Method and system for optical yield measurement of a standing crop in a field

Patent metadata

Field	Value
Publication number	US-11783576-B2
Application number	US-202117301317-A
Country	US
Kind code	B2
Filing date	Mar 31, 2021
Priority date	Oct 29, 2020
Publication date	Oct 10, 2023
Grant date	Oct 10, 2023

Abstract

An electronic data processor is configured to identify the component pixels of a harvestable plant component within the obtained image data of plant pixels of the one or more target plants. An edge, boundary or outline of the component pixels is determined. The data processor is configured to detect a size of the harvestable plant component based on the determined edge, boundary or outline of the identified component pixels. A user interface is configured to provide an aggregate, sectional yield, or per row yield based on a detected size of the harvestable plant component for the one or more target plants as an indicator of yield of the one or more plants or standing crop in the field.

First claim

The following is claimed:

1. A method for estimating yield of a standing crop in a field, the method comprising:
obtaining, by an imaging device, image data associated with one or more target plants in one or more rows of the standing crop in the field;
identifying the component pixels of a harvestable plant component within the obtained image data of plant pixels of the one or more target plants, wherein the harvestable plant component comprises a target ear of corn or maize;
determining an edge, boundary or outline of the component pixels;
detecting a size of the harvestable plant component based on the determined edge, boundary or outline of the identified component pixels; and
providing, via a user interface, a yield metric based on a detected size of the harvestable plant component for the one or more target plants as an indicator of yield of the one or more plants or standing crop in the field; and
estimating a yield reduction to the yield metric by color differentiation of a pathogen color of exposed grain kernels of the target ear of the standing crop in the field; wherein the providing the yield metric comprises a yield-adjusted yield metric of per-plant yield of the one or more plants of the standing crop in the field, where the color differentiation is with respect to background pixels, leaf pixels, stem pixels, or stalk pixels of the one or more target plants.

2. The method according to claim 1 further comprising:
determining a potential cause of the yield reduction based on color differentiation of the exposed grain kernels at top end opposite the base end of the ear of target corn;
sampling multiple target ears throughout the field to determine the potential cause of the yield reduction; and
estimating a geographic position in two-dimensional or three dimensional coordinates of each one of the sampled target ears throughout the field to determine an aggregate yield reduction associated with the yield-reduced aggregate yield.

3. The method according to claim 2 wherein the determining of the potential cause comprises:
suggesting a fungus, smut, mold, bacteria, virus or other pathogen as the potential cause based on pathogen color pixels in or commingled with the component pixels or exposed ear pixels, where the pathogen color pixels meet a color classification criteria.

4. The method according to claim 1 wherein the pathogen color may represent an identifier or characteristic of the respective pathogen selected from the group consisting of: a white or a whitish pixel color; a gray or grayish pixel color; a rust or rust-tone pixel color; a black or blackish pixel color; a brown or dark pixel color, or another pathogen pixel color or pathogen pixel wavelength range that uniquely identifies a corresponding phylum, class, order, family, genus or species of the respective particular pathogen.

5. The method according to claim 2 wherein the determining of the potential cause comprises:
identifying or recognizing a fungus, smut, mold, bacteria, virus or other potential pathogen based on detection of spectral-specific electromagnetic energy, within certain light wavelengths/frequencies in the visible wavelength/frequency range and infra-red, near-infrared, or ultraviolet wavelength/frequency ranges, from the harvestable plant component pixels or exposed harvestable plant component pixels.

6. The method according to claim 2 wherein the determining the potential cause comprises:
providing a possible pathogen identifier or list of or list of possible pathogen identifiers, of a corresponding possible or actual pathogen infecting the plant or harvestable plant component, based on: color pixels or color voxels that satisfy a color classification criteria, and an observed spectral profile of magnitude versus frequency/wavelength for spectral pixels or spectral voxels that satisfy a spectral classification criteria comprising one or more specific reference spectral frequency or wavelength ranges associated with magnitude peaks of the respective possible pathogen in observed electromagnetic energy associated with the harvestable component pixels, component voxels or exposed harvestable component pixels.

7. The method according to claim 6 wherein the spectral pixel or spectral voxel is indicative of a respective pathogen, a list of respective potential pathogens, or corresponding phylum, class, order, family, genus or species of the respective particular pathogen associated with magnitude versus frequency/wavelength response for observed visible light, ultra-violet light and/or near-infrared light.

8. The method according to claim 1 further comprising:
determining a potential cause of the yield reduction based on the size of the exposed ear at the top end opposite the exposed grain kernels at the base end of the ear of target corn, where the exposed grain kernels at the base end are underdeveloped, missing, or absent for a portion of the top end;
sampling multiple target ears throughout the field to determine the potential cause of the yield reduction; and
estimating a geographic position in two-dimensional or three dimensional coordinates of each one of the sampled target ears in at least a portion of the field to determine an aggregate yield reduction associated with the yield-reduced aggregate yield.

9. The method according to claim 8 wherein the determining of the potential cause comprises suggesting a nutrient deficiency or nitrogen deficiency based on a reduced size of the top end of one or more target ears of corn in the field.

10. The method according to claim 8 wherein the determining of the potential cause comprises suggesting a lack of pollination based on a reduced size of the top end of one or more target ears of corn in the field.

11. The method according to claim 1 further comprising:
estimating a first yield reduction component to the aggregate yield based on comparison of observed exposed grain kernels of the target ear to reference exposed grain kernels of reference images;
estimating a second yield reduction component to the aggregate yield derived from fungus, mold or plant disease data for the growing season in the same geographic region or county as the field;
wherein the providing of the aggregate yield comprises a yield-reduced aggregate yield of the one or more plants or the standing crop in the field derived from or based on the first yield reduction component and the second yield reduction component.

12. The method according to claim 1 further comprising:
estimating a first yield reduction component to the aggregate yield based on application of observed, obtained image data of component pixels to an artificial intelligence algorithm that is or was trained based on reference image data of exposed grain kernels representative of diseased pixel sets and healthy pixel sets of the harvestable plant component;
estimating a second yield reduction component to the aggregate yield derived from classification or identification of the diseased pixel sets in the obtained image data of component pixels for the growing season in the same geographic region or county as the field;
wherein the providing of the aggregate yield comprises a yield-reduced aggregate yield of the one or more plants or the standing crop in the field derived from or based on the first yield reduction component and the second yield reduction component.

13. The method according to claim 1 further comprising:
estimating a plant height of the one or more target plants in the obtained image data and a corresponding component height range for the harvestable plant component in the obtained image data to reduce a search space size in the obtained image

Assignees

• Deere & Co

Inventors

• Anderson Noel W
• Advani Gurmukh H
• Smith Benjamin M

Classifications

• A01C21/007

  Determining fertilization requirements · CPC title

• G06V20/188 Primary

  Vegetation · CPC title

• A01B79/005

  Precision agriculture · CPC title

• A01D41/1277 Primary

  for measuring grain quality · CPC title

• G06Q10/04

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title