US 11,854,233 B1
Detecting overexposure in images from sunlight
Riccardo Gherardi, Seattle, WA (US); Saral Jain, Seattle, WA (US); Hasan Tuna Icingir, Seattle, WA (US); Griffin Alexander Jarmin, Seattle, WA (US); and Bo Chen, Bothell, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Feb. 8, 2021, as Appl. No. 17/170,493.
Application 17/170,493 is a division of application No. 16/688,914, filed on Nov. 19, 2019, granted, now 10,917,558.
Application 16/688,914 is a division of application No. 15/635,070, filed on Jun. 27, 2017, granted, now 10,491,808, issued on Nov. 26, 2019.
Int. Cl. G06K 9/00 (2022.01); G06T 7/80 (2017.01); G06V 20/13 (2022.01); G06V 20/52 (2022.01); G06V 10/60 (2022.01)
CPC G06T 7/80 (2017.01) [G06V 10/60 (2022.01); G06V 20/13 (2022.01); G06V 20/52 (2022.01); G06T 2207/30232 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method, comprising:
under control of one or more computing systems configured with executable instructions,
receiving an image of an area and camera parameters corresponding to a camera that generated the image, wherein the camera parameters include an integration time of the camera, and a gain of the camera;
determining, based at least in part on the integration time, the gain, and the image, a current radiance value corresponding to the camera;
computing a ratio between the current radiance value and a baseline radiance value previously determined for the camera;
determining that the ratio exceeds a threshold; and
in response to determining that the ratio exceeds the threshold, sending an indication that direct sunlight has been detected in at least a portion of the area.