APPARATUS AND METHOD OF FIVE DIMENSIONAL (5D) VIDEO STABILIZATION WITH CAMERA AND GYROSCOPE FUSION

    公开(公告)号:US20190147606A1

    公开(公告)日:2019-05-16

    申请号:US16016232

    申请日:2018-06-22

    Abstract: An apparatus and method of five dimensional (5D) video stabilization with camera and gyroscope fusion are herein disclosed. According to one embodiment, an apparatus includes a feature matcher configured to receive an image sequence and determine feature pairs in the image sequence; a residual two-dimensional (2D) translation estimator connected to the feature matcher and configured to determine a raw 2D translation path; a residual 2D translation smoother connected to the residual 2D translation estimator and configured to determine a 2D smoothed translation path; a distortion calculator connected to the residual 2D translation estimator and the residual 2D translation smoother and configured to determine a distortion grid; and a distortion compensator connected to the distortion calculator and configured to compensate for distortion in the image sequence.

    APPARATUS AND METHOD FOR MODELING RANDOM PROCESS USING REDUCED LENGTH LEAST-SQUARES AUTOREGRESSIVE PARAMETER ESTIMATION

    公开(公告)号:US20180196906A1

    公开(公告)日:2018-07-12

    申请号:US15465181

    申请日:2017-03-21

    CPC classification number: G06F17/5036 G06F17/5072 G06F17/5081

    Abstract: An apparatus and method for modelling a random process using reduced length least-squares autoregressive parameter estimation is herein disclosed. The apparatus includes an autocorrelation processor, configured to generate or estimate autocorrelations of length m for a stochastic process, where m is an integer; and a least-squares (LS) estimation processor connected to the autocorrelation processor and configured to model the stochastic process by estimating pth order autoregressive (AR) parameters using LS regression, where p is an integer much less than m. The method includes generating, by an autocorrelation processor, autocorrelations of length m for a stochastic process, where m is an integer; and modelling the stochastic process, by a least-squares estimation processor, by estimating pth order autoregressive (AR) parameters by least-squares (LS) regression, where p is an integer much less than m.

Patent Agency Ranking