Measuring crop residue from imagery using a machine-learned semantic segmentation model

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, wherein the image data comprises a plurality of pixels;
• inputting, by the computing system, the image data into a machine-learned semantic segmentation model configured to receive imagery and to process the imagery to semantically segment the imagery;
• receiving, by the computing system, a semantic segmentation of the image data as an output of the machine-learned semantic segmentation model, wherein the semantic segmentation respectively labels each of the plurality of pixels as a residue pixel or a non-residue pixel;
• and
• determining, by the computing system, a crop residue value for the image data based at least in part on the semantic segmentation of the image data.

An agricultural machinery 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 semantic segmentation model configured to receive imagery and to process the imagery to semantically segment the imagery;
• 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, wherein the image data comprises a plurality of pixels;
• inputting the image data into the machine-learned semantic segmentation model;
• receiving a semantic segmentation of the image data as an output of the machine-learned semantic segmentation model, wherein the semantic segmentation respectively labels each of the plurality of pixels as a residue pixel or a non-residue pixel;
• and
• determining a crop residue value for the image data based at least in part on the semantic segmentation of the image data.