LOCAL DETECTION MODEL (LDM) FOR RECURSIVE MOTION ESTIMATION
    3.
    发明申请
    LOCAL DETECTION MODEL (LDM) FOR RECURSIVE MOTION ESTIMATION 有权
    局部检测模型(LDM)用于回归运动估计

    公开(公告)号:US20140321559A1

    公开(公告)日:2014-10-30

    申请号:US14224206

    申请日:2014-03-25

    Abstract: The present disclosure relates to a method for improving an estimation process, comprising providing an image; detecting a failure area within said image to obtain a failure area map; obtaining a motion or disparity estimation map containing estimation vectors determined in an estimation process; providing a local direction model, LDM, map comprising LDM vectors determined on the basis of said estimated vectors and said detected failure area, and adjusting said estimation process dependent on the local direction model map.

    Abstract translation: 本公开涉及一种用于改进估计处理的方法,包括提供图像; 检测所述图像内的故障区域以获得故障区域图; 获得包含在估计过程中确定的估计向量的运动或视差估计图; 提供局部方向模型,LDM,包括基于所述估计向量确定的LDM向量和所述检测到的故障区域的地图,以及根据局部方向模型图来调整所述估计处理。

    CALIBRATION IN THE LOOP
    6.
    发明申请
    CALIBRATION IN THE LOOP 审中-公开
    循环中的校准

    公开(公告)号:US20140043447A1

    公开(公告)日:2014-02-13

    申请号:US13933643

    申请日:2013-07-02

    Abstract: Method for iteratively calibrating a disparity estimation process generating a disparity estimation map relating to a 3D image which consists of at least a right and a left image, the method comprising: estimating a left-to-right image disparity map of a 3D image in horizontal and vertical direction, estimating a right-to-left image disparity map of the 3D image in horizontal and vertical direction, determining a misalignment value between the left and right images on the basis of the disparity maps, feeding back the misalignment value as to be considered in the next estimating the disparity maps of a next 3D image, and repeating the method for the next 3D image to iteratively calibrate the disparity estimation process.

    Abstract translation: 一种用于迭代地校准视差估计处理的方法,所述差异估计处理产生与由至少右和左图像组成的3D图像相关的视差估计图,所述方法包括:估计水平的3D图像的从左到右的图像视差图 垂直方向,估计水平和垂直方向上的3D图像的从右到左图像视差图,基于视差图确定左图像和右图像之间的未对准值,将未对准值反馈为 在下一次估计下一个3D图像的视差图中考虑,并且重复下一个3D图像的方法以迭代地校准视差估计过程。

Patent Agency Ranking