US 11,983,889 B1
Selective training of neural networks using motion estimation
John Hayes, Mountain View, CA (US); Volkmar Uhlig, Cupertino, CA (US); Akash J. Sagar, Redwood City, CA (US); Nima Soltani, Los Gatos, CA (US); Feng Tian, Foster City, CA (US); and Christopher R. Lumb, San Francisco, CA (US)
Assigned to GHOST AUTONOMY INC., Mountain View, CA (US)
Filed by GHOST AUTONOMY INC., Mountain View, CA (US)
Filed on Feb. 3, 2023, as Appl. No. 18/164,561.
Application 18/164,561 is a continuation of application No. 17/036,551, filed on Sep. 29, 2020, granted, now 11,574,409.
Claims priority of provisional application 62/908,422, filed on Sep. 30, 2019.
Int. Cl. G06K 9/62 (2022.01); G06N 3/08 (2023.01); G06T 7/215 (2017.01); G06T 7/246 (2017.01); G06V 10/764 (2022.01); G06V 10/771 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01)
CPC G06T 7/215 (2017.01) [G06N 3/08 (2013.01); G06T 7/246 (2017.01); G06V 10/764 (2022.01); G06V 10/771 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30252 (2013.01)] 17 Claims
OG exemplary drawing
 
7. An apparatus configured to perform steps comprising:
selecting, from a plurality of pixels in video data from a vehicle, based on motion relative to the vehicle, one or more pixels; and
raining a neural network based on the video data including the selected one or more pixels by setting the output of an error function applied to the selected one or more pixels during training of the neural network to zero;
wherein identifying the one or more pixels comprises identifying, for inclusion in the one or more pixels, at least one of: one or more pixels corresponding to one or more objects appearing to move away from the autonomous vehicle, or one or more pixels corresponding to one or more objects appearing effectively stationary relative to the autonomous vehicle.