Systems and methods for determining residue length within a field

1. A method for determining residue length within a field, the method comprising:

receiving, with a computing system, a captured image depicting an imaged portion of the field from one or more imaging devices;

determining, with the computing system, an image gradient orientation at each of a plurality of pixels within the captured image;

identifying, with the computing system, a residue piece present within the image portion of the field based at least in part on the determined image gradient orientations, wherein identifying the residue piece comprises:

generating, with the computing system, a composite image depicting the image gradient orientation at which a maximum local density of the image gradient orientations occurs for the plurality of pixels; and

generating, with the computing system, a plurality of binary images based on the composite image, each binary image corresponding to one of a plurality of predetermined image gradient orientations such that each binary image depicts one or more pixels of the plurality of pixels at which the maximum local density of the image gradient orientations occurs at the corresponding predetermined image gradient orientation; and

determining, with the computing system, a length of the identified residue piece.

2. The method of claim 1 , wherein identifying the residue piece comprises:

generating, with the computing system, a mask image depicting one or more residue regions within the imaged portion of the field.

3. The method of claim 1 , wherein the predetermined image gradient orientation associated with a first binary image of the plurality of binary images overlaps with the predetermined image gradient orientation associated with a second binary image of the plurality of binary images.

4. The method of claim 1 , wherein identifying the residue piece further comprises:

morphologically closing, with the computing system, one or more gaps present within each of the plurality of binary images in a direction perpendicular to a dominant orientation depicted within the plurality of binary images.

5. The method of claim 4 , wherein identifying the residue piece further comprises:

initially classifying, with the computing system, each pixel of the plurality of pixels within each of the plurality of binary images as one of a residue pixel associated with a specific residue piece, a non-residue pixel, or an uncertain pixel based on a distance between each pixel and an edge of one the one or more residue regions depicted within the mask image.

6. The method of claim 5 , wherein identifying the residue piece further comprises:

further classifying, with the computing system, each pixel initially classified as an uncertain pixel based a proximity of each uncertain pixel to one or more pixels of the plurality of pixels initially classified as a residue pixel and one or more pixels of the plurality of pixels initially classified as a non-residue pixel.

7. The method of claim 6 , wherein identifying the residue piece further comprises:

identifying, with the computing system, a perimeter of one or more residue pieces based on the classified pixels.

8. The method of claim 1 , wherein determining the length of the identified residue piece comprises:

defining, with the computing system, a polygonal shape around each identified residue piece within each of the plurality of binary images; and

determining, with the computing system, a longest dimension of each polygonal shape.

9. The method of claim 8 , further comprising:

placing, with the computing system, each polygonal shape onto a canvas image.

10. The method of claim 9 , further comprising:

when a fraction of overlapping pixels associated two of the polygonal shapes depicted on the canvas image exceeds a threshold, discarding, with the computing system, the determined longest dimension associated with a smaller of the two polygonal shapes.

11. The method of claim 1 , wherein the one or more imaging devices are supported relative to an agricultural machine such that the images of the field are captured as the agricultural machine travels across the field, the method further comprising:

initiating, with the computing system, a control action associated with adjusting an operation of the agricultural machine based on the determined length as the agricultural machine travels across the field.

12. A system for determining residue length within a field, the system comprising:

an imaging device configured to capture images of a field; and

a computing system communicatively coupled to the imaging device, the computing system including a processor and associated memory, the memory storing instructions that, when implemented by the processor, configure the computing system to:

receive a captured image depicting an imaged portion of the field from one or more imaging devices;

determine an image gradient orientation at each of a plurality of pixels within the captured image;

identify a residue piece present within the image portion of the field at least in part based on the determined image gradient orientations, wherein, when identifying the residue piece, the computing system is configured to:

generate a composite image depicting the image gradient orientation at which a maximum local density of the image gradient orientations occurs for the plurality of pixels; and

generate a plurality of binary images based on the composite image, each binary image corresponding to one of a plurality of predetermined image gradient orientations such that each binary image depicts one or more pixels of the plurality of pixels at which the maximum local density of the image gradient orientations occurs at the corresponding predetermined image gradient orientation; and

determine a length of the identified residue piece.

13. The system of claim 12 , wherein, when identifying the residue piece, the computing system is further configured to:

generate a mask image depicting one or more residue regions within the imaged portion of the field.

14. The system of claim 12 , wherein, when identifying the residue piece, the computing system is further configured to:

morphologically close one or more gaps present within each of the plurality of binary images in a direction perpendicular to a dominant orientation depicted within the plurality of binary images.

15. The system of claim 14 , wherein, when identifying the residue piece, the computing system is further configured to:

initially classify each pixel of the plurality of pixels within each of the plurality of binary images as one of a residue pixel associated with a specific residue piece, a non-residue pixel, or an uncertain pixel based on a distance between each pixel and an edge of one the one or more residue regions depicted within the mask image.

16. The system of claim 15 , wherein, when identifying the residue piece, the computing system is further configured to:

further classify each pixel initially classified as an uncertain pixel based a proximity of each uncertain pixel to one or more pixels of the plurality of pixels initially classified as a residue pixel and one or more pixels of the plurality of pixels initially classified as a non-residue pixel.

17. The method of claim 16 , wherein, when identifying the residue piece, the computing system is further configured to:

identify a perimeter of one or more residue pieces based on the classified pixels.

18. The system of claim 13 , wherein:

the imaging device is supported relative to an agricultural machine such that the images of the field are captured as the agricultural machine travels across the field; and

the computing system is further configured to initiate a control action associated with adjusting an operation of an agricultural machine based on the determined length as the agricultural machine travels across the field.