公开(公告)号：WO2022226432A1

公开(公告)日：2022-10-27

申请号：PCT/US2022/030356

申请日：2022-05-20

申请人： INNOPEAK TECHNOLOGY, INC.

发明人： ZHOU, Yang

IPC分类号： G06T7/73 ,  G06T7/55 ,  G06T7/70

摘要： The present invention is directed to extended reality systems and methods. In an exemplary embodiment, two-dimensional hand images are captured. Two-dimensional key points are identified using the two-dimensional hand images. The two-dimensional key points are mapped to three-dimensional key points. Hand prediction is performed using the threedimensional key points. There are other embodiments as well.

公开(公告)号：WO2022256189A1

公开(公告)日：2022-12-08

申请号：PCT/US2022/030353

申请日：2022-05-20

申请人： INNOPEAK TECHNOLOGY, INC.

发明人： ZHOU, Yang

IPC分类号： G06F3/01 ,  A63F13/213 ,  A63F13/428

摘要： The present invention is directed to extended reality systems and methods. In an exemplary embodiment, hand images that are captured by at least two cameras are used in a hand detection process, which is performed on the images that are alternatively seletected from the images captured by the at least two cameras. Hand tracking is performed once a hand is detected. There are other embodiments as well.

公开(公告)号：WO2023069085A1

公开(公告)日：2023-04-27

申请号：PCT/US2021/055775

申请日：2021-10-20

申请人： INNOPEAK TECHNOLOGY, INC.

发明人： LIU, Celong ,  HA, Yuanzhou ,  WANG, Lingyu ,  ZHOU, Yang ,  XU, Yi

IPC分类号： G06T15/00

摘要： This application is directed to a method implemented at an electronic device for rendering realistic hand images. A computer system creates a three-dimensional (3D) rigged hand model having unique hand characteristics. The 3D rigged hand model is posed to a hand gesture based on one or more kinesiology parameters. The hand gesture of the 3D rigged hand model is adjusted with reference to one or more natural gestures, and rendered on a background image to obtain a hand image. In some embodiments, for each natural gesture, depth data are captured and measured from one or more marked key points of a respective subset of real hands that are posed with the respective natural gesture. A subset of the depth data of the real hands with the one or more natural gestures are transferred to the 3D rigged hand model.

公开(公告)号：WO2023063944A1

公开(公告)日：2023-04-20

申请号：PCT/US2021/054825

申请日：2021-10-13

申请人： INNOPEAK TECHNOLOGY, INC.

发明人： LI, Xiang ,  LU, Jie ,  ZHOU, Yang ,  TIAN, Yuan ,  XU, Kai

IPC分类号： G06F3/033

摘要： This application is directed to recognizing hand gestures in images. An electronic device obtains an input image and down-samples the input image to a first image from which a first gesture label vector is determined. A first hand region where the hand is captured is detected in the first image. In accordance with the first hand region in the first image, the input image is cropped to an input hand region corresponding to the first hand region. A second gesture label vector is determined from the input hand region of the input image. The input hand region is associated with a first hand gesture based on both the first and second gesture label vectors. In some embodiments, the first and second gesture label vectors are combined in a weighted manner and applied to select the first hand gesture is selected from a plurality of predefined hand gestures.

公开(公告)号：WO2022241328A1

公开(公告)日：2022-11-17

申请号：PCT/US2022/030347

申请日：2022-05-20

申请人： INNOPEAK TECHNOLOGY, INC.

发明人： ZHOU, Yang

IPC分类号： G06F3/01

摘要： The present invention is directed to extended reality systems and methods. In an exemplary embodiment, hand images that are captured by at least two cameras are used in a hand shape calibration process, which correlates hand shape and distance. The resulting calibration parameters are used in subsequent gesture detection processes. There are other embodiments as well.

公开(公告)号：WO2022103412A1

公开(公告)日：2022-05-19

申请号：PCT/US2020/063624

申请日：2020-12-07

申请人： INNOPEAK TECHNOLOGY, INC.

发明人： ZHOU, Yang ,  LI, Xiang ,  GAO, Yu ,  LIU, Jie ,  XU, Yi

IPC分类号： G06K9/00 ,  G06F3/01 ,  G06N3/08

摘要： This application is directed to identifying user gestures. An electronic device receives a first sequence of image frames, identifies a first hand pose of a hand at different locations, and determines a first moving direction of the first hand pose. The electronic device determines a first hand gesture based on the first hand pose and first moving direction, and performs a first predefined operation accordingly on a first one of a set of objects. After performing the first predefined operation, the electronic device receives a second sequence of image frames and identifies a second hand pose of the same hand. The second hand pose is different from the first hand pose. The electronic device determines a second moving direction that is different from the first moving direction, and selects a second one of the set of objects based on the second hand pose and second moving direction.