公开(公告)号：USD966262S1

公开(公告)日：2022-10-11

申请号：US29695018

申请日：2019-06-14

Applicant: Google LLC

Designer： Rachael Elizabeth Roberts ,  Romain Clement ,  Xi Chen ,  Luc Vincent

公开(公告)号：US11430199B2

公开(公告)日：2022-08-30

申请号：US16467285

申请日：2016-12-09

Applicant: Google LLC

Inventor： Christopher Ducote ,  Ian Muldoon ,  Romain Clement

IPC: G06V10/22 ,  G06T7/292 ,  G06K9/62 ,  G06T3/40 ,  G06T5/50 ,  H04N5/232 ,  H04N13/25 ,  G06V10/25 ,  G06V20/56 ,  G06V20/62

Abstract: A vehicle mounted imaging system tracks and resolves image using an object image regions of interest at a higher resolution than that which can be provided by typical wide-angle optics. The imaging system includes an object identification camera, a sampling camera, and one or more computing devices. The one or more computing devices obtain a full-frame image from the object identification camera and identify at least one region of interest within the full frame image. The one or more computing devices then configure the sampling camera to capture images of a sampling area containing the region of interest, wherein the sampling area consists of some, but not all, of a field of view of the sampling camera. Using a super-image resolution technique, the one or more computing devices create a high-resolution image of the region of interest from a plurality of images captured by the sampling camera.

公开(公告)号：USD857526S1

公开(公告)日：2019-08-27

申请号：US29609743

申请日：2017-07-05

Applicant: Google LLC

Designer： Rachael Elizabeth Roberts ,  Romain Clement ,  Xi Chen ,  Luc Vincent

公开(公告)号：US20190311209A1

公开(公告)日：2019-10-10

申请号：US16467285

申请日：2016-12-09

Applicant: Google LLC

Inventor： Christopher Ducote ,  Ian Muldoon ,  Romain Clement

IPC: G06K9/20 ,  G06K9/32 ,  H04N5/232 ,  G06K9/62 ,  G06K9/00 ,  G06T3/40 ,  G06T7/292 ,  G06T5/50

Abstract: A vehicle mounted imaging system tracks and resolves image using an object image regions of interest at a higher resolution than that which can be provided by typical wide-angle optics. The imaging system includes an object identification camera, a sampling camera, and one or more computing devices. The one or more computing devices obtain a full-frame image from the object identification camera and identify at least one region of interest within the full frame image. The one or more computing devices then configure the sampling camera to capture images of a sampling area containing the region of interest, wherein the sampling area consists of some, but not all, of a field of view of the sampling camera. Using a super-image resolution technique, the one or more computing devices create a high-resolution image of the region of interest from a plurality of images captured by the sampling camera.