Analysis and sorting in aquaculture
Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for sorting fish in aquaculture. In some implementations, one or more images are obtained of a particular fish within a population of fish. Based on the one or more images of the fish, a data element is determined. The data element can include a first value that reflects a physical characteristic of the particular fish, and a second value that reflects a condition factor of the particular fish. Based on the data element, the fish is classified as a member of a particular subpopulation of the population of fish. An actuator of an automated fish sorter is controlled based on classifying the particular fish as a member of the particular subpopulation of the population of fish.
1. A computer-implemented method comprising:
generating images of farmed fish within an enclosure using an underwater camera;
applying a machine learning-trained model to features of the images to generate respective estimates for the farmed fish in the images, wherein each of the estimates represent a range of weights;
generating a distribution that indicates, for each of multiple values or ranges, a count of the farmed fish whose respective generated estimate is associated with the value or range; and
adjusting an automated process associated with the enclosure based at least on the distribution.
2. The method of claim 1 , wherein the underwater camera comprises a stereo camera.
3. The method of claim 1 , wherein the distribution comprises a histogram.
4. The method of claim 1 , comprising estimating a quantity of runt fish within the enclosure based on the distribution.
5. The method of claim 1 , comprising training the model based on features of other images.
6. The method of claim 1 , wherein the estimates are condition factor estimates or biomass estimates.
7. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
generating images of farmed fish within an enclosure using an underwater camera;
applying a machine learning-trained model to features of the images to generate respective estimates for the farmed fish in the images, wherein each of the estimates represent a range of weights;
generating a distribution that indicates, for each of multiple values or ranges, a count of the farmed fish whose respective generated estimate is associated with the value or range; and
adjusting an automated process associated with the enclosure based at least on the distribution.
8. The medium of claim 7 , wherein the underwater camera comprises a stereo camera.
9. The medium of claim 7 , wherein the distribution comprises a histogram.
10. The medium of claim 7 , wherein the operations comprise estimating a quantity of runt fish within the enclosure based on the distribution.
11. The medium of claim 7 , wherein the operations comprise training the model based on features of other images.
12. The medium of claim 7 , wherein the estimates are condition factor estimates or biomass estimates.
13. A system comprising:
one or more computers; and
one or more computer memory devices storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
generating images of farmed fish within an enclosure using an underwater camera;
applying a machine learning-trained model to features of the images to generate respective estimates for the farmed fish in the images, wherein each of the estimates represent a range of weights;
generating a distribution that indicates, for each of multiple values or ranges, a count of the farmed fish whose respective generated estimate is associated with the value or range; and
adjusting an automated process associated with the enclosure based at least on the distribution.
14. The system of claim 13 , wherein the underwater camera comprises a stereo camera.
15. The system of claim 13 , wherein the distribution comprises a histogram.
16. The system of claim 13 , wherein the operations comprise estimating a quantity of runt fish within the enclosure based on the distribution.
17. The system of claim 13 , wherein the operations comprise training the model based on features of other images.
18. The system of claim 13 , wherein the estimates are condition factor estimates or biomass estimates.