US 11,861,917 B2
Apparatuses, systems, and methods for detecting vehicle occupant actions
Aaron Scott Chan, Lisle, IL (US); and Kenneth J. Sanchez, San Francisco, CA (US)
Assigned to STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANIES, Bloomington, IL (US)
Filed by STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed on Jul. 29, 2022, as Appl. No. 17/876,645.
Application 17/876,645 is a continuation of application No. 15/181,673, filed on Jun. 14, 2016, granted, now 11,423,671.
Prior Publication US 2022/0375265 A1, Nov. 24, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/59 (2022.01); B60W 40/08 (2012.01); G06F 16/50 (2019.01); G06V 10/75 (2022.01); G06V 40/20 (2022.01); G06T 7/20 (2017.01); G06F 18/2415 (2023.01); G06N 7/01 (2023.01); H04N 7/18 (2006.01); G06Q 40/08 (2012.01); H04N 23/90 (2023.01)
CPC G06V 20/597 (2022.01) [B60W 40/08 (2013.01); G06F 16/50 (2019.01); G06F 18/2415 (2023.01); G06N 7/01 (2023.01); G06T 7/20 (2013.01); G06V 10/751 (2022.01); G06V 20/59 (2022.01); G06V 40/20 (2022.01); G06Q 40/08 (2013.01); H04N 7/181 (2013.01); H04N 23/90 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A system for detecting vehicle occupant actions, the system comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to:
receive previously classified image data from a previously classified image database, the previously classified image data representing driver postures that are rotated and scaled to be standardized for a range of different drivers and different locations of a vehicle interior sensor within a vehicle, wherein the previously classified image data is representative of previously classified vehicle occupant actions;
receive current image data from the vehicle interior sensor subsequent to the vehicle interior sensor being registered within the vehicle, wherein the current image data is representative of current vehicle occupant actions; and
determine a vehicle occupant action based at least in part upon a comparison of the current image data and the previously classified image data.