US 11,867,819 B2
Automatic positioning of 2D image sign sightings in 3D space
David Doria, Oak Park, IL (US); Charles Morcom, Chicago, IL (US); Engin Burak Anil, Mount Prospect, IL (US); Fangning He, Chicago, IL (US); and Matthew Emery Goss, Chicago, IL (US)
Assigned to HERE Global B.V., Eindhoven (NL)
Filed by HERE Global B.V., Eindhoven (NL)
Filed on Jun. 10, 2021, as Appl. No. 17/344,297.
Application 17/344,297 is a continuation of application No. 16/223,679, filed on Dec. 18, 2018, granted, now 11,055,546.
Prior Publication US 2021/0303884 A1, Sep. 30, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/11 (2017.01); G06V 20/58 (2022.01); G01S 17/931 (2020.01); G06V 20/56 (2022.01); G06V 10/80 (2022.01); G01S 17/89 (2020.01); G01S 7/48 (2006.01); G06F 18/25 (2023.01)
CPC G01S 17/931 (2020.01) [G06T 7/11 (2017.01); G06V 10/803 (2022.01); G06V 20/582 (2022.01); G06V 20/588 (2022.01); G01S 7/4802 (2013.01); G01S 17/89 (2013.01); G06F 18/251 (2023.01); G06T 2207/10028 (2013.01); G06T 2207/20112 (2013.01); G06T 2207/30252 (2013.01); G06V 2201/12 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for sign detection comprising:
receiving point cloud data associated with multiple locations in a geographic region as a vehicle travels along a path;
calculating a sign position candidate for the point cloud data;
receiving image data associated with the geographic region;
calculating a sighting frustum from the image data;
performing a comparison of the sighting frustum to the sign position candidate to identify a plurality of association sets;
removing one or more association sets so as to select an accurate association set; and
storing a sign location in a geographic database in response to the selected accurate association set comparison.