公开(公告)号：US20160350904A1

公开(公告)日：2016-12-01

申请号：US15232229

申请日：2016-08-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Guofeng Zhang ,  Hujun Bao ,  Kangkan Wang ,  Jiong Zhou

IPC: G06T7/00 ,  G06T17/00 ,  G06K9/62

CPC classification number: G06T7/85 ,  G06K9/6202 ,  G06T7/337 ,  G06T7/579 ,  G06T7/593 ,  G06T7/73 ,  G06T17/00 ,  G06T2207/10028 ,  G06T2207/20221 ,  G06T2207/30244

Abstract: Embodiments of the present disclosure disclose a static object reconstruction method and system that are applied to the field of graph and image processing technologies. In the embodiments of the present disclosure, when a static object reconstruction system does not obtain, by means of calculation, an extrinsic camera parameter in a preset time when calculating the extrinsic camera parameter based on a three-dimensional feature point, it indicates that depth data collected by a depth camera is lost or damaged, and a two-dimensional feature point is used to calculate the extrinsic camera parameter to implement alignment of point clouds of a frame of image according to the extrinsic camera parameter. In this way, a two-dimensional feature point and a three-dimensional feature point are mixed, which can implement that a static object can also be successfully reconstructed when depth data collected by a depth camera is lost or damaged.

Abstract translation: 本公开的实施例公开了应用于图形和图像处理技术领域的静态对象重建方法和系统。 在本公开的实施例中，当静态对象重建系统通过计算在基于三维特征点计算外在相机参数时在预设时间内获得外部相机参数时，其指示深度 由深度摄像机收集的数据丢失或损坏，并且使用二维特征点来计算外在摄像机参数，以根据外在摄像机参数来实现帧图像的点云的对准。 以这种方式，二维特征点和三维特征点被混合，这可以实现当深度相机收集的深度数据丢失或损坏时也可以成功地重建静态对象。

公开(公告)号：US09830701B2

公开(公告)日：2017-11-28

申请号：US15232229

申请日：2016-08-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Guofeng Zhang ,  Hujun Bao ,  Kangkan Wang ,  Jiong Zhou

IPC: G06K9/00 ,  G06T7/00 ,  G06T17/00 ,  G06K9/62 ,  G06T7/80 ,  G06T7/33 ,  G06T7/73 ,  G06T7/579 ,  G06T7/593

CPC classification number: G06T7/85 ,  G06K9/6202 ,  G06T7/337 ,  G06T7/579 ,  G06T7/593 ,  G06T7/73 ,  G06T17/00 ,  G06T2207/10028 ,  G06T2207/20221 ,  G06T2207/30244

Abstract: Embodiments of the present disclosure disclose a static object reconstruction method and system that are applied to the field of graph and image processing technologies. In the embodiments of the present disclosure, when a static object reconstruction system does not obtain, by means of calculation, an extrinsic camera parameter in a preset time when calculating the extrinsic camera parameter based on a three-dimensional feature point, it indicates that depth data collected by a depth camera is lost or damaged, and a two-dimensional feature point is used to calculate the extrinsic camera parameter to implement alignment of point clouds of a frame of image according to the extrinsic camera parameter. In this way, a two-dimensional feature point and a three-dimensional feature point are mixed, which can implement that a static object can also be successfully reconstructed when depth data collected by a depth camera is lost or damaged.

公开(公告)号：US20160379375A1

公开(公告)日：2016-12-29

申请号：US15263668

申请日：2016-09-13

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yadong Lu ,  Guofeng Zhang ,  Hujun Bao

IPC: G06T7/20 ,  G06K9/00 ,  G06T7/00

CPC classification number: G06T7/246 ,  G01C11/06 ,  G06K9/00201 ,  G06K9/00664 ,  G06T7/579 ,  G06T2207/10021 ,  G06T2207/30244

Abstract: A camera tracking method includes obtaining an image set of a current frame; separately extracting feature points of each image in the image set of the current frame; obtaining a matching feature point set of the image set according to a rule that scene depths of adjacent regions on an image are close to each other; separately estimating, a three-dimensional location of a scene point corresponding to each pair of matching feature points in a local coordinate system of the current frame and a three-dimensional location of the scene point in a local coordinate system of a next frame; estimating a motion parameter of the binocular camera on the next frame using invariance of center-of-mass coordinates to rigid transformation according to the three-dimensional location of the scene point corresponding to the matching feature points; and optimizing the motion parameter of the binocular camera on the next frame.

Abstract translation: 相机跟踪方法包括获得当前帧的图像集; 分别提取当前帧的图像集中的每个图像的特征点; 根据图像上的相邻区域的场景深度彼此接近的规则获得图像集合的匹配特征点集合; 单独估计与当前帧的局部坐标系中的每对匹配特征点对应的场景点的三维位置和下一帧的局部坐标系中场景点的三维位置; 根据对应于匹配特征点的场景点的三维位置，使用质心坐标的不变性到刚性变换来估计下一帧上的双目相机的运动参数; 并且在下一帧上优化双目相机的运动参数。

公开(公告)号：US10382737B2

公开(公告)日：2019-08-13

申请号：US15642171

申请日：2017-07-05

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xiaowei Yang ,  Guofeng Zhang ,  Yi He

IPC: H04N13/117 ,  H04N13/00 ,  G06T7/50 ,  G06T7/20 ,  G06T5/00 ,  G06T5/50 ,  H04N19/00 ,  H04N19/553 ,  G06T7/579

Abstract: An image processing method includes obtaining multiple video frames, where the multiple video frames are collected from a same scene at different angles and determining a depth map of each video frame according to corresponding pixels among the multiple video frames; supplementing background missing regions of the multiple video frames according to depth maps of the multiple video frames, to obtain supplemented video frames of the multiple video frames and depth maps of the multiple supplemented video frames. The method also includes generating an alpha image of each video frame according to an occlusion relationship between each of the multiple video frames and a supplemented video frame of each video frame in a background missing region and generating a browsing frame at a specified browsing angle according to the multiple video frames, the supplemented video frames of the multiple video frames, and alpha images of the multiple video frames.

公开(公告)号：US20190335155A1

公开(公告)日：2019-10-31

申请号：US16509846

申请日：2019-07-12

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xiaowei Yang ,  Guofeng Zhang ,  Yi He

IPC: H04N13/117 ,  G06T7/20 ,  H04N13/00 ,  G06T5/50 ,  G06T7/579 ,  H04N19/553 ,  G06T7/50 ,  G06T5/00 ,  H04N19/00

Abstract: An image processing method includes obtaining multiple video frames, where the multiple video frames are collected from a same scene at different angles and determining a depth map of each video frame according to corresponding pixels among the multiple video frames; supplementing background missing regions of the multiple video frames according to depth maps of the multiple video frames, to obtain supplemented video frames of the multiple video frames and depth maps of the multiple supplemented video frames. The method also includes generating an alpha image of each video frame according to an occlusion relationship between each of the multiple video frames and a supplemented video frame of each video frame in a background missing region and generating a browsing frame at a specified browsing angle according to the multiple video frames, the supplemented video frames of the multiple video frames, and alpha images of the multiple video frames.

公开(公告)号：US20170330375A1

公开(公告)日：2017-11-16

申请号：US15667917

申请日：2017-08-03

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zichong Chen ,  Guofeng Zhang ,  Kangkan Wang

IPC: G06T17/20

CPC classification number: G06T17/20 ,  G06T7/75 ,  G06T17/00 ,  G06T2200/04 ,  G06T2200/08 ,  G06T2207/10028 ,  G06T2207/30196 ,  G06T2215/16

Abstract: A data processing method and apparatus are provided. The method includes obtaining a first reconstruction model of a target object and dividing the first reconstruction model into M local blocks. Additionally, the method includes obtaining N target object sample alignment models, where each target object sample alignment model and the first reconstruction model have a same corresponding posture parameter, each target object sample alignment model includes M local blocks, and the ith local block of each target object sample alignment model is aligned with the ith local block of the first reconstruction model, where i is 1, . . . , or M. The method also includes approximating the N target object sample alignment models to the first reconstruction model, to determine a second reconstruction model that is of the target object and includes M local blocks.

公开(公告)号：US20170302901A1

公开(公告)日：2017-10-19

申请号：US15642171

申请日：2017-07-05

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xiaowei Yang ,  Guofeng Zhang ,  Yi He

IPC: H04N13/00 ,  G06T7/50 ,  G06T7/20

CPC classification number: H04N13/117 ,  G06T5/005 ,  G06T5/50 ,  G06T7/20 ,  G06T7/50 ,  G06T7/579 ,  G06T2207/10028 ,  G06T2207/20221 ,  H04N13/00 ,  H04N19/00 ,  H04N19/553 ,  H04N2213/005

Abstract: An image processing method includes obtaining multiple video frames, where the multiple video frames are collected from a same scene at different angles and determining a depth map of each video frame according to corresponding pixels among the multiple video frames; supplementing background missing regions of the multiple video frames according to depth maps of the multiple video frames, to obtain supplemented video frames of the multiple video frames and depth maps of the multiple supplemented video frames. The method also includes generating an alpha image of each video frame according to an occlusion relationship between each of the multiple video frames and a supplemented video frame of each video frame in a background missing region and generating a browsing frame at a specified browsing angle according to the multiple video frames, the supplemented video frames of the multiple video frames, and alpha images of the multiple video frames.