Underwater camera biomass prediction aggregation
Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for underwater camera biomass prediction aggregation. In some implementations, an exemplary method includes obtaining images of fish captured by an underwater camera; providing data of the images to a trained model; obtaining output of the trained model indicating the likelihoods that the biomass of fish are within multiple ranges; combining likelihoods of the output based on one or more ranges common to likelihoods of two or more fish to generate a biomass distribution; and determining an action based on the biomass distribution.
1. A method comprising:
obtaining images of fish captured by an underwater camera including an image of a first fish and an image of a second fish;
providing data corresponding to the images to a trained model;
obtaining output of the trained model including (i) a first distribution indicating likelihoods that the first fish has a biomass within a first set of multiple biomass ranges and (ii) a second distribution indicating likelihoods that the second fish has a biomass within a second set of multiple biomass ranges;
combining the first distribution associated with the first fish and the second distribution associated with the second fish to generate an aggregated biomass distribution; and
determining an action based on the aggregated biomass distribution.
2. The method of claim 1 , comprising:
determining, based on the image of the first fish and the image of the second fish, a data set including a first value that indicates a length between a first point on the first fish and a second point on the first fish and a second value that indicates a length between a third point on the second fish and a fourth point on the second fish.
3. The method of claim 2 , wherein the data corresponding to the images comprises:
the data set including the first value and the second value.
4. The method of claim 2 , comprising:
detecting the first point and the second point on the first fish and the third point and the fourth point on the second fish.
5. The method of claim 4 , wherein detecting the points comprise:
providing the images to a second model trained to detect feature points on a fish body.
6. The method of claim 1 , comprising:
detecting the first fish and the second fish within the images using a second trained model.
7. The method of claim 1 , wherein the action comprises:
adjusting a feeding system providing feed to the fish.
8. The method of claim 1 , wherein the action comprises:
sending data including at least a portion of the aggregated biomass distribution to a user device, wherein the data is configured to, when displayed on the user device, present a user of the user device with a visual representation of at least the portion of the aggregated biomass distribution.
9. The method of claim 8 , wherein the visual representation of at least the portion of the aggregated biomass distribution comprises interactive elements configured to display one or more images of the fish.
10. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
obtaining images of fish captured by an underwater camera including an image of a first fish and an image of a second fish;
providing data corresponding to the images to a trained model;
obtaining output of the trained model including (i) a first distribution indicating likelihoods that the first fish has a biomass within a first set of multiple biomass ranges and (i) a second distribution indicating likelihoods that the second fish has a biomass within a second set of multiple biomass ranges;
combining the one or more values of first distribution associated with the first fish and the second distribution associated with the second fish to generate an aggregated biomass distribution; and
determining an action based on the aggregated biomass distribution.
11. The non-transitory, computer-readable medium of claim 10 , comprising:
determining, based on the image of the first fish and the image of the second fish, a data set including a first value that indicates a length between a first point on the first fish and a second point on the first fish and a second value that indicates a length between a third point on the second fish and a fourth point on the second fish.
12. The non-transitory, computer-readable medium of claim 11 , wherein the data corresponding to the images comprises:
the data set including the first value and the second value.
13. The non-transitory, computer-readable medium of claim 11 , comprising:
detecting the first point and the second point on the first fish and the third point and the fourth point on the second fish.
14. The non-transitory, computer-readable medium of claim 13 , wherein detecting the points comprise:
providing the images to a second model trained to detect feature points on a fish body.
15. The non-transitory, computer-readable medium of claim 10 , comprising:
detecting the first fish and the second fish within the images using a second trained model.
16. The non-transitory, computer-readable medium of claim 10 , wherein the action comprises:
adjusting a feeding system providing feed to the fish.
17. The non-transitory, computer-readable medium of claim 10 , wherein the action comprises:
sending data including at least a portion of the aggregated biomass distribution to a user device, wherein the data is configured to, when displayed on the user device, present a user of the user device with a visual representation of at least the portion of the aggregated biomass distribution.
18. The non-transitory, computer-readable medium of claim 17 , wherein the visual representation of at least the portion of the aggregated biomass distribution comprises interactive elements configured to display one or more images of the fish.
19. A computer-implemented system, comprising:
one or more computers; and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
obtaining images of fish captured by an underwater camera including an image of a first fish and an image of a second fish;
providing data corresponding to the images to a trained model;
obtaining output of the trained model including (i) a first distribution indicating likelihoods that the first fish has a biomass within a first set of multiple biomass ranges and (ii) a second distribution indicating likelihoods that the second fish has a biomass within a second set of multiple biomass ranges;
combining the first distribution associated with the first fish and the second distribution associated with the second fish to generate an aggregated biomass distribution; and
determining an action based on the aggregated biomass distribution.
20. The system of claim 19 , comprising:
determining, based on the image of the first fish and the image of the second fish, a data set including a first value that indicates a length between a first point on the first fish and a second point on the first fish and a second value that indicates a length between a third point on the second fish and a fourth point on the second fish.