US 11,654,770 B1
Limiting car behavior based on a pre-set driver profile enabled by face recognition
Patrick Martin, Rochester, MI (US)
Assigned to Ambarella International LP, Santa Clara, CA (US)
Filed by Ambarella International LP, Santa Clara, CA (US)
Filed on Mar. 31, 2021, as Appl. No. 17/218,164.
Application 17/218,164 is a continuation of application No. 16/132,677, filed on Sep. 17, 2018, granted, now 11,040,619.
Application 16/132,677 is a continuation in part of application No. 16/118,787, filed on Aug. 31, 2018, granted, now 10,850,693.
Application 16/118,787 is a continuation in part of application No. 16/033,724, filed on Jul. 12, 2018, granted, now 10,956,759.
Application 16/033,724 is a continuation in part of application No. 16/001,242, filed on Jun. 6, 2018, granted, now 10,953,850.
Application 16/001,242 is a continuation in part of application No. 15/965,891, filed on Apr. 28, 2018, granted, now 10,967,824.
Claims priority of provisional application 62/653,008, filed on Apr. 5, 2018.
This patent is subject to a terminal disclaimer.
Int. Cl. B60K 28/02 (2006.01); B60W 50/14 (2020.01); B60Q 9/00 (2006.01); G06N 3/08 (2023.01); G06T 7/593 (2017.01); G06V 20/59 (2022.01); G06V 40/10 (2022.01); G06V 40/16 (2022.01); G06F 18/214 (2023.01); H04N 13/00 (2018.01); H04N 13/239 (2018.01); G06F 18/22 (2023.01); G06F 18/25 (2023.01)
CPC B60K 28/02 (2013.01) [B60Q 9/00 (2013.01); B60W 50/14 (2013.01); G06F 18/214 (2023.01); G06N 3/08 (2013.01); G06T 7/593 (2017.01); G06V 20/597 (2022.01); G06V 40/10 (2022.01); G06V 40/168 (2022.01); G06V 40/172 (2022.01); B60W 2540/043 (2020.02); B60W 2540/30 (2013.01); G06F 18/22 (2023.01); G06F 18/25 (2023.01); G06T 2207/10021 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/30268 (2013.01); H04N 13/239 (2018.05); H04N 2013/0081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus comprising:
an interface configured to receive pixel data corresponding to users of a vehicle; and
a processor configured to (i) process said pixel data arranged as video frames, (ii) perform computer vision operations to detect objects in said video frames by (a) applying a feature detection window to each of a plurality of layers in each of the video frames and (b) performing feature extraction based on weight values for each of said plurality of layers in said video frames, (iii) detect users of said vehicle based on said objects detected in said video frames, (iv) determine a limitation profile for said users, (v) monitor for conditions provided by said limitation profile and (vi) generate a reaction if one or more of said conditions are met, wherein said weight values are determined by said processor analyzing training data prior to said feature extraction.