Granted Patent B2

US 12,279,599 · App. 18/349,449 · Granted Apr 22, 2025

Inventors: Laura Valentine Chrobak (Menlo Park, CA); Peter Kimball (Mountain View, CA); Barnaby John James (Campbell, CA); Julia Black Ling (Menlo Park, CA)

Assignee: TidalX AI Inc.

A01K61/95A23K50/80G01N21/532G01N21/534G01N33/18G06F18/22G06N20/00G06V40/10

Abstract

Claims (59)

1. A computer-implemented method comprising:

receiving a first pair of images of an aquaculture environment, the first pair of images captured by a camera system at a first time;

receiving a second pair of images of the aquaculture environment, the second pair of images captured by the camera system at a second time different from the first time;

generating, from each of the first pair of images and the second pair of images, first and second respective distance distributions of one or more objects in the aquaculture environment, wherein each of the first and second respective distance distributions represents counts of objects at respective distances from the camera system;

determining, based on a comparison of the first and second distance distributions, a measure associated with an optical property of water in the aquaculture environment; and

generating, based on the measure, a signal configured to activate one or more systems associated with the aquaculture environment.

2. The method of claim 1 , wherein the optical property of the water is turbidity.

3. The method of claim 1 , wherein the signal is associated with a change in operation of a feeding subsystem.

4. The method of claim 1 , wherein determining the measure associated with the optical property of the water further comprises:

determining, using computer vision, an identification of each of the one or more objects in the environment; and

determining, based on the identification of each of the one or more objects in aquaculture environment, the measure associated with the optical property of the water.

5. The method of claim 1 , further comprising:

obtaining criteria associated with the measure associated with the optical property of the water;

determining whether the criteria are satisfied; and

in response to determining that the criteria is satisfied, providing the signal.

6. The method of claim 5 , wherein determining whether the criteria are satisfied includes evaluating the signal using at least one of (i) at least one rule, or (ii) at least one trained machine learning model.

7. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising:

receiving a first pair of images of an aquaculture environment, the first pair of images captured by a camera system at a first time;

receiving a second pair of images of the aquaculture environment, the second pair of images captured by the camera system at a second time different from the first time;

generating, from each of the first pair of images and the second pair of images, first and second respective distance distributions of one or more objects in the aquaculture environment, wherein each of the first and second respective distance distributions represents counts of objects at respective distances from the camera system;

determining, based on a comparison of the first and second distance distributions, a measure associated with an optical property of water in the aquaculture environment; and

generating, based on the measure, a signal configured to active one or more systems associated with the aquaculture environment.

8. The system of claim 7 , wherein the optical property of the water is turbidity.

9. The system of claim 7 , wherein the signal is associated with a change in operation of a feeding subsystem.

10. The system of claim 7 , wherein determining the measure associated with the optical property of the water further comprises:

determining, using computer vision, an identification of each of the one or more objects in the aquaculture environment; and

determining, based on the identification of each of the one or more object in the aquaculture environment, the measure associated with the optical property of the water.

11. The system of claim 7 , wherein providing the signal further comprises:

obtaining criteria associated with the measure associated with the optical property of the water;

determining whether the criteria are satisfied; and

in response to determining that the criteria is satisfied, providing the signal.

12. One or more non-transitory computer-readable storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

receiving a first pair of images of an aquaculture environment, the first pair of images captured by a camera system at a first time;

receiving a second pair of images of the aquaculture environment, the second pair of images captured by the camera system at a second time different from the first time;

generating, from each of the first pair of images and the second pair of images, first and second respective distance distributions of one or more objects in the aquaculture environment, wherein each of the first and second respective distance distributions represents counts of objects at respective distances from the camera system;

determining, based on a comparison of the first and second distance distributions, a measure associated with an optical property of water in the aquaculture environment; and

generating, based on the measure, a signal configured to activate one or more systems associated with the aquaculture environment.

13. The one or more non-transitory computer-readable storage media of claim 12 , wherein the optical property of the water is turbidity.

14. The one or more non-transitory computer-readable storage media of claim 12 , wherein the signal is associated with a change in operation of a feeding subsystem.

15. The one or more non-transitory computer-readable storage media of claim 12 , wherein determining the measure associated with a property of the water further comprises:

determining, using computer vision, an identification of each of the one or more objects in the environment; and

determining, from the identification of each of the one or more objects in the environment, the measure associated with the optical property of the water.

16. The one or more non-transitory computer-readable storage media of claim 12 , wherein the operations further comprise:

obtaining criteria associated with the measure associated with the optical property of the water;

determining whether the criteria are satisfied; and

in response to determining that the criteria is satisfied, providing the signal.

17. The method of claim 1 , wherein generating the first and second respective distance distributions of one or more objects in the aquaculture environment comprises, for each of the first and second respective distance distributions:

identifying, by a model configured to perform object recognition, the one or more objects in the environment;

determining, by one or more computing devices, a set of relative distances for the one or more objects from the respective pair of images, wherein each relative distance in the set of relative distances is an estimated distance between an object of the one or more objects and the camera system; and

generating, by the one or more computing devices, a set of absolute distances for the one or more objects based on the set of relative distances and parameters of the camera system that captured the respective pair of images, wherein each absolute distance in the set of absolute distances represents an adjustment of the respective relative distance for an object in the one or more objects, wherein the adjustment of the respective relative distance is based on the parameters of the camera system.

18. The method of claim 17 , wherein determining the measure associated with the optical property of the water comprises:

determining a first median distance for the first set of absolute distances for the first distance distribution and a second median distance for the second set of absolute distances for the second distance distribution;

comparing the first median distance to the second median distance;

based on the comparison of the first median distance to the second median distance, determining a rate of change for the optical property of the water; and

determining the measure based on the rate of change for the optical property of the water.

19. The method of claim 1 , wherein the signal is configured to adjust at least one lighting device associated with the aquaculture environment, trigger one or more alerts in a maintenance system associated with the aquaculture environment, affect an operation of a parasite detection system associated with the aquaculture environment, affect an operation of a navigation system associated with the camera device.

20. The method of claim 1 , wherein the signal is configured to affect an operation of a biomass estimation system, and wherein affecting the operation of the biomass estimation system comprises:

assigning a confidence score of measurements captured by the biomass estimation system based on conditions of the aquaculture environment; and

adjusting, based on the signal and the confidence score, a duration of time for capturing measurements by the biomass estimation system.

Assignments (2)

Continuity (2)

References Cited (81)