公开(公告)号：US11786129B2

公开(公告)日：2023-10-17

申请号：US17666319

申请日：2022-02-07

Applicant: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.

Inventor： Srikrishna Karanam ,  Ziyan Wu ,  Georgios Georgakis

IPC: G06K9/00 ,  A61B5/00 ,  G16H30/40 ,  G06T7/00 ,  G06T7/90 ,  G06T17/00 ,  G06T7/50 ,  G06T7/70 ,  G06T17/20 ,  G16H10/60 ,  G16H30/20 ,  G06V20/64 ,  G06V40/10 ,  G06V40/20 ,  G06V20/62 ,  G06F18/21 ,  G06F18/214 ,  G06V10/764 ,  G06V10/774 ,  G06V10/778 ,  G06V10/82 ,  G06V10/42 ,  G06V10/40

CPC classification number: A61B5/0077 ,  A61B5/0035 ,  A61B5/70 ,  G06F18/21 ,  G06F18/214 ,  G06F18/2193 ,  G06T7/0012 ,  G06T7/50 ,  G06T7/70 ,  G06T7/90 ,  G06T17/00 ,  G06T17/20 ,  G06V10/40 ,  G06V10/42 ,  G06V10/764 ,  G06V10/774 ,  G06V10/7796 ,  G06V10/82 ,  G06V20/62 ,  G06V20/64 ,  G06V40/10 ,  G06V40/20 ,  G16H10/60 ,  G16H30/20 ,  G16H30/40 ,  G06T2200/08 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30004 ,  G06T2207/30196 ,  G06V2201/033

Abstract: Human mesh model recovery may utilize prior knowledge of the hierarchical structural correlation between different parts of a human body. Such structural correlation may be between a root kinematic chain of the human body and a head or limb kinematic chain of the human body. Shape and/or pose parameters relating to the human mesh model may be determined by first determining the parameters associated with the root kinematic chain and then using those parameters to predict the parameters associated with the head or limb kinematic chain. Such a task can be accomplished using a system comprising one or more processors and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to implement one or more neural networks trained to perform functions related to the task.

公开(公告)号：US11557391B2

公开(公告)日：2023-01-17

申请号：US16995446

申请日：2020-08-17

Applicant: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.

Inventor： Ziyan Wu ,  Srikrishna Karanam ,  Changjiang Cai ,  Georgios Georgakis

IPC: G06K9/62 ,  G16H30/40 ,  G06T7/00 ,  G06T7/90 ,  G06T17/00 ,  G06T7/50 ,  G06T7/70 ,  G06T17/20 ,  G16H10/60 ,  G16H30/20 ,  A61B5/00 ,  G06V10/40 ,  G06V10/42 ,  G06V20/64 ,  G06V40/10 ,  G06V40/20 ,  G06V20/62

Abstract: The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.

公开(公告)号：US11257586B2

公开(公告)日：2022-02-22

申请号：US16863382

申请日：2020-04-30

Applicant: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.

Inventor： Srikrishna Karanam ,  Ziyan Wu ,  Georgios Georgakis

IPC: G06K9/00 ,  G16H30/40 ,  G06T7/00 ,  G06T7/90 ,  G06T17/00 ,  G06K9/46 ,  G06T7/50 ,  G06T7/70 ,  G06K9/62 ,  G06T17/20 ,  G16H10/60 ,  G16H30/20 ,  A61B5/00 ,  G06K9/52

Abstract: Human mesh model recovery may utilize prior knowledge of the hierarchical structural correlation between different parts of a human body. Such structural correlation may be between a root kinematic chain of the human body and a head or limb kinematic chain of the human body. Shape and/or pose parameters relating to the human mesh model may be determined by first determining the parameters associated with the root kinematic chain and then using those parameters to predict the parameters associated with the head or limb kinematic chain. Such a task can be accomplished using a system comprising one or more processors and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to implement one or more neural networks trained to perform functions related to the task.

公开(公告)号：US20210158028A1

公开(公告)日：2021-05-27

申请号：US16995446

申请日：2020-08-17

Applicant: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.

Inventor： Ziyan Wu ,  Srikrishna Karanam ,  Changjiang Cai ,  Georgios Georgakis

IPC: G06K9/00 ,  G06T7/70 ,  G06T7/90 ,  G06T7/50 ,  G06K9/62 ,  G06T17/20

Abstract: The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.

公开(公告)号：US11963741B2

公开(公告)日：2024-04-23

申请号：US18095857

申请日：2023-01-11

Applicant: Shanghai United Imaging Intelligence Co., Ltd.

Inventor： Ziyan Wu ,  Srikrishna Karanam ,  Changjiang Cai ,  Georgios Georgakis

IPC: G06F18/21 ,  A61B5/00 ,  G06F18/214 ,  G06T7/00 ,  G06T7/50 ,  G06T7/70 ,  G06T7/90 ,  G06T17/00 ,  G06T17/20 ,  G06V10/40 ,  G06V10/42 ,  G06V10/764 ,  G06V10/774 ,  G06V10/778 ,  G06V10/82 ,  G06V20/62 ,  G06V20/64 ,  G06V40/10 ,  G06V40/20 ,  G16H10/60 ,  G16H30/20 ,  G16H30/40

CPC classification number: A61B5/0077 ,  A61B5/0035 ,  A61B5/70 ,  G06F18/21 ,  G06F18/214 ,  G06F18/2193 ,  G06T7/0012 ,  G06T7/50 ,  G06T7/70 ,  G06T7/90 ,  G06T17/00 ,  G06T17/20 ,  G06V10/40 ,  G06V10/42 ,  G06V10/764 ,  G06V10/774 ,  G06V10/7796 ,  G06V10/82 ,  G06V20/62 ,  G06V20/64 ,  G06V40/10 ,  G06V40/20 ,  G16H10/60 ,  G16H30/20 ,  G16H30/40 ,  G06T2200/08 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30004 ,  G06T2207/30196 ,  G06V2201/033

Abstract: The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.

公开(公告)号：US20230141392A1

公开(公告)日：2023-05-11

申请号：US18095857

申请日：2023-01-11

Applicant: Shanghai United Imaging Intelligence Co., Ltd.

Inventor： Ziyan Wu ,  Srikrishna Karanam ,  Changjiang Cai ,  Georgios Georgakis

IPC: A61B5/00 ,  G16H30/40 ,  G06T7/00 ,  G06T7/90 ,  G06T17/00 ,  G06T7/50 ,  G06T7/70 ,  G06T17/20 ,  G16H10/60 ,  G16H30/20 ,  G06V20/64 ,  G06V40/10 ,  G06V40/20 ,  G06V20/62 ,  G06F18/21 ,  G06F18/214 ,  G06V10/764 ,  G06V10/774 ,  G06V10/778 ,  G06V10/82 ,  G06V10/42 ,  G06V10/40

CPC classification number: A61B5/0077 ,  G16H30/40 ,  G06T7/0012 ,  G06T7/90 ,  G06T17/00 ,  G06T7/50 ,  G06T7/70 ,  G06T17/20 ,  G16H10/60 ,  G16H30/20 ,  A61B5/0035 ,  A61B5/70 ,  G06V20/64 ,  G06V40/10 ,  G06V40/20 ,  G06V20/62 ,  G06F18/21 ,  G06F18/214 ,  G06F18/2193 ,  G06V10/764 ,  G06V10/774 ,  G06V10/7796 ,  G06V10/82 ,  G06V10/42 ,  G06V10/40 ,  G06T2207/30004 ,  G06T2200/08 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06V2201/033

Abstract: The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.

公开(公告)号：US20220165396A1

公开(公告)日：2022-05-26

申请号：US17666319

申请日：2022-02-07

Applicant: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.

Inventor： Srikrishna Karanam ,  Ziyan Wu ,  Georgios Georgakis

IPC: G16H30/40 ,  G06T7/00 ,  G06T7/90 ,  G06T17/00 ,  G06T7/50 ,  G06T7/70 ,  G06K9/62 ,  G06T17/20 ,  G16H10/60 ,  G16H30/20 ,  A61B5/00 ,  G06V10/40 ,  G06V10/42 ,  G06V20/64 ,  G06V40/10 ,  G06V40/20

Abstract: Human mesh model recovery may utilize prior knowledge of the hierarchical structural correlation between different parts of a human body. Such structural correlation may be between a root kinematic chain of the human body and a head or limb kinematic chain of the human body. Shape and/or pose parameters relating to the human mesh model may be determined by first determining the parameters associated with the root kinematic chain and then using those parameters to predict the parameters associated with the head or limb kinematic chain. Such a task can be accomplished using a system comprising one or more processors and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to implement one or more neural networks trained to perform functions related to the task.

公开(公告)号：US20210158107A1

公开(公告)日：2021-05-27

申请号：US16863382

申请日：2020-04-30

Applicant: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.

Inventor： Srikrishna Karanam ,  Ziyan Wu ,  Georgios Georgakis

IPC: G06K9/62 ,  G06K9/52 ,  G06K9/00

Abstract: Human mesh model recovery may utilize prior knowledge of the hierarchical structural correlation between different parts of a human body. Such structural correlation may be between a root kinematic chain of the human body and a head or limb kinematic chain of the human body. Shape and/or pose parameters relating to the human mesh model may be determined by first determining the parameters associated with the root kinematic chain and then using those parameters to predict the parameters associated with the head or limb kinematic chain. Such a task can be accomplished using a system comprising one or more processors and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to implement one or more neural networks trained to perform functions related to the task.