Systems and methods for residue bunch detection

1. A method for detecting residue bunches within a field, the method comprising:

receiving, with a computing system, a depth image depicting an imaged portion of an agricultural field, the imaged portion of the field being at least partially represented by a plurality of pixels within the depth;

classifying, with the computing system, a portion of the plurality of pixels that are associated with crop residue within the imaged portion of the field as residue pixels, each residue pixel being associated with a respective pixel height;

classifying, with the computing system, another portion of the plurality of pixels that are associated with soil within the imaged portion of the field as soil pixels, each soil pixel being associated with a respective pixel height;

determining, with the computing system, a reference height based at least in part on an average height of the soil calculated as a function of the pixel heights of the soil pixels;

defining, with the computing system, a pixel height threshold based at least in part on the reference height;

identifying, with the computing system, each residue pixel having a pixel height that exceeds the pixel height threshold as a candidate residue bunch pixel; and

determining, with the computing system, whether a residue bunch is present within the imaged portion of the field based at least in part on the candidate residue bunch pixels.

2. The method of claim 1 , further comprising generating, with the computing system, a slope-corrected depth image in which the depth image is corrected based on an estimated slope of the imaged portion of the field, the pixel height of each of the plurality of pixels deriving from the slope-corrected depth image.

3. The method of claim 1 , wherein defining the pixel height threshold comprises setting the pixel height threshold as a summation of the reference height and a predetermined height value.

4. The method of claim 1 , wherein determining whether a residue bunch is present within the imaged portion of the field comprises:

determining an area associated with the candidate residue bunch pixels;

comparing the area to a predetermined area threshold; and

determining that a residue bunch is present within the imaged portion of the field when the area associated with the candidate residue bunch pixels exceeds the predetermined area threshold.

5. The method of claim 4 , further comprising:

generating, with the computing system, a residue bunch mask of the candidate residue bunch pixels, the area associated with the candidate residue bunch pixels comprising a pixel area of the candidate residue bunch pixels within the residue bunch mask.

6. The method of claim 1 , further comprising, when it is determined that a residue bunch is present within the imaged portion of the field, calculating a height associated with the detected residue bunch.

7. The method of claim 1 , wherein receiving the depth image comprises receiving the depth image from an imaging device supported relative to an agricultural machine, the depth image being captured by the imaging device as the agricultural machine travels across the field.

8. The method of claim 7 , further comprising initiating, with the computing system, a control action associated with adjusting an operation of the agricultural machine based at least in part on the determination that a residue bunch is present within the imaged portion of the field.

9. A system for detecting residue bunches within a field, the system comprising:

an imaging device configured to capture a depth image depicting an imaged portion of the field, the imaged portion of the field being at least partially represented by a plurality of pixels within the depth image; 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 the from the imaging devices;

classify a portion of the plurality of pixels that are associated with crop residue within the imaged portion of the field as residue pixels, each residue pixel being associated with a respective pixel height;

classify another portion of the plurality of pixels that are associated with soil within the imaged portion of the field as soil pixels, each soil pixel being associated with a respective pixel height;

determine a reference height based at least in part on an average height of the soil calculated as a function of the pixel heights of the soil pixels;

define a pixel height threshold based at least in part on the reference height;

identify each residue pixel having a pixel height that exceeds the pixel height threshold as a candidate residue bunch pixel; and

determine whether a residue bunch is present within the imaged portion of the field based at least in part on the candidate residue bunch pixels.

10. The system of claim 9 , wherein the computing system is further configured to determine an area associated with the candidate residue bunch pixels and compare the area to a predetermined area threshold, the computing system being configured to determine that a residue bunch is present within the imaged portion of the field when the area associated with the candidate residue bunch pixels exceeds the predetermined area threshold.

11. The system of claim 10 , wherein the computing system is further configured to generate a residue bunch mask of the candidate residue bunch pixels, the area associated with the candidate residue bunch pixels comprising a pixel area of the candidate residue bunch pixels within the residue bunch mask.

12. The system of claim 9 , wherein, when it is determined that a residue bunch is present within the imaged portion of the field, the computing system is further configured to calculate a height associated with the detected residue bunch.

13. The system of claim 9 , wherein:

the imaging device is supported relative to an agricultural machine such that the depth image is 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 the agricultural machine based at least in part on the determination that a residue bunch is present within the imaged portion of the field.