RECOGNITION APPARATUS BASED ON NEURAL NETWORK AND METHOD OF TRAINING NEURAL NETWORK

    公开(公告)号:US20170213129A1

    公开(公告)日:2017-07-27

    申请号:US15195302

    申请日:2016-06-28

    Inventor: Jun Haeng LEE

    CPC classification number: G06N3/08 G06N3/04 G06N3/049 G06N3/084

    Abstract: A recognition apparatus and a training method are provided. The recognition apparatus includes a memory configured to store a neural network including a previous layer of neurons, and a current layer of neurons that are activated based on first synaptic signals and second synaptic signals, the first synaptic signals being input from the previous layer, and the second synaptic signals being input from the current layer. The recognition apparatus further includes a processor configured to generate a recognition result based on the neural network. An activation neuron among the neurons of the current layer generates a first synaptic signal to excite or inhibit neurons of a next layer, and generates a second synaptic signal to inhibit neurons other than the activation neuron in the current layer.

    DEVICE AND METHOD TO PROCESS DATA IN PARALLEL
    22.
    发明申请
    DEVICE AND METHOD TO PROCESS DATA IN PARALLEL 有权
    并行处理数据的设备和方法

    公开(公告)号:US20170011006A1

    公开(公告)日:2017-01-12

    申请号:US14989851

    申请日:2016-01-07

    CPC classification number: G06F17/15 G06F7/5443 G06F17/153 G06N3/00

    Abstract: A method and apparatus for processing data are provided. The processor includes an input buffer, a data extractor, a multiplier, and an adder. The input buffer receives data and stores the data. The data extractor extracts kernel data corresponding to a kernel in the data from the input buffer. The multiplier multiplies the extracted kernel data by a convolution coefficient. The adder calculates a sum of multiplication results from the multiplier.

    Abstract translation: 提供了一种用于处理数据的方法和装置。 处理器包括输入缓冲器,数据提取器,乘法器和加法器。 输入缓冲区接收数据并存储数据。 数据提取器从输入缓冲器中提取与数据相对应的内核数据。 乘法器将提取的内核数据乘以卷积系数。 加法器计算乘法器的相乘结果之和。

    MOTION ANALYSIS METHOD AND APPARATUS
    24.
    发明申请
    MOTION ANALYSIS METHOD AND APPARATUS 有权
    运动分析方法和装置

    公开(公告)号:US20160140731A1

    公开(公告)日:2016-05-19

    申请号:US14699546

    申请日:2015-04-29

    CPC classification number: G06T7/593 G06K9/00335

    Abstract: A method and apparatus for analyzing a motion based on depth information are provided. The method includes: receiving event signals from a first vision sensor configured to generate at least one event signal by sensing at least a portion of an object in which a motion occurs; receiving a current frame from a second vision sensor configured to time-synchronously capture the object; synchronizing the received event signals and the received current frame; and obtaining depth information of the object based on the synchronized event signals and current frame.

    Abstract translation: 提供了一种基于深度信息分析运动的方法和装置。 该方法包括:从第一视觉传感器接收事件信号,该第一视觉传感器经配置以通过感测发生运动的对象的至少一部分来生成至少一个事件信号; 从被配置为时间同步地捕获对象的第二视觉传感器接收当前帧; 同步所接收的事件信号和接收到的当前帧; 并且基于同步的事件信号和当前帧来获得对象的深度信息。

    APPARATUS AND METHOD FOR ANALYZING IMAGE INCLUDING EVENT INFORMATION
    25.
    发明申请
    APPARATUS AND METHOD FOR ANALYZING IMAGE INCLUDING EVENT INFORMATION 有权
    用于分析包括事件信息的图像的装置和方法

    公开(公告)号:US20150030204A1

    公开(公告)日:2015-01-29

    申请号:US14331405

    申请日:2014-07-15

    CPC classification number: G06T7/246 G06T7/55 G06T2207/10004

    Abstract: An apparatus and method for analyzing an image including event information for determining a pattern of at least one pixel group corresponding to event information included in an input image, and analyzes at least one of an appearance of an object and a motion of the object, based on the at least one pattern.

    Abstract translation: 一种用于分析包括用于确定与包括在输入图像中的事件信息相对应的至少一个像素组的图案的事件信息的图像的装置和方法,并且基于对象的外观和对象的运动来分析至少一个 在至少一个图案上。

    IMAGE ADJUSTMENT APPARATUS AND IMAGE SENSOR FOR SYNCHRONOUS IMAGE AND ASYNCHRONOUS IMAGE
    26.
    发明申请
    IMAGE ADJUSTMENT APPARATUS AND IMAGE SENSOR FOR SYNCHRONOUS IMAGE AND ASYNCHRONOUS IMAGE 审中-公开
    用于同步图像和异常图像的图像调整装置和图像传感器

    公开(公告)号:US20140368712A1

    公开(公告)日:2014-12-18

    申请号:US14299599

    申请日:2014-06-09

    CPC classification number: H04N5/3765 H04N5/2258

    Abstract: Disclosed is an image adjustment apparatus including a receiver which is configured to receive a first input image of an object which is time-synchronously captured and a second input image in which a motion event of the object is sensed time-asynchronously, and an adjuster which is configured to adjust the first input image and the second input image.

    Abstract translation: 公开了一种图像调整装置,包括:接收器,其被配置为接收时间同步捕获的对象的第一输入图像;以及第二输入图像,其中对象的运动事件被异步地感测;以及调节器, 被配置为调整第一输入图像和第二输入图像。

    METHOD AND APPARATUS FOR MOTION RECOGNITION
    27.
    发明申请
    METHOD AND APPARATUS FOR MOTION RECOGNITION 审中-公开
    运动识别的方法和装置

    公开(公告)号:US20140184498A1

    公开(公告)日:2014-07-03

    申请号:US14199164

    申请日:2014-03-06

    CPC classification number: G06F3/017 G06K9/00335 G06T7/254 G06T2200/28

    Abstract: A motion recognizing apparatus and method are provided. According to an aspect, a motion recognizing apparatus may include: an optical sensor configured to sense at least a portion of a subject where a motion occurs and to output one or more events in response thereto; a motion tracing unit configured to trace a motion locus of the portion where the motion occurs based on the one or more outputted events; and a motion pattern determining unit configured to determine a motion pattern of the portion where the motion occurs based on the traced motion locus.

    Abstract translation: 提供了一种运动识别装置和方法。 根据一方面,运动识别装置可以包括:光学传感器,被配置为感测发生运动的对象的至少一部分并且响应于此而输出一个或多个事件; 运动跟踪单元,被配置为基于所述一个或多个输出事件跟踪所述运动发生的部分的运动轨迹; 以及运动图案确定单元,被配置为基于跟踪的运动轨迹来确定运动发生的部分的运动模式。

    METHOD AND DEVICE FOR PREDICTING DEFECTS

    公开(公告)号:US20230054159A1

    公开(公告)日:2023-02-23

    申请号:US17748241

    申请日:2022-05-19

    Abstract: A method and device for predicting a defect. The method includes determining a sequence between a plurality of sub-models by modeling a production process into the plurality of sub-models, mapping production process data into each of the plurality of sub-models, determining, by a corresponding sub-model, output data comprising defect information on a potential defect occurring in a corresponding step, for each of the plurality of sub-models, predicting information associated with a defect in the production process based on the output data corresponding to each of the plurality of sub-models, and inputting the output data of each of the sub-models to a subsequent sub-model of the corresponding sub-model, based on the sequence.

Patent Agency Ranking