Vision system for robotic attacher
View Patent ↗In certain embodiments, a system includes a controller operable to access a first image generated by a first camera. The controller determines a reference point from at least one main feature of a dairy livestock included in the first image. The controller is further operable to access a second image generated by the second camera. The second image includes at least a portion of an udder of the dairy livestock. The controller determines a location of a teat of the dairy livestock based on the second image.
1. A system comprising:
a controller operable to:
access a first image generated by a first camera, the first image including one or more main features of a dairy livestock;
determine a reference point based at least in part on the first image, the reference point determined from at least one of the one or more main features of the dairy livestock;
access a second image generated by a second camera, the second image including at least a portion of an udder of the dairy livestock; and
determine a location of a teat of the dairy livestock based at least in part on the second image.
2. The system of claim 1 , wherein the first camera comprises a three-dimensional camera and the second camera comprises a two-dimensional camera.
3. The system of claim 1 , wherein:
the first camera and the second camera are each positioned on a robotic attacher; and
the controller is further operable to:
communicate, in response to determining the reference point, a first signal to the robotic attacher, the first signal causing the robotic attacher to be positioned relative to the reference point such that the second camera may generate the second image including at least a portion of the udder of the dairy livestock;
communicate, in response to determining a location of the teat of the dairy livestock, a second signal to the robotic attacher, the second signal causing the robotic attacher to position milking equipment relative to the determined location of the teat of the dairy livestock such that the robotic attacher may attach the milking equipment to the teat.
4. The system of claim 3 , wherein the second camera is positioned on the robotic attacher proximate to a portion of the robotic attacher adapted to hold a teat cup.
5. The system of claim 1 , wherein:
the one or more main features of the dairy livestock include the hind legs of the dairy livestock;
the reference point is located between the hind legs of the dairy, livestock; and
a robotic attacher attaches milking equipment to the teat between the hind legs of the dairy livestock.
6. The system of claim 1 , wherein the controller is further operable to:
access identification information associated with the dairy livestock;
access historical data associated with the dairy livestock based on the identification information, the historical data including a previously-determined location of the teat of the dairy livestock; and
communicate a signal to the second camera, the signal causing the second camera to be directed toward the previously-determined location of the teat of the dairy livestock when generating the second image.
7. The system of claim 1 , wherein:
the dairy livestock is located in a milking stall; and
the controller is further operable to communicate a signal to the first camera, the signal causing the first camera to generate the first image of a pre-determined location relative to the milking stall.
8. A method, comprising:
accessing a first image generated by a first camera, the first image including one or more main features of a dairy livestock;
determining a reference point based at least in part on the first image, the reference point determined from at least one of the one or more main features of the dairy livestock;
accessing a second image generated by a second camera, the second image including at least a portion of an udder of the dairy livestock; and
determining a location of a teat of the dairy livestock based at least in part on the second image.
9. The method of claim 8 , wherein:
the first image comprises a three-dimensional image; and
the second image comprises a two-dimensional image.
10. The method of claim 8 , wherein the first camera and the second camera are each positioned on a robotic attacher, the method further comprising:
communicating, in response to determining the reference point, a first signal to the robotic attacher, the first signal causing the robotic attacher to be positioned relative to the reference point such that the second camera may generate the second image including at least a portion of the udder of the dairy livestock; and
communicating, in response to determining a location of the teat of the dairy livestock, a second signal to the robotic attacher, the second signal causing the robotic attacher to position milking equipment relative to the determined location of the teat of the dairy livestock such that the robotic attacher may attach the milking equipment to the teat.
11. The method of claim 8 , wherein:
the one or more main features of the dairy livestock include the hind legs of the dairy livestock;
the reference point is located between the hind legs of the dairy livestock; and
the method further comprises attaching milking equipment to the teat between the hind legs of the dairy livestock.
12. The method of claim 8 , further comprising:
accessing identification information associated with the dairy livestock;
accessing historical data associated with the dairy livestock based on the identification information, the historical data including a previously-determined location of the teat of the dairy livestock; and
communicating a signal to the second camera, the signal causing the second camera to be directed toward the previously-determined location of the teat of the dairy livestock when generating the second image.
13. The method of claim 8 , wherein the dairy livestock is located in a milking stall, and further comprising:
communicating a signal to the first camera, the signal causing the first camera to generate the first image of a pre-determined location relative to the milking stall.
14. A non-transitory computer readable storage medium comprising logic, the logic, when executed by a processor, operable to:
access a first image generated by a first camera, the first image including one or more main features of a dairy livestock;
determine a reference point based at least in part on the first image, the reference point determined from at least one of the one or more main features of the dairy livestock;
access a second image generated by a second camera, the second image including at least a portion of an udder of the dairy livestock; and
determine a location of a teat of the dairy livestock based at least in part on the second image.
15. The logic of claim 14 , wherein:
the first image comprises a three-dimensional image; and
the second image comprises a two-dimensional image.
16. The logic of claim 14 , wherein:
the first camera and the second camera are each positioned on a robotic attacher; and
the logic is further operable to:
communicate, in response to determining the reference point, a first signal to the robotic attacher, the first signal causing the robotic attacher to be positioned relative to the reference point such that the second camera may generate the second image including at least a portion of the udder of the dairy livestock;
communicate, in response to determining a location of the teat of the dairy livestock, a second signal to the robotic attacher, the second signal causing the robotic attacher to position milking equipment relative to the determined location of the teat of the dairy livestock such that the robotic attacher may attach the milking equipment to the teat.
17. The logic of claim 14 , wherein:
the one or more main features of the dairy livestock include the hind legs of the dairy livestock; and
the reference point is located between the hind legs of the dairy livestock.
18. The logic of claim 14 , wherein the logic is further operable to:
access identification information associated with the dairy livestock;
access historical data associated with the dairy livestock based on the identification information, the historical data including a previously-determined location of the teat of the dairy livestock; and
communicate a signal to the second camera; the signal causing the second camera to be directed toward the previously-determined location of the teat of the dairy livestock when generating the second image.
19. The logic of claim 14 , wherein:
the dairy livestock is located in a milking stall; and
the logic is further operable to communicate a signal to the first camera, the signal causing the first camera to generate the first image of a pre-determined location relative to the milking stall.