公开(公告)号：US11482045B1

公开(公告)日：2022-10-25

申请号：US16799502

申请日：2020-02-24

Applicant: Amazon Technologies, Inc.

Inventor： Jaechul Kim ,  Nishitkumar Ashokkumar Desai ,  Jayakrishnan Kumar Eledath ,  Kartik Muktinutalapati ,  Shaonan Zhang ,  Hoi Cheung Pang ,  Dilip Kumar ,  Kushagra Srivastava ,  Gerard Guy Medioni ,  Daniel Bibireata

IPC: G06K9/00 ,  G06V40/20 ,  G06K9/62 ,  G06F17/16 ,  G06Q30/02 ,  G06N3/08 ,  G06N20/00 ,  G06V20/10 ,  G06V20/52

Abstract: Where an event is determined to have occurred at a location within a vicinity of a plurality of actors, imaging data captured using cameras having the location is processed using one or more machine learning systems or techniques operating on the cameras to determine which of the actors is most likely associated with the event. For each relevant pixel of each image captured by a camera, the camera returns a set of vectors extending to pixels of body parts of actors who are most likely to have been involved with an event occurring at the relevant pixel, along with a measure of confidence in the respective vectors. A server receives the vectors from the cameras, determines which of the images depicted the event in a favorable view, based at least in part on the quality of such images, and selects one of the actors as associated with the event accordingly.

公开(公告)号：US11922728B1

公开(公告)日：2024-03-05

申请号：US18049252

申请日：2022-10-24

Applicant: Amazon Technologies, Inc.

Inventor： Jaechul Kim ,  Nishitkumar Ashokkumar Desai ,  Jayakrishnan Kumar Eledath ,  Kartik Muktinutalapati ,  Shaonan Zhang ,  Hoi Cheung Pang ,  Dilip Kumar ,  Kushagra Srivastava ,  Gerard Guy Medioni ,  Daniel Bibireata

IPC: G06V40/20 ,  G06F17/16 ,  G06F18/2321 ,  G06N3/08 ,  G06N20/00 ,  G06Q30/0201 ,  G06V20/10 ,  G06V20/52

CPC classification number: G06V40/20 ,  G06F17/16 ,  G06F18/2321 ,  G06N3/08 ,  G06N20/00 ,  G06Q30/0201 ,  G06V20/10 ,  G06V20/52

Abstract: Where an event is determined to have occurred at a location within a vicinity of a plurality of actors, imaging data captured using cameras having the location is processed using one or more machine learning systems or techniques operating on the cameras to determine which of the actors is most likely associated with the event. For each relevant pixel of each image captured by a camera, the camera returns a set of vectors extending to pixels of body parts of actors who are most likely to have been involved with an event occurring at the relevant pixel, along with a measure of confidence in the respective vectors. A server receives the vectors from the cameras, determines which of the images depicted the event in a favorable view, based at least in part on the quality of such images, and selects one of the actors as associated with the event accordingly.

公开(公告)号：US11468698B1

公开(公告)日：2022-10-11

申请号：US16712914

申请日：2019-12-12

Applicant: Amazon Technologies, Inc.

Inventor： Jaechul Kim ,  Nishitkumar Ashokkumar Desai ,  Jayakrishnan Kumar Eledath ,  Kartik Muktinutalapati ,  Shaonan Zhang ,  Hoi Cheung Pang ,  Dilip Kumar ,  Kushagra Srivastava ,  Gerard Guy Medioni ,  Daniel Bibireata

IPC: G06K9/00 ,  G06V40/10 ,  G06N20/00 ,  G06N3/02 ,  G06Q30/06 ,  G06V20/52

Abstract: Where an event is determined to have occurred at a location within a vicinity of a plurality of actors, imaging data captured using cameras having the location is processed using one or more machine learning systems or techniques operating on the cameras to determine which of the actors is most likely associated with the event. For each relevant pixel of each image captured by a camera, the camera returns a set of vectors extending to pixels of body parts of actors who are most likely to have been involved with an event occurring at the relevant pixel, along with a measure of confidence in the respective vectors. A server receives the vectors from the cameras, determines which of the images depicted the event in a favorable view, based at least in part on the quality of such images, and selects one of the actors as associated with the event accordingly.