US 12,288,413 B2
Camera tampering detection
Ali Hassani, Ann Arbor, MI (US); Hafiz Malik, Canton, MI (US); and Jonathan Diedrich, Carleton, MI (US)
Assigned to Ford Global Technologies, LLC, Dearborn, MI (US)
Filed by Ford Global Technologies, LLC, Dearborn, MI (US)
Filed on May 21, 2021, as Appl. No. 17/326,450.
Prior Publication US 2022/0374641 A1, Nov. 24, 2022
Int. Cl. G06V 40/10 (2022.01); G05D 1/00 (2006.01); H04N 25/63 (2023.01); H04N 25/67 (2023.01)
CPC G06V 40/10 (2022.01) [G05D 1/0055 (2013.01); H04N 25/63 (2023.01); H04N 25/67 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer, comprising:
a processor; and
a memory, the memory including instructions executable by the processor to:
acquire one or more images from a camera;
determine first camera noise values based on the one or more images by determining reactions of camera photo receptors to light;
compare the first camera noise values with second camera noise values determined based on previously acquired images from the camera by determining covariance matrices based on the one or more images of the camera and the previously acquired images from the camera, diagonalizing the covariance matrices to determine eigenvectors, and determining first and second camera noise values that include interaction noise principal components and temporal noise components of the eigenvectors;
output a tamper determination for the camera based on whether the first camera mean and variance values of the noise values match, within a tolerance value, the second camera mean and variance values of the noise values determined based on the previously acquired images from the camera; and
when the tamper d ion indicates that the first camera noise values do not match the second camera noise values, within a tolerance value, update the second camera noise values based on successful non-biometric access.