-
公开(公告)号：US20230044664A1
公开(公告)日：2023-02-09
申请号：US17838887
申请日：2022-06-13
Applicant: Purdue Research Foundation
Inventor： Ayan Sinha , Chiho Choi , Joon Hee Choi , Karthik Ramani
IPC: G06F3/01 , H04N13/271 , G06N20/00 , G06V10/44 , G06V20/64 , G06V30/194 , G06V40/10
Abstract: A method for hand pose identification in an automated system includes providing map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.
-
公开(公告)号：US20170168586A1
公开(公告)日：2017-06-15
申请号：US15380002
申请日：2016-12-15
Applicant: Purdue Research Foundation
Inventor： Ayan Sinha , Chiho Choi , Joon Hee Choi , Karthik Ramani
CPC classification number: G06F3/017 , G06K9/00214 , G06K9/00389 , G06K9/4628 , G06K9/66 , G06N99/005 , H04N13/271
Abstract: A method for hand pose identification in an automated system includes providing depth map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.
-
公开(公告)号：US11360570B2
公开(公告)日：2022-06-14
申请号：US17107160
申请日：2020-11-30
Applicant: Purdue Research Foundation
Inventor： Ayan Sinha , Chiho Choi , Joon Hee Choi , Karthik Ramani
IPC: G06F3/01 , H04N13/271 , G06N20/00 , G06V10/44 , G06V20/64 , G06V30/194 , G06V40/10
Abstract: A method for hand pose identification in an automated system includes providing depth map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.
-
公开(公告)号：US10318008B2
公开(公告)日：2019-06-11
申请号：US15380002
申请日：2016-12-15
Applicant: Purdue Research Foundation
Inventor： Ayan Sinha , Chiho Choi , Joon Hee Choi , Karthik Ramani
Abstract: A method for hand pose identification in an automated system includes providing depth map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.
-
Patent Agency Ranking
公开(公告)号：US20210081055A1
公开(公告)日：2021-03-18
申请号：US17107160
申请日：2020-11-30
Applicant: Purdue Research Foundation
Inventor： Ayan Sinha , Chiho Choi , Joon Hee Choi , Karthik Ramani
Abstract: A method for hand pose identification in an automated system includes providing depth map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.
-
公开(公告)号：US10852840B2
公开(公告)日：2020-12-01
申请号：US16707936
申请日：2019-12-09
Applicant: Purdue Research Foundation
Inventor： Ayan Sinha , Chiho Choi , Joon Hee Choi , Karthik Ramani
Abstract: A method for hand pose identification in an automated system includes providing depth map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.
-
公开(公告)号：US12013986B2
公开(公告)日：2024-06-18
申请号：US17838887
申请日：2022-06-13
Applicant: Purdue Research Foundation
Inventor： Ayan Sinha , Chiho Choi , Joon Hee Choi , Karthik Ramani
IPC: G06F3/01 , G06N20/00 , G06V10/44 , G06V20/64 , G06V30/194 , G06V40/10 , H04N13/271
CPC classification number: G06F3/017 , G06N20/00 , G06V10/454 , G06V20/653 , G06V30/194 , G06V40/11 , G06V40/113 , H04N13/271
Abstract: A method for hand pose identification in an automated system includes providing map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.
-
公开(公告)号：US20200225761A1
公开(公告)日：2020-07-16
申请号：US16707936
申请日：2019-12-09
Applicant: Purdue Research Foundation
Inventor： Ayan Sinha , Chiho Choi , Joon Hee Choi , Karthik Ramani
Abstract: A method for hand pose identification in an automated system includes providing depth map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.
-
公开(公告)号：US20190310716A1
公开(公告)日：2019-10-10
申请号：US16436588
申请日：2019-06-10
Applicant: Purdue Research Foundation
Inventor： Ayan Sinha , Chiho Choi , Joon Hee Choi , Karthik Ramani
Abstract: A method for hand pose identification in an automated system includes providing depth map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.011 seconds)
