-
公开(公告)号:US20220380065A1
公开(公告)日:2022-12-01
申请号:US17332236
申请日:2021-05-27
Applicant: HONEYWELL INTERNATIONAL INC.
Inventor: Zuowei He , Gang He , Zhiguo Ren , Zhong Chen
Abstract: Systems and methods for calibrating a synthetic image on an avionic display. The method includes receiving a synthetic image frame generated by an avionic display system and a sensor image frame from a forward-facing onboard sensor system. Object recognition is performed on the sensor image frame to generate a first search region for a first Federal Aviation Administration (FAA) marking, defined as a first search region-FAA marking pair. The sensor image frame and the first search region-FAA marking pair are processed using a deep learning method (DLM) to determine for the first FAA marking of the first search region-FAA marking pair, each of: a position deviation calculation, an orientation deviation calculation, and a synthetic image distortion factor. The synthetic image frame is then updated and rendered in accordance with the position deviation calculation, the orientation deviation calculation, and the synthetic image distortion factor, thereby calibrating the synthetic image frame.
-
公开(公告)号:US11928830B2
公开(公告)日:2024-03-12
申请号:US17645591
申请日:2021-12-22
Applicant: Honeywell International Inc.
Inventor: Zhiguo Ren , Alberto Speranzon , Carl Dins , Juan Hu , Zhiyong Dai , Vijay Venkataraman
CPC classification number: G06T7/521 , G06T7/593 , G06T17/10 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084
Abstract: Disclosed are methods and systems for generating three-dimensional reconstructions of environments. A system, for example, may include a housing having an image sensor directed in a first direction and a distance sensor directed in a second direction and a control unit including a processor and a memory storing instructions. The processor may be configured to execute the instructions to: generate a first 3D model of an environment; generate a plurality of revolved 3D models by revolving the first 3D model relative to the image sensor to a plurality of positions within a predetermined angular range; match a set of distance values to one of the revolved 3D models; determine an angular position of the second direction relative to the first direction; and generate a 3D reconstruction of the environment.
-
公开(公告)号:US11851215B2
公开(公告)日:2023-12-26
申请号:US17332236
申请日:2021-05-27
Applicant: HONEYWELL INTERNATIONAL INC.
Inventor: Zuowei He , Gang He , Zhiguo Ren , Zhong Chen
IPC: B64F5/60 , B64D43/00 , B64D45/08 , B64D47/06 , B64D47/08 , G06K9/00 , G06N3/08 , G06V20/58 , G06V20/56
CPC classification number: B64F5/60 , B64D43/00 , B64D45/08 , B64D47/06 , B64D47/08 , G06N3/08 , G06V20/582 , G06V20/588
Abstract: Systems and methods for calibrating a synthetic image on an avionic display. The method includes receiving a synthetic image frame generated by an avionic display system and a sensor image frame from a forward-facing onboard sensor system. Object recognition is performed on the sensor image frame to generate a first search region for a first Federal Aviation Administration (FAA) marking, defined as a first search region-FAA marking pair. The sensor image frame and the first search region-FAA marking pair are processed using a deep learning method (DLM) to determine for the first FAA marking of the first search region-FAA marking pair, each of: a position deviation calculation, an orientation deviation calculation, and a synthetic image distortion factor. The synthetic image frame is then updated and rendered in accordance with the position deviation calculation, the orientation deviation calculation, and the synthetic image distortion factor, thereby calibrating the synthetic image frame.
-
-