US 12,254,699 B1
Detection of camera with impaired view
Shaurye Agarwal, Evanston, IL (US); Akshay Raj Dhamija, Campbell, CA (US); Howard Yu, San Francisco, CA (US); Margaret Irene Finch, Austin, TX (US); Jing Wang, Toronto (CA); Rohit Annigeri, Santa Clara, CA (US); Sharan Srinivasan, Sunnyvale, CA (US); Yan Wang, Mercer Island, WA (US); and Nathan Hurst, Seattle, WA (US)
Assigned to Samsara Inc., San Francisco, CA (US)
Filed by Samsara Inc., San Francisco, CA (US)
Filed on Sep. 3, 2024, as Appl. No. 18/823,263.
Application 18/823,263 is a continuation of application No. 18/618,182, filed on Mar. 27, 2024, granted, now 12,112,548.
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/56 (2022.01); G06T 3/60 (2024.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01)
CPC G06V 20/56 (2022.01) [G06T 3/60 (2013.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
training an impairment classifier utilizing training data comprising a plurality of images, impairment labels for each image of the plurality of images, and rotation information for each of the plurality of images;
accessing a vehicle image captured by a camera on a vehicle;
providing the vehicle image to the impairment classifier as input, the impairment classifier providing an output of a camera impairment from a set of camera impairment categories;
causing presentation on a user interface (UI) of the vehicle image and the camera impairment;
determining that the camera impairment is fixable based on a rotation of the vehicle image; and
modifying the vehicle image to correct the rotation of the vehicle image for behavioral monitoring of the vehicle.