Entity identification using machine learning
US-2021142052-A1 · May 13, 2021 · US
US11657498B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11657498-B2 |
| Application number | US-202016845189-A |
| Country | US |
| Kind code | B2 |
| Filing date | Apr 10, 2020 |
| Priority date | Apr 10, 2020 |
| Publication date | May 23, 2023 |
| Grant date | May 23, 2023 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for a lighting controller for sea lice detection. In some implementations, fish are contained within an elliptical tank filled with water. An imaging station located on the elliptical tank is used to capture an image of a fish from which image analysis can be performed to detect sea lice or other skin features, including lesions, on the fish. Pairs of imaging assemblies coordinate pulsing light of at least a first and a second color and capturing images of the fish while the fish is illuminated by at least the first and the second color. By using the captured images with different color light, computers can detect features on the body of a fish including sea lice, skin lesions, shortened operculum or other physical deformities and skin features. Detection results can aid in mitigation techniques or be stored for analytics. For example, sea lice detection results can inform targeted treatments comprised of lasers, fluids, or mechanical devices such as a brush or suction.
Opening claim text (preview).
What is claimed is: 1. A computer-implemented method, comprising: illuminating, by a fish imaging system that includes (i) a fish imaging container that includes top, bottom, left and right sides around the fish imaging container that each include a window for viewing fish that swim through the fish imaging container, and (ii) top, bottom, left and right fish imaging assemblies that are each associated with a respective side of the fish imaging container, and that each include (a) a camera for viewing, through a window of the fish imaging container, fish that swim through the fish imaging container, and (b) a pair of lights including a light of a first color and a light of a second color, each for illuminating, through the window of the fish imaging container, fish that swim through the fish imaging container, a light of the first color in both the top and the bottom fish imaging assemblies; while the light of the first color is illuminated in both the top and the bottom fish imaging assemblies, controlling an exposure of a camera in both the left and the right fish imaging assemblies to generate left and right images of a particular fish swimming through the fish imaging container; after the first image is generated, ceasing illumination of the light of the first color in both the top and bottom fish imaging assemblies; after ceasing illumination of the light of the first color in both the top and bottom fish imaging assemblies, illuminating a light of the first color in both of the left and the right fish imaging assemblies; and while the light of the first color is illuminated in both the left and the right fish imaging assemblies, controlling an exposure of the camera in each of the top and the bottom fish imaging assemblies to generate top and bottom images of the particular fish swimming through the fish imaging container. 2. The computer-implemented method of claim 1 , wherein the fish that swim through the fish imaging container are kept in a continuous loop fish tank with straight and curved sections equipped, and wherein the continuous loop fish tank includes the fish imaging container and the four fish imaging assemblies in one of the straight sections. 3. The computer-implemented method of claim 1 , wherein the fish imaging container and the four fish imaging assemblies are deployed in the open ocean. 4. The computer-implemented method of claim 1 , further comprising: ceasing illumination of the light of the first color in both the left and the right fish imaging assemblies; after ceasing illumination of the light of the first color in both the left and the right fish imaging assemblies, illuminating a light of the second color in both the top and the bottom fish imaging assemblies; and while the light of the second color is illuminated in both the top and the bottom fish imaging assemblies, controlling the exposure of the camera in both of the left and right fish imaging assemblies to generate additional left and right images of the particular fish swimming through the fish imaging container. 5. The computer-implemented method of claim 1 , comprising determining whether the particular fish is likely affected by a particular condition based on an analysis of at least the top, bottom, left and right images. 6. The computer-implemented method of claim 1 , comprising providing features associated with the top, bottom, left and right images as inputs to a machine learning model. 7. The computer-implemented method of claim 1 , comprising determining, from the top, bottom, left and rights images, that the particular fish is infected with sea lice. 8. The computer-implemented method of claim 1 , wherein illumination of the lights of the top and bottom fish imaging assemblies alternate with illumination of the lights of the left and right fish imaging assemblies at a rate of greater than 60 Hz. 9. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising: illuminating, by a fish imaging system that includes (i) a fish imaging container that includes top, bottom, left and right sides around the fish imaging container that each include a window for viewing fish that swim through the fish imaging container, and (ii) top, bottom, left and right fish imaging assemblies that are each associated with a respective side of the fish imaging container, and that each include (a) a camera for viewing, through a window of the fish imaging container, fish that swim through the fish imaging container, and (b) a pair of lights including a light of a first color and a light of a second color, each for illuminating, through the window of the fish imaging container, fish that swim through the fish imaging container, a light of the first color in both the top and the bottom fish imaging assemblies; while the light of the first color is illuminated in both the top and the bottom fish imaging assemblies, controlling an exposure of a camera in both the left and the right fish imaging assemblies to generate left and right images of a particular fish swimming through the fish imaging container; after the first image is generated, ceasing illumination of the light of the first color in both the top and bottom fish imaging assemblies; after ceasing illumination of the light of the first color in both the top and bottom fish imaging assemblies, illuminating a light of the first color in both of the left and the right fish imaging assemblies; and while the light of the first color is illuminated in both the left and the right fish imaging assemblies, controlling an exposure of the camera in each of the top and the bottom fish imaging assemblies to generate top and bottom images of the particular fish swimming through the fish imaging container. 10. The medium of claim 9 , wherein the fish that swim through the fish imaging container are kept in a continuous loop fish tank with straight and curved sections equipped, and wherein the continuous loop fish tank includes the fish imaging container and the four fish imaging assemblies in one of the straight sections. 11. The medium of claim 9 , wherein the fish imaging container and the four fish imaging assemblies are deployed in the open ocean. 12. The medium of claim 9 , wherein the operations comprise: ceasing illumination of the light of the first color in both the left and the right fish imaging assemblies; after ceasing illumination of the light of the first color in both the left and the right fish imaging assemblies, illuminating a light of the second color in both the top and the bottom fish imaging assemblies; and while the light of the second color is illuminated in both the top and the bottom fish imaging assemblies, controlling the exposure of the camera in both of the left and right fish imaging assemblies to generate additional left and right images of the particular fish swimming through the fish imaging container. 13. The medium of claim 9 , wherein the operations comprise determining whether the particular fish is likely affected by a particular condition based on an analysis of at least the top, bottom, left and right images. 14. The medium of claim 9 , wherein the operations comprise providing features associated with the top, bottom, left and right images as inputs to a machine learning model. 15. The medium of claim 9 , wherein the operations comprise determining, from the top, bottom, left and rights images, that the particular fish is infected with sea lice. 16. The medium of claim 9 , wherein illumination of the lights of the top and bottom fi
Prevention or treatment of fish diseases · CPC title
Aquaria; Terraria (A01K63/04, A01K63/06 take precedence) · CPC title
Aquaculture, e.g. of fish · CPC title
Arrangements for heating or lighting in, or attached to, receptacles for live fish · CPC title
Range image; Depth image; 3D point clouds · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.