EVENT-BASED IMAGE FEATURE EXTRACTION
    21.
    发明申请

    公开(公告)号:US20180357504A1

    公开(公告)日:2018-12-13

    申请号:US15621040

    申请日:2017-06-13

    CPC classification number: G06K9/4609 G06K9/4642

    Abstract: Event-based image feature extraction includes reducing an accumulated magnitude of a leaky integrate and fire (LIF) neuron based on a difference between a current time and a previous time; receiving an event input from a dynamic vision sensor (DVS) pixel at the current time; weighting the received input; adding the weighted input to the reduced magnitude to form an accumulated magnitude of the LIF neuron at the current time; and, if the accumulated magnitude reaches a threshold, firing the neuron and decreasing the accumulated magnitude.

    Large radius edge-preserving low-pass filtering
    22.
    发明授权
    Large radius edge-preserving low-pass filtering 有权
    大半径边缘保留低通滤波

    公开(公告)号:US09275446B2

    公开(公告)日:2016-03-01

    申请号:US14054087

    申请日:2013-10-15

    Abstract: A method of large-radius edge-preserving low-pass filtering is performed on a digital signal having data points. The method includes computing a weighted average of a signal layer at vertices spaced a distance apart such that an amount of the vertices is less than an amount of the data points and producing, for each of the data points, a large-radius edge-preserving low-pass filtered signal based on the weighted average of the signal layer at vertices neighboring the data point.

    Abstract translation: 对具有数据点的数字信号执行大半径边缘保留低通滤波的方法。 该方法包括计算在间隔开距离的顶点处的信号层的加权平均值,使得顶点的量小于数据点的数量,并且对于每个数据点产生大半径边缘保留 基于邻近数据点的顶点处的信号层的加权平均值的低通滤波信号。

Patent Agency Ranking