data. The process of each unit described above is repeated until a predetermined iteration termination condition is satisfied.

Patent Agency Ranking