公开(公告)号：US10580453B1

公开(公告)日：2020-03-03

申请号：US15479489

申请日：2017-04-05

Applicant: Amazon Technologies, Inc.

Inventor： Matthew Alan Townsend ,  Moshe Bouhnik ,  Konstantin Kraimer ,  Eduard Oks

IPC: G11B27/02 ,  H04N5/262 ,  G06K9/00 ,  G06K9/62 ,  G06T7/60 ,  G06K9/52 ,  G06K9/46 ,  G06T7/90 ,  G06T7/73 ,  H04N5/232

Abstract: A system and method for determining video clips including interesting content from video data. The system may receive annotation data identifying time and positions corresponding to objects represented in the video data and the system may determine priority metrics associated with each of the objects. By associating the priority metrics with the time and positions corresponding to the objects, the system may generate a priority metric map indicating a time and position of interesting moments in the video data. The system may generate moments and/or video clips based on the priority metric map. The system may determine a time (e.g., video frames) and/or space (e.g., pixel coordinates) associated with the moments/video clips and may simulate camera motion such as panning and/or zooming with the moments/video clips. The system may generate a Master Clip Table including the moments, video clips and/or annotation data associated with the moments/video clips.

公开(公告)号：US10860190B1

公开(公告)日：2020-12-08

申请号：US16390689

申请日：2019-04-22

Applicant: Amazon Technologies, Inc.

Inventor： Nicholas Robert Ditzler ,  Lee David Thompson ,  Devesh Sanghvi ,  Hilit Unger ,  Moshe Bouhnik ,  Siddharth Jacob Thazhathu ,  Anton Fedorenko

IPC: G06F3/048 ,  G06F3/0484 ,  G06F3/0482 ,  G06F3/0485 ,  G06F3/0488

Abstract: Techniques for presenting and interacting with composite images on a computing device are described. In an example, the device presents a first article and a first portion of a first composite image showing a second article. The first composite image shows a first outfit combination that is different from the first outfit. The device receives a first user interaction indicating a request to change the second article and presents the first article and a second portion of a second composite image showing a clothing article in a second outfit. The second composite image shows a second outfit combination that is different from the first outfit, the second outfit, and the first outfit combination. The device receives a second user interaction indicating a request to use the third article and presents the second composite image showing the second outfit combination.

公开(公告)号：US10540757B1

公开(公告)日：2020-01-21

申请号：US15919118

申请日：2018-03-12

Applicant: Amazon Technologies, Inc.

Inventor： Moshe Bouhnik ,  Hilit Unger ,  Eduard Oks ,  Noam Sorek

IPC: G06T5/50 ,  G06T7/11 ,  G06T7/70 ,  G06T7/37 ,  G06T3/40 ,  G06N3/04

Abstract: A computer-implemented method includes receiving first pose data for a first human represented in a first image, receiving second pose data for a second human represented in a second image, receiving first semantic segmentation data for the first image, and receiving second semantic segmentation data for the second image. A pose-aligned second image can be generated by modifying the second image based on the first pose data, the second pose data, the first semantic segmentation data, and the second semantic segmentation data. A mixed image can be determined by combining pixel values from the first image and pixel values of the pose-aligned second image according to mask data. In some embodiments, the mixed image includes a representation of an outfit that includes first clothing represented in the first image and second clothing represented in the second image.

公开(公告)号：US09620168B1

公开(公告)日：2017-04-11

申请号：US14976192

申请日：2015-12-21

Applicant: Amazon Technologies, Inc.

Inventor： Matthew Alan Townsend ,  Moshe Bouhnik ,  Konstantin Kraimer ,  Eduard Oks

IPC: H04N9/80 ,  G11B27/02 ,  G06K9/00 ,  G06K9/46 ,  G06T7/40 ,  G06K9/52 ,  G06T7/60 ,  H04N5/262 ,  G06K9/62 ,  G06T7/00

CPC classification number: G11B27/02 ,  G06K9/00268 ,  G06K9/00671 ,  G06K9/00751 ,  G06K9/4642 ,  G06K9/4652 ,  G06K9/52 ,  G06K9/6201 ,  G06K2009/4666 ,  G06T7/60 ,  G06T2207/30168 ,  H04N5/23238 ,  H04N5/2628

Abstract: A system and method for determining video clips including interesting content from video data. The system may receive annotation data identifying time and positions corresponding to objects represented in the video data and the system may determine priority metrics associated with each of the objects. By associating the priority metrics with the time and positions corresponding to the objects, the system may generate a priority metric map indicating a time and position of interesting moments in the video data. The system may generate moments and/or video clips based on the priority metric map. The system may determine a time (e.g., video frames) and/or space (e.g., pixel coordinates) associated with the moments/video clips and may simulate camera motion such as panning and/or zooming with the moments/video clips. The system may generate a Master Clip Table including the moments, video clips and/or annotation data associated with the moments/video clips.