US 12,347,211 B2
Apparatuses, systems and methods for generation and transmission of vehicle operation mode data
Kenneth J. Sanchez, San Francisco, CA (US); and Aaron Scott Chan, San Jose, CA (US)
Assigned to STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed by STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed on Jan. 25, 2024, as Appl. No. 18/422,830.
Application 18/422,830 is a continuation of application No. 17/554,776, filed on Dec. 17, 2021, granted, now 11,922,705.
Application 17/554,776 is a continuation of application No. 16/727,011, filed on Dec. 26, 2019, granted, now 11,238,293, issued on Feb. 1, 2022.
Application 16/727,011 is a continuation of application No. 15/717,312, filed on Sep. 27, 2017, granted, now 10,558,874, issued on Feb. 11, 2020.
Claims priority of provisional application 62/448,043, filed on Jan. 19, 2017.
Prior Publication US 2024/0169744 A1, May 23, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/59 (2022.01); G06V 20/64 (2022.01); G06V 40/10 (2022.01); G06V 40/20 (2022.01)
CPC G06V 20/597 (2022.01) [G06V 20/64 (2022.01); G06V 40/103 (2022.01); G06V 40/107 (2022.01); G06V 40/20 (2022.01); G06V 40/10 (2022.01)] 20 Claims
OG exemplary drawing
 
8. A computer-implemented method, comprising:
extracting, by one or more processors, image features from vehicle interior data from at least one vehicle interior sensor, wherein at least a portion of the extracted image features include data representative of one or more postures of a vehicle operator; and
generating, by one or more processors, data representative of a pattern of behaviors based on comparing the extracted features with previously classified vehicle interior data wherein the previously classified vehicle interior data is further representative of known postures of vehicle operators during known patterns of behavior of vehicle operators, including by comparing data representative of the one or more postures of the vehicle operator to data representative of rotated and scaled versions of the known postures that are normalized for a range of different drivers.