Depth sensing apparatus with self-calibration and self-calibration method thereof

    公开(公告)号:US10742961B2

    公开(公告)日:2020-08-11

    申请号:US15255164

    申请日:2016-09-02

    Abstract: A depth sensing apparatus with self-calibration and a self-calibration method thereof are provided. The depth sensing apparatus includes a projection apparatus, an image capturing apparatus and a calibration module. The projection apparatus projects a calibration pattern and a depth computation pattern to a reference plane based on a predefined calibration pattern and a predefined depth computation pattern. The image capturing apparatus captures an image including the calibration pattern and the depth computation pattern. The calibration module coupled to the image capturing apparatus adjusts apparatus parameters of the depth sensing apparatus to calibrate a depth computation deviation according to the calibration pattern of the image, the predefined calibration pattern and a predefined lookup table corresponding to the predefined calibration pattern.

    System and method for computing relative rotation and relative translation of back-to-back cameras

    公开(公告)号:US12075024B2

    公开(公告)日:2024-08-27

    申请号:US17556401

    申请日:2021-12-20

    Inventor: Te-Mei Wang

    CPC classification number: H04N17/002 G06T1/0007 G06T3/02 G06T7/80

    Abstract: A system and a method for computing the relative rotation and the relative translation of back-to-back cameras comprise: a fixed mode and an adjustment mode. In the fixed mode, a reversible external camera is installed next to the back-to-back cameras, the external camera is flipped to shoot a calibration pattern from different positions and angles, the intrinsic and extrinsic parameters of each camera are computed, and then a reverse calculation is performed on the extrinsic parameters, as such the amount of translation and rotation of the back-to-back cameras are obtained. When the relative angle of the back-to-back cameras changes, the angle is automatically detected and the extrinsic parameters of the camera computed at the fixed mode is modified, and then the reverse calculation is performed on the extrinsic parameters to adjust the amount of translation and rotation of the back-to-back cameras.

    DEPTH CAMERA CALIBRATION DEVICE AND METHOD THEREOF

    公开(公告)号:US20200184684A1

    公开(公告)日:2020-06-11

    申请号:US16233262

    申请日:2018-12-27

    Abstract: A depth camera calibration device and a method thereof are provided. The method comprises: disabling a projection function of a camera and photographing surface planes to obtain a first image; enabling the projection function of the camera and photographing the surface planes to obtain a second image, and a positional relationship between the camera and a calibration plate assembly remaining unchanged when obtaining the first image and the second image; and obtaining parameters of the camera by cropping an image boundary, calculating positions of characteristic points, reading a projection pattern, calculating positions of corresponding points and excluding abnormal points according to the first image and the second image.

    Hole filling method for multi-view disparity maps
    7.
    发明授权
    Hole filling method for multi-view disparity maps 有权
    多视差视差图的填孔方法

    公开(公告)号:US09076249B2

    公开(公告)日:2015-07-07

    申请号:US13789693

    申请日:2013-03-08

    CPC classification number: G06T15/00 H04N13/00 H04N13/111

    Abstract: A hole filling method for multi-view disparity maps is provided. At least one disparity map is respectively captured as a plurality of known views among a plurality of views for capturing an object. As for a plurality of virtual views among the views excluding the at least one known view, disparity maps of the virtual views are synthesized by sequentially using the disparity maps of the known views according to a distance of a virtual camera position or a transformed angle between each virtual view and each known view. Hole filling information of the disparity maps of other virtual views having the distances or the transformed angles smaller than that of the virtual view is used to fill holes in the synthesized disparity maps of the virtual views.

    Abstract translation: 提供了一种用于多视角视差图的孔填充方法。 在用于捕获对象的多个视图中,分别捕获至少一个视差图作为多个已知视图。 对于除了至少一个已知视图之外的视图中的多个虚拟视图,虚拟视图的视差图是通过依照虚拟相机位置的距离或者虚拟相机位置的距离或者在 每个虚拟视图和每个已知视图。 使用具有小于虚拟视图的距离或变换角度的其他虚拟视图的视差图的填孔信息来填充虚拟视图的合成视差图中的空洞。

    IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD
    8.
    发明申请
    IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD 有权
    图像处理装置和图像处理方法

    公开(公告)号:US20130251240A1

    公开(公告)日:2013-09-26

    申请号:US13726821

    申请日:2012-12-26

    Abstract: An image processing apparatus includes a determination unit, a search unit, a weight assignment unit and a filling unit. The determination unit determines whether a hole is surrounded by the foreground in a disparity map or a depth map. The search unit searches for multiple relative backgrounds along multiple directions when the hole is surrounded by the foreground. The weight assignment unit respectively assigns weights to the relative backgrounds. The filling unit selects an extremum from the weights, and fills the hole according to the relative background corresponding to the extremum.

    Abstract translation: 图像处理装置包括确定单元,搜索单元,重量分配单元和填充单元。 确定单元确定孔在视差图或深度图中是否被前景包围。 当孔被前景包围时,搜索单元沿着多个方向搜索多个相对背景。 权重分配单元分配权重给相对背景。 填充单元从重物中选择极值,并根据与极值相对应的相对背景填充孔。

    Depth camera calibration device and method thereof

    公开(公告)号:US10977829B2

    公开(公告)日:2021-04-13

    申请号:US16233262

    申请日:2018-12-27

    Abstract: A depth camera calibration device and a method thereof are provided. The method comprises: disabling a projection function of a camera and photographing surface planes to obtain a first image; enabling the projection function of the camera and photographing the surface planes to obtain a second image, and a positional relationship between the camera and a calibration plate assembly remaining unchanged when obtaining the first image and the second image; and obtaining parameters of the camera by cropping an image boundary, calculating positions of characteristic points, reading a projection pattern, calculating positions of corresponding points and excluding abnormal points according to the first image and the second image.

Patent Agency Ranking