Residual error mitigation in multiview calibration

    公开(公告)号:US10666926B1

    公开(公告)日:2020-05-26

    申请号:US16038225

    申请日:2018-07-18

    Abstract: Multiview calibration is essential for accurate three-dimensional computation. However, multiview calibration can not be accurate enough because of the tolerances required in some of the intrinsic and extrinsic parameters that are associated with the calibration process, along with fundamental imperfections that are associated with the manufacturing and assembly process itself. As a result, residual error in calibration is left over, with no known methods to mitigate such errors. Residual error mitigation is presented in this work to address the shortcomings that are associated with calibration of multiview camera systems. Residual error mitigation may be performed inline with a given calibration approach, or may be presented as a secondary processing step that is more application specific. Residual error mitigation aims at modifying the original parameters that have been estimated during an initial calibration process. These new, modified parameters are then used for triangulation and depth estimation of scene information. This approach also resolves parameter tolerances that are either too cumbersome to measure, or otherwise impossible to measure for practical stereo and multiview camera production and calibration applications.

    Coarse to fine calibration parameter validation and temperature mitigation

    公开(公告)号:US10607370B1

    公开(公告)日:2020-03-31

    申请号:US16177360

    申请日:2018-10-31

    Abstract: A method and system for calibration parameter validation. The method includes performing a camera calibration generating a calibration result, applying a coarse pass-fail criteria to the calibration result and rejecting the camera if the calibration result does not pass the coarse pass fail-criteria. The method further includes applying a fine pass-fail criteria based upon at least information stored at a central repository to the calibration result if the calibration result passes the coarse pass-fail criteria, rejecting the camera if the calibration result does not pass the fine pass fail-criteria, accepting the camera if the calibration result passes the fine pass fail-criteria, and entering the calibration result into the central repository. The information stored at the central repository includes key performance indicator/key performance metric information for one or more measured parameters of the calibration result.

    Method and Apparatus for Enhancing Stereo Vision Through Image Segmentation
    25.
    发明申请
    Method and Apparatus for Enhancing Stereo Vision Through Image Segmentation 审中-公开
    通过图像分割增强立体视觉的方法和装置

    公开(公告)号:US20140205183A1

    公开(公告)日:2014-07-24

    申请号:US14226858

    申请日:2014-03-27

    Abstract: A method and apparatus for segmenting an image are provided. The method may include the steps of clustering pixels from one of a plurality of images into one or more segments, determining one or more unstable segments changing by more than a predetermined threshold from a prior of the plurality of images, determining one or more segments transitioning from an unstable to a stable segment, determining depth for one or more of the one or more segments that have changed by more than the predetermined threshold, determining depth for one or more of the one or more transitioning segments, and combining the determined depth for the one or more unstable segments and the one or more transitioning segments with a predetermined depth of all segments changing less than the predetermined threshold from the prior of the plurality of images.

    Abstract translation: 提供了一种用于分割图像的方法和装置。 该方法可以包括以下步骤:将来自多个图像中的一个图像的像素聚类成一个或多个片段,从多个图像中的先前确定一个或多个从不同于预定阈值改变的不稳定片段,确定一个或多个片段转换 从不稳定段到稳定段,确定已经改变超过预定阈值的一个或多个段中的一个或多个的深度,确定一个或多个过渡段中的一个或多个的深度,以及将确定的深度合并 所述一个或多个不稳定段和所述一个或多个所有段的预定深度从所述多个图像中的先前变化小于所述预定阈值的一个或多个过渡段。

    Apparatus and method for segmenting an image

    公开(公告)号:US10586334B2

    公开(公告)日:2020-03-10

    申请号:US14148761

    申请日:2014-01-07

    Abstract: A method and system for segmenting a plurality of images. The method comprises the steps of segmenting the image through a novel clustering technique that is, generating a composite depth map including temporally stable segments of the image as well as segments in subsequent images that have changed. These changes may be determined by determining one or more differences between the temporally stable depth map and segments included in one or more subsequent frames. Thereafter, the portions of the one or more subsequent frames that include segments including changes from their corresponding segments in the temporally stable depth map are processed and are combined with the segments from the temporally stable depth map to compute their associated disparities in one or more subsequent frames. The images may include a pair of stereo images acquired through a stereo camera system at a substantially similar time.

Patent Agency Ranking