中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

38 records (took 0.019 seconds)

    METHOD AND APPARATUS FOR RECOGNIZING OBJECT
    11.
    发明申请
    METHOD AND APPARATUS FOR RECOGNIZING OBJECT 有权
    用于识别对象的方法和装置

    公开(公告)号：US20160203610A1

    公开(公告)日：2016-07-14

    申请号：US14714437

    申请日：2015-05-18

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Kyoobin LEE ,  Keun Joo PARK ,  Eric Hyunsurk RYU ,  Jun Haeng LEE

    IPC: G06T7/00 ,  G06K9/00 ,  G06K9/46 ,  G06T7/20

    CPC classification number: G06K9/00221 ,  G06K9/00255 ,  G06K9/00355 ,  G06K9/00973

    Abstract: A method of recognizing an object includes controlling an event-based vision sensor to perform sampling in a first mode and to output first event signals based on the sampling in the first mode, determining whether object recognition is to be performed based on the first event signals, controlling the event-based vision sensor to perform sampling in a second mode and to output second event signals based on the sampling in the second mode in response to the determining indicating that the object recognition is to be performed, and performing the object recognition based on the second event signals.

    Abstract translation: 识别对象的方法包括：控制基于事件的视觉传感器以第一模式进行采样，并且基于第一模式中的采样来输出第一事件信号，基于第一事件信号来确定是否要执行对象识别 控制基于事件的视觉传感器以在第二模式中执行采样，并且响应于指示将要执行对象识别的确定，基于第二模式中的采样来输出第二事件信号，并且基于 关于第二个事件信号。

    INTERFACING APPARATUS AND USER INPUT PROCESSING METHOD
    13.
    发明申请
    INTERFACING APPARATUS AND USER INPUT PROCESSING METHOD 审中-公开
    接口设备和用户输入处理方法

    公开(公告)号：US20160011654A1

    公开(公告)日：2016-01-14

    申请号：US14677084

    申请日：2015-04-02

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Jun Haeng LEE ,  Jun Seok KIM ,  Chang Woo SHIN ,  Eric Hyun-surk RYU

    IPC: G06F3/01 ,  G06F3/00 ,  G06F3/16

    CPC classification number: G06N3/063 ,  G06N3/049

    Abstract: An interfacing apparatus and a user input processing method are provided. The interfacing apparatus may group event generation elements and output an address of a group in which an event occurs based on a generated group event signal. The interfacing apparatus may include a grouper configured to generate a group event signal in which a plurality of event generation elements corresponding to a plurality of pixels in at least one event sensor are grouped based on one or more events occurring with respect to the plurality of pixels, and an interface configured to output an address of the group of the plurality of event generation elements in which the one or more event occurs based on the generated group event signal

    Abstract translation: 提供了一种接口装置和用户输入处理方法。 接口装置可以对事件生成元素进行分组，并且基于生成的组事件信号来输出事件发生的组的地址。 接口装置可以包括：一个分组器，被配置为基于一个或多个相对于多个像素发生的事件来生成组事件信号，其中与至少一个事件传感器中的多个像素相对应的多个事件生成元素被分组 以及接口，被配置为基于所生成的组事件信号来输出其中发生所述一个或多个事件的所述多个事件生成元素的组的地址

    EVENT-BASED IMAGE PROCESSING APPARATUS AND METHOD
    16.
    发明申请
    EVENT-BASED IMAGE PROCESSING APPARATUS AND METHOD 有权
    基于事件的图像处理设备和方法

    公开(公告)号：US20130335595A1

    公开(公告)日：2013-12-19

    申请号：US13921808

    申请日：2013-06-19

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Kyoobin LEE ,  Hyun Surk RYU ,  Jun Haeng LEE ,  Keun Joo PARK ,  Chang-Woo SHIN ,  Jooyeon WOO

    IPC: H04N5/232

    CPC classification number: H04N5/23229 ,  G06T7/20 ,  G06T7/269 ,  G06T2207/10016

    Abstract: Provided is an event-based image processing apparatus and method, the apparatus including a sensor which senses occurrences of a predetermined event in a plurality of image pixels and which outputs an event signal in response to the sensed occurrences, a time stamp unit which generates time stamp information by mapping a pixel corresponding to the event signals to a time at which the event signals are output from the sensor, and an optical flow generator which generates an optical flow based on the time stamp information in response to the outputting of the event signals.

    Abstract translation: 提供了一种基于事件的图像处理装置和方法，该装置包括：感测多个图像像素中的预定事件的发生并且响应于感测到的事件而输出事件信号的传感器，产生时间的时间戳单元 通过将与事件信号相对应的像素映射到从传感器输出事件信号的时间的印模信息，以及响应于事件信号的输出而基于时间戳信息产生光流的光流发生器 。

    DEEP LEARNING DEVICE AND SYSTEM INCLUDING THE SAME
    18.
    发明申请
    DEEP LEARNING DEVICE AND SYSTEM INCLUDING THE SAME 有权

    公开(公告)号：US20220374680A1

    公开(公告)日：2022-11-24

    申请号：US17529439

    申请日：2021-11-18

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Young Jae KIM ,  Kae Weon YOU ,  Ji Ung LEE ,  Jun Haeng LEE ,  Kyoung Hoon KANG ,  Young Hak LEE

    IPC: G06N3/04

    Abstract: A deep learning device and system including the same is provided. The deep learning device comprising processing circuitry configured to determine whether a received image is abnormal using an anomaly detection model; merge at least some vectors extracted from the anomaly detection model; input, to a probability approximation model, principal components generated by a principal component analysis (PCA) to detect whether out of distribution (OOD) occurs in data of the received image; store a result of the determinations; and extract at least some the data in which the OOD occurs, as target labeling, using a target labeling extraction model when a rate of the data in which the OOD occurs is greater than or equal to a threshold value, wherein the anomaly detection model determines whether the received image is abnormal using the target labeling.

    INTERFACE NEURAL NETWORK
    19.
    发明申请
    INTERFACE NEURAL NETWORK 有权

    公开(公告)号：US20210056394A1

    公开(公告)日：2021-02-25

    申请号：US17091837

    申请日：2020-11-06

    Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  UNIVERSITAET ZUERICH

    Inventor： Jun Haeng LEE ,  Tobi DELBRUCK ,  Eric Hyunsurk RYU

    IPC: G06N3/04

    Abstract: An operation method of a neural network, a training method, and a signal processing apparatus are provided. The operation method includes receiving an output signal from a first neural network, and converting a first feature included in the output signal to a second feature configured to be input to a second neural network, based on a conversion rule controlling conversion between a feature to be output from the first neural network and a feature to be input to the second neural network. The operation method further includes generating an input signal to be input to the second neural network, based on the second feature, and transmitting the input signal to the second neural network.

Patent Agency Ranking