US 12,277,722 B2
Visual detection of haloclines
Barnaby John James, Campbell, CA (US)
Assigned to TidalX AI Inc., Mountain View, CA (US)
Filed by TidalX AI Inc., San Ramon, CA (US)
Filed on May 20, 2022, as Appl. No. 17/749,613.
Application 17/749,613 is a continuation of application No. 17/078,490, filed on Oct. 23, 2020, granted, now 11,367,209.
Prior Publication US 2022/0284612 A1, Sep. 8, 2022
Int. Cl. G06T 7/571 (2017.01); A01K 29/00 (2006.01); A01K 61/13 (2017.01); G06V 40/10 (2022.01); H04N 7/18 (2006.01)
CPC G06T 7/571 (2017.01) [A01K 29/00 (2013.01); A01K 61/13 (2017.01); G06V 40/10 (2022.01); H04N 7/18 (2013.01); G06T 2207/30242 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining, for each of multiple vertical positions in a water column, one or more images that were taken at the vertical position in the water column;
for each of the multiple vertical positions in the water column, determining a respective quantity of in-focus pixels and a respective quantity of out-of-focus pixels for each of the one or more images that were taken at the vertical position in the water column;
for each of the multiple vertical positions in the water column, determining a ratio that is based on the respective quantity of in-focus pixels and the respective quantity of out-of-focus pixels for each of the one or more images that were taken at the vertical position in the water column;
generating, a distribution that correlates the determined ratios with the multiple vertical positions;
determining a vertical position of a cline within the water column based at least on the generated distribution; and
adjusting operation of one or more items of aquaculture equipment based on determining the depth of the cline within the water column.