-
公开(公告)号:US20180364546A1
公开(公告)日:2018-12-20
申请号:US16110073
申请日:2018-08-23
Applicant: Amazon Technologies, Inc.
Inventor: Scott Raymond Harris , Stephen Thomas Safarik , Paul Viola
Abstract: Described are systems and methods for surveying a destination as an unmanned aerial vehicle (“UAV”) descends toward the destination. To confirm that the destination is clear of objects and includes a safe landing or delivery location, such as a substantially planar surface, the UAV may capture and process images at different altitudes during the descent. Feature points of a first image captured at a first altitude may be paired with feature points of a second image captured at a second, different altitude. A homography may be computed to confirm that the paired feature points lie in the same plane and then the two images may be registered based on the paired feature points. The registered images may then be processed to determine depth information and determine if descent of the UAV is to continue or be aborted.
-
公开(公告)号:US11238281B1
公开(公告)日:2022-02-01
申请号:US15444079
申请日:2017-02-27
Applicant: Amazon Technologies, Inc.
Inventor: Chengwu Cui , Stephen Thomas Safarik , Yves Albers Schoenberg
IPC: G06K9/00 , G06K9/46 , B64C39/02 , B64D47/08 , G05D1/00 , H04N13/128 , H04N13/296 , G08G5/04
Abstract: In some embodiments, a first image may be captured from a first field of view using a first exposure time. A second image may be captured from a second field of view using a second exposure time that is different than the first exposure time. An overlapping field of view may be defined by an overlapping portion of the first field of view and the second field of view. Histograms may be created for the first image and the second image, and possibly more images that include different exposure times and represent the overlapping field of view. The histograms may be analyzed to determine a presence or an absence of a light source in the overlapping field of view.
-
公开(公告)号:US10088736B2
公开(公告)日:2018-10-02
申请号:US14863873
申请日:2015-09-24
Applicant: Amazon Technologies, Inc.
Inventor: Scott Raymond Harris , Stephen Thomas Safarik , Paul Viola
Abstract: Described are systems and methods for surveying a destination as an unmanned aerial vehicle (“UAV”) descends toward the destination. To confirm that the destination is clear of objects and includes a safe landing or delivery location, such as a substantially planar surface, the UAV may capture and process images at different altitudes during the descent. Feature points of a first image captured at a first altitude may be paired with feature points of a second image captured at a second, different altitude. A homography may be computed to confirm that the paired feature points lie in the same plane and then the two images may be registered based on the paired feature points. The registered images may then be processed to determine depth information and determine if descent of the UAV is to continue or be aborted.
-
公开(公告)号:US20170257547A1
公开(公告)日:2017-09-07
申请号:US15243892
申请日:2016-08-22
Applicant: Amazon Technologies, Inc.
Inventor: Stephen Thomas Safarik
CPC classification number: H04N5/2351 , B64C39/024 , B64C2201/024 , B64C2201/027 , B64C2201/042 , B64C2201/108 , B64C2201/123 , B64C2201/127 , B64C2201/128 , B64C2201/141 , B64C2201/145 , B64D45/08 , B64D47/08 , G05D1/0088 , G05D1/0676 , H04N5/2352 , H04N5/2353 , H04N5/247
Abstract: An incident light meter on an autonomous vehicle receives ambient light and outputs an incident light measurement in response the ambient light. One or more image sensors of the autonomous vehicle image the environment of the autonomous vehicle. An exposure setting is generated at least in part on the incident light measurement. The one or more image sensors capture a digital image at the exposure setting.
-
公开(公告)号:US09753460B1
公开(公告)日:2017-09-05
申请号:US15243892
申请日:2016-08-22
Applicant: Amazon Technologies, Inc.
Inventor: Stephen Thomas Safarik
CPC classification number: H04N5/2351 , B64C39/024 , B64C2201/024 , B64C2201/027 , B64C2201/042 , B64C2201/108 , B64C2201/123 , B64C2201/127 , B64C2201/128 , B64C2201/141 , B64C2201/145 , B64D45/08 , B64D47/08 , G05D1/0088 , G05D1/0676 , H04N5/2352 , H04N5/2353 , H04N5/247
Abstract: An incident light meter on an autonomous vehicle receives ambient light and outputs an incident light measurement in response the ambient light. One or more image sensors of the autonomous vehicle image the environment of the autonomous vehicle. An exposure setting is generated at least in part on the incident light measurement. The one or more image sensors capture a digital image at the exposure setting.
-
公开(公告)号:US20170090271A1
公开(公告)日:2017-03-30
申请号:US14863873
申请日:2015-09-24
Applicant: Amazon Technologies, Inc.
Inventor: Scott Raymond Harris , Stephen Thomas Safarik , Paul Viola
CPC classification number: G03B15/006 , G06K9/0063 , G06K9/46 , G06K9/4604 , G06Q10/08355 , G06T7/33 , G06T7/50 , H04N7/183
Abstract: Described are systems and methods for surveying a destination as an unmanned aerial vehicle (“UAV”) descends toward the destination. To confirm that the destination is clear of objects and includes a safe landing or delivery location, such as a substantially planar surface, the UAV may capture and process images at different altitudes during the descent. Feature points of a first image captured at a first altitude may be paired with feature points of a second image captured at a second, different altitude. A homography may be computed to confirm that the paired feature points lie in the same plane and then the two images may be registered based on the paired feature points. The registered images may then be processed to determine depth information and determine if descent of the UAV is to continue or be aborted.
-
公开(公告)号:US09454154B1
公开(公告)日:2016-09-27
申请号:US15063136
申请日:2016-03-07
Applicant: Amazon Technologies, Inc.
Inventor: Stephen Thomas Safarik
CPC classification number: H04N5/2351 , B64C39/024 , B64C2201/024 , B64C2201/027 , B64C2201/042 , B64C2201/108 , B64C2201/123 , B64C2201/127 , B64C2201/128 , B64C2201/141 , B64C2201/145 , B64D45/08 , B64D47/08 , G05D1/0088 , G05D1/0676 , H04N5/2352 , H04N5/2353 , H04N5/247
Abstract: An incident light meter on an autonomous vehicle receives ambient light and outputs an incident light measurement in response the ambient light. One or more image sensors of the autonomous vehicle image the environment of the autonomous vehicle. An exposure setting is generated at least in part on the incident light measurement. The one or more image sensors capture a digital image at the exposure setting.
Abstract translation: 自主车辆上的入射光度计接收环境光,并响应于环境光输出入射光测量。 自主车辆的一个或多个图像传感器对自主车辆的环境进行成像。 至少部分地对入射光测量产生曝光设定。 一个或多个图像传感器在曝光设置下捕获数字图像。
-
-
-
-
-
-