公开(公告)号：WO2021146035A1

公开(公告)日：2021-07-22

申请号：PCT/US2020/066485

申请日：2020-12-21

Applicant: MAGIC LEAP, INC. ,  GROSSMAN, Etienne Gregoire ,  JOHNSON, Michael Robert ,  ZHAO, Wenyi ,  SHAH, Nukul Sanjay ,  HUANG, Po-Kang

Inventor： EDWIN, Lionel Ernest ,  MILLER, Samuel A. ,  CLARK, Brian

IPC: G02B27/01 ,  G06F3/01 ,  G02B2027/0138 ,  G02B2027/014 ,  G02B2027/0178 ,  G02B27/0172 ,  G06T2207/10024 ,  G06T3/0068 ,  G06T5/006 ,  H04N13/344 ,  H04N5/2253

Abstract: The systems and methods described can include approaches to calibrate head-mounted displays for improved viewing experiences. Some methods include receiving data of a first target image associated with an undeformed state of a first eyepiece of a head-mounted display device; receiving data of a first captured image associated with deformed state of the first eyepiece of the head-mounted display device; determining a first transformation that maps the first captured image to the image; and applying the first transformation to a subsequent image for viewing on the first eyepiece of the head-mounted display device.

公开(公告)号：WO2006083297A2

公开(公告)日：2006-08-10

申请号：PCT/US2005020748

申请日：2005-06-10

Applicant: SARNOFF CORP ,  ZHAO WENYI ,  NISTER DAVID ,  HSU STEPHEN CHARLES

Inventor： ZHAO WENYI ,  NISTER DAVID ,  HSU STEPHEN CHARLES

IPC: G06K9/36

CPC classification number: G06K9/00214 ,  G06T7/30 ,  G06T7/33 ,  G06T7/579 ,  G06T7/74 ,  G06T7/80 ,  G06T2200/08 ,  G06T2207/10032 ,  G06T2207/30184 ,  G06T2207/30241 ,  G06T2207/30244

Abstract: A method and apparatus for performing two-dimensional video alignment onto three-dimensional point clouds. The system recovers camera pose from camera video, determines a depth map, converts the depth map to a Euclidean video point cloud, and registers two-dimensional video to the three-dimensional point clouds.

Abstract translation: 一种用于在三维点云上执行二维视频对准的方法和装置。 系统从摄像机视频恢复摄像机姿态，确定深度图，将深度图转换为欧几里德视频点云，并将二维视频注册到三维点云。

公开(公告)号：WO2006083297A3

公开(公告)日：2006-08-10

申请号：PCT/US2005/020748

申请日：2005-06-10

Applicant: SARNOFF CORPORATION ,  ZHAO, Wenyi ,  NISTER, David ,  HSU, Stephen, Charles

Inventor： ZHAO, Wenyi ,  NISTER, David ,  HSU, Stephen, Charles

IPC: G06K9/00

Abstract: A method and apparatus for performing two-dimensional video alignment onto three-dimensional point clouds. The system recovers camera pose from camera video, determines a depth map, converts the depth map to a Euclidean video point cloud, and registers two-dimensional video to the three-dimensional point clouds.

公开(公告)号：WO2005024698A2

公开(公告)日：2005-03-17

申请号：PCT/US2004/028871

申请日：2004-09-07

Applicant: SARNOFF CORPORATION ,  HANNA, Keith ,  TAN, Yi ,  ZHAO, Wenyi

Inventor： HANNA, Keith ,  TAN, Yi ,  ZHAO, Wenyi

IPC: G06K

CPC classification number: H04N7/181 ,  G06K9/00604

Abstract: The method and apparatus for performing iris recognition from at least one image is disclosed. A plurality of cameras is used to capture a plurality of images where at least one of the images contains a region having at least a portion of an iris. At least one of the plurality of images is then processed to perform iris recognition.

Abstract translation: 公开了从至少一个图像执行虹膜识别的方法和装置。 使用多个照相机来拍摄多个图像，其中至少一个图像包含具有至少一部分虹膜的区域。 然后处理多个图像中的至少一个以执行虹膜识别。

公开(公告)号：WO2005024698A3

公开(公告)日：2005-11-24

申请号：PCT/US2004028871

申请日：2004-09-07

Applicant: SARNOFF CORP ,  HANNA KEITH ,  TAN YI ,  ZHAO WENYI

Inventor： HANNA KEITH ,  TAN YI ,  ZHAO WENYI

IPC: G06K20060101 ,  G06K9/00 ,  G06K9/32 ,  G06K9/36 ,  H04N7/18

CPC classification number: H04N7/181 ,  G06K9/00604

Abstract: The method and apparatus for performing iris recognition from at least one image is disclosed. A plurality of cameras (105, 115) are used to capture a plurality of images where at least one of the images contains a region having at least a portion of an iris. At least one of the plurality of images is then processed to perform iris recognition (120, 145).

Abstract translation: 公开了从至少一个图像执行虹膜识别的方法和装置。 多个照相机（105,115）用于拍摄多个图像，其中至少一个图像包含具有至少一部分虹膜的区域。 然后处理多个图像中的至少一个以执行虹膜识别（120,145）。

公开(公告)号：WO9952059A3

公开(公告)日：2000-08-31

申请号：PCT/IB9900975

申请日：1999-04-06

Applicant: LG ELECTRONICS INC ,  ZHAO WENYI

Inventor： ZHAO WENYI

IPC: G06K9/70 ,  G06K9/00 ,  G06K9/68 ,  G06F17/30

CPC classification number: G06K9/00288

Abstract: An apparatus and method for classifying input data, where differences between general characteristics of the input item and the training data are reduced by manipulating general characteristics of an original subspace defined by the training data, projecting the input item into the manipulated subspace before classifying the input item and determining projection coefficients used to project the input item into the manipulated subspace. The input item is classified by mapping the projection coefficients of the input item and the projection coefficients of the training data into a classification space. The input item and training data may correspond to images, sounds, colors or other data of varying dimension, where manipulation is performed by comparing one or more of the general characteristics of the original subspace including rotational orientation, translational orientation, scale, and illumination.

Abstract translation: 一种用于对输入数据进行分类的装置和方法，其中通过操纵由训练数据定义的原始子空间的一般特征来减少输入项和训练数据的一般特性之间的差异，将输入项投影到被操纵的子空间中，然后再分类输入 项目和确定用于将输入项投影到被操纵的子空间中的投影系数。 通过将输入项目的投影系数和训练数据的投影系数映射到分类空间来分类输入项目。 输入项目和训练数据可以对应于不同维度的图像，声音，颜色或其他数据，其中通过比较原始子空间的一个或多个一般特征包括旋转取向，平移取向，比例尺和照明来执行操作。