Measuring crop residue from imagery using a machine-learned convolutional neural network

1. A computing system physically located on at least one of a work vehicle or an implement towed by the work vehicle, the computing system comprising:

one or more processors; and

one or more non-transitory computer-readable media that collectively store:

a machine-learned convolutional neural network configured to receive imagery and to process the imagery to select a level of crop residue from a plurality of pre-defined levels of crop residue; and

instructions that, when executed by the one or more processors, configure the computing system to perform operations, the operations comprising:

obtaining image data that depicts a portion of a field, the image data being captured by an imaging device that is physically located on at least one of the work vehicle or the implement towed by the work vehicle,

inputting the image data into the machine-learned convolutional neural network;

receiving an output of the machine-learned convolutional neural network for the image data, wherein the output of the machine-learned convolutional neural network assigns to the image data a particular one of the plurality of pre-defined levels of crop residue, and

controlling an operation of at least one of the work vehicle or the implement towed by the work vehicle based at least in part on the output of the machine-learned convolutional neural network.

2. The computing system of claim 1 , wherein the plurality of pre-defined levels of crop residue comprise eleven or twenty-one crop residue percentages.

3. The computing system of claim 1 , wherein the machine-learned convolutional neural network is configured to provide the output at a final fully-connected layer of the machine-learned convolutional neural network.

4. The computing system of claim 3 , wherein the final fully-connected layer of the machine-learned convolutional neural network applies a softmax function.

5. The computing system of claim 1 , wherein the image data comprises a plurality of image frames.

6. The computing system of claim 1 , wherein the image data comprises a single image frame and wherein the operations further comprise:

obtaining a plurality of image frames that depict respective portions of the field;

performing the operations recited in claim 1 for each of the plurality of image frames to determine a plurality of frame-wise crop residue levels respectively for the plurality of image frames; and

determining a total crop residue value-for the field based at least in part on the plurality of frame-wise crop residue levels.

7. A computer-implemented method, comprising:

obtaining, by a computing system comprising one or more computing devices, image data that depicts a portion of a field, the computing system being physically located on at least one of a work vehicle or an implement towed by the work vehicle, the image data being captured by an imaging device that is physically located on at least one of the work vehicle or the implement towed by the work vehicle;

inputting, by the computing system, the image data into a machine-learned convolutional neural network that is configured to receive imagery and to process the imagery to select a level of crop residue from a plurality of pre-defined levels of crop residue;

receiving, by the computing system, an output of the machine-learned convolutional neural network for the image data, wherein the output of the machine-learned convolutional neural network assigns to the image data a particular one of the plurality of pre-defined levels of crop residue; and

controlling, by the computing system, an operation of at least one of the work vehicle or the implement towed by the work vehicle based at least in part on the output of the machine-learned convolutional neural network.

8. The computer-implemented method of claim 7 , wherein the plurality of pre-defined levels of crop residue consist of eleven or twenty-one crop residue percentages.

9. The computer-implemented method of claim 7 , wherein the machine-learned convolutional neural network is configured to provide the output at a final fully-connected layer of the machine-learned convolutional neural network.

10. The computer-implemented method of claim 9 , wherein the final fully-connected layer of the machine-learned convolutional neural network applies a softmax function.

11. The computer-implemented method of claim 7 , wherein the image data comprises a plurality of image frames.

12. The computer-implemented method of claim 7 , wherein the image data comprises a single image frame and wherein the method further comprises:

obtaining, by the computing system, a plurality of image frames that depict respective portions of the field;

performing, by the computing system, the computer-implemented method of claim 7 for each of the plurality of image frames to determine a plurality of frame-wise crop residue levels respectively for the plurality of image frames; and

determining, by the computing system, a total crop residue value for the field based at least in part on the plurality of frame-wise crop residue levels.

13. An agricultural work vehicle or implement, comprising:

one or more imaging devices; and

a controller comprising one or more processors and one or more non-transitory computer-readable media that collectively store:

a machine-learned convolutional neural network configured to receive imagery and to process the imagery to select a level of crop residue from a plurality of pre-defined levels of crop residue; and

instructions that, when executed by the one or more processors, configure the controller to perform operations, the operations comprising:

obtaining image data that depicts a portion of a field;

inputting the image data into the machine-learned convolutional neural network;

receiving an output of the machine-learned convolutional neural network for the image data, wherein the output of the machine-learned convolutional neural network assigns to the image data a particular one of the plurality of pre-defined levels of crop residue; and

controlling an operation of the agricultural work vehicle or implement based at least in part on the output of the machine-learned convolutional neural network.

14. The agricultural work vehicle or implement of claim 13 , wherein the plurality of pre-defined levels of crop residue comprise a plurality of bands of crop residue percentage.

15. The agricultural work vehicle or implement of claim 13 , wherein the machine-learned convolutional neural network is configured to provide the output at a final fully-connected layer of the machine-learned convolutional neural network.

16. The agricultural work vehicle or implement of claim 15 , wherein the final fully-connected layer of the machine-learned convolutional neural network applies a softmax function.

17. The agricultural work vehicle or implement of claim 13 , wherein the image data comprises a plurality of image frames.

18. The agricultural work vehicle or implement of claim 13 , wherein the image data comprises a single image frame and wherein the operations further comprise:

obtaining a plurality of image frames that depict respective portions of the field;

performing the operations recited in claim 13 for each of the plurality of image frames to determine a plurality of frame-wise crop residue values respectively for the plurality of image frames; and

determining a total crop residue value for the field based at least in part on the plurality of frame-wise crop residue values.

19. A computing system, comprising:

one or more processors; and

one or more non-transitory computer-readable media that collectively store:

a machine-learned convolutional neural network configured to receive imagery and to process the imagery to select a level of crop residue from a plurality of pre-defined levels of crop residue; and

instructions that, when executed by the one or more processors, configure the computing system to perform operations, the operations comprising:

obtaining a plurality of image frames that depict respective portions of a field;

inputting each of the plurality of image frames into the machine-learned convolutional neural network;

receiving an output of the machine-learned convolutional neural network for each of the plurality of image frames, wherein the output of the machine-learned convolutional neural network assigns to each image frame a particular one of the plurality of pre-defined levels of crop residue such that a plurality of frame-wise crop residue levels are respectively determined for the plurality of image frames; and

determining a total crop residue value for the field based at least in part on the plurality of frame-wise crop residue levels.

20. The computing system of claim 19 , wherein:

the computing system is physically located on at least one of a work vehicle or an implement towed by the work vehicle;

obtaining the plurality of image frames comprises obtaining the plurality of image frames captured by an imaging device that is physically located on at least one of the work vehicle or the implement towed by the work vehicle; and

the operations further comprise controlling an operation of at least one of the work vehicle or the implement towed by the work vehicle based at least in part on at least one of the plurality of frame-wise crop residue levels or the determined total crop residue value for the field.

21. A computer-implemented method, comprising:

obtaining, by a computing system comprising one or more computing devices, a plurality of image frames that depict respective portions of a field;

inputting, by the computing system, the plurality of image frames into a machine-learned convolutional neural network that is configured to receive imagery and to process the imagery to select a level of crop residue from a plurality of pre-defined levels of crop residue;

receiving, by the computing system, an output of the machine-learned convolutional neural network for the image data, wherein the output of the machine-learned convolutional neural network assigns to each image frame a particular one of the plurality of pre-defined levels of crop residue such that a plurality of frame-wise crop residue levels are respectively determined for the plurality of image frames; and

determining, by the computing system, a total crop residue value for the field based at least in part on the plurality of frame-wise crop residue levels.

22. The computer-implemented method of claim 21 , wherein:

the computing system is physically located on at least one of a work vehicle or an implement towed by the work vehicle;

obtaining, by the computing system, the plurality of image frames comprises obtaining the plurality of image frames captured by an imaging device that is physically located on at least one of the work vehicle or the implement towed by the work vehicle; and

the method further comprises controlling, by the computing system, an operation of at least one of the work vehicle or the implement towed by the work vehicle based at least in part on at least one of the plurality of frame-wise crop residue levels or the determined total crop residue value for the field.

23. A computing system comprising:

one or more processors; and

one or more non-transitory computer-readable media that collectively store:

a machine-learned convolutional neural network configured to receive imagery and to process the imagery to select a level of crop residue from a plurality of pre-defined levels of crop residue; and

instructions that, when executed by the one or more processors, configure the computing system to perform operations, the operations comprising:

obtaining image data that depicts a portion of a field;

inputting the image data into the machine-learned convolutional neural network; and

receiving an output of the machine-learned convolutional neural network for the image data, wherein the output of the machine-learned convolutional neural network assigns to the image data a particular one of the plurality of pre-defined levels of crop residue,

wherein the machine-learned convolutional neural network is configured to provide the output at a final fully-connected layer of the machine-learned convolutional neural network.

24. The computing system of claim 23 , wherein the final fully-connected layer of the machine-learned convolutional neural network applies a softmax function.

25. The computing system of claim 23 , wherein:

the computing system is physically located on at least one of a work vehicle or an implement towed by the work vehicle;

obtaining the image data of the field comprises obtaining image data captured by an imaging device that is physically located on at least one of the work vehicle or the implement towed by the work vehicle; and

the operations further comprise controlling an operation of at least one of the work vehicle or the implement towed by the work vehicle based at least in part on the output of the machine-learned convolutional neural network.

26. A computer-implemented method, comprising:

obtaining, by a computing system comprising one or more computing devices, image data that depicts a portion of a field;

inputting, by the computing system, the image data into a machine-learned convolutional neural network that is configured to receive imagery and to process the imagery to select a level of crop residue from a plurality of pre-defined levels of crop residue; and

receiving, by the computing system, an output of the machine-learned convolutional neural network for the image data, wherein the output of the machine-learned convolutional neural network assigns to the image data a particular one of the plurality of pre-defined levels of crop residue,

wherein the machine-learned convolutional neural network is configured to provide the output at a final fully-connected layer of the machine-learned convolutional neural network.

27. The computer-implemented method of claim 26 , wherein the final fully-connected layer of the machine-learned convolutional neural network applies a softmax function.

28. The computer-implemented method of claim 26 , wherein:

the computing system is physically located on at least one of a work vehicle or an implement towed by the work vehicle;

obtaining, by the computing system, the image data of the field comprises obtaining image data captured by an imaging device that is physically located on at least one of the work vehicle or the implement towed by the work vehicle; and

the method further comprises controlling, by the computing system, an operation of at least one of the work vehicle or the implement towed by the work vehicle based at least in part on the output of the machine-learned convolutional neural network.