US 11,816,991 B2
Vehicle environment modeling with a camera
Gideon Stein, Jerusalem (IL); Itay Blumenthal, Jerusalem (IL); Nadav Shaag, Jerusalem (IL); and Jeffrey Moskowitz, Jerusalem (IL)
Assigned to Mobileye Vision Technologies Ltd., Jerusalem (IL)
Filed by Mobileye Vision Technologies Ltd., Jerusalem (IL)
Filed on Nov. 25, 2020, as Appl. No. 17/104,572.
Application 17/104,572 is a continuation of application No. 16/387,969, filed on Apr. 18, 2019, granted, now 10,872,433.
Claims priority of provisional application 62/769,241, filed on Nov. 19, 2018.
Claims priority of provisional application 62/769,236, filed on Nov. 19, 2018.
Claims priority of provisional application 62/663,529, filed on Apr. 27, 2018.
Claims priority of provisional application 62/662,965, filed on Apr. 26, 2018.
Claims priority of provisional application 62/659,470, filed on Apr. 18, 2018.
Prior Publication US 2021/0118161 A1, Apr. 22, 2021
Int. Cl. G06K 9/00 (2022.01); G08G 1/16 (2006.01); G06T 7/55 (2017.01); B60W 40/06 (2012.01); G06T 7/246 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01); G06V 20/58 (2022.01)
CPC G08G 1/166 (2013.01) [B60W 40/06 (2013.01); G06T 7/248 (2017.01); G06T 7/55 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01); G06V 20/58 (2022.01); G08G 1/165 (2013.01); B60W 2420/42 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30252 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A device for modeling a road surface, the device comprising:
an image capture device with a sensor to obtain a time-ordered sequence of images representative of a surface, one of the sequence of images being a current image; and
processing circuitry to:
provide a data set to a first artificial neural network (ANN) to produce a first output of three-dimensional structure of a scene, the data set including:
a portion of the sequence of images, the portion of the sequence of images including the current image;
motion of the sensor; and
an epipole, wherein the first structure includes a representation of a vertical deviations from the surface of points observed in the portion of the sequence of images;
provide the data set to a second ANN to produce a second output of photogrammetric loss of the scene; and
compare the first output to the second output to determine a feature of the surface.