System and method for field variance determination

• US 9,734,400 B2
• Filed: 02/01/2016
• Issued: 08/15/2017
• Est. Priority Date: 01/30/2015
• Status: Active Grant

• Current Assignee: AgriSight, Inc.
• Original Assignee: AgriSight, Inc.
• Inventors: Shriver, John
• Primary Examiner(s): JARRETT, RYAN A
• Application Number:
  US15/012,762
• Publication Number:
  US 20160239709A1
• Time in Patent Office: 561 Days
• Field of Search: None
• CPC Class Codes: G01N 33/025 Fruits or vegetables
• CPC Class Codes: G06V 20/188 Vegetation

Abstract

A method for measuring performance of a geographic region from an image including a set of image elements includes: receiving the image corresponding to a time unit, generating a geographic region performance map for the image, combining the geographic region performance map with a second geographic region performance map, and generating a geographic region performance summary map. Generating the geographic region performance map for the image can include mapping a set of image elements to a set of geographic sub-regions, generating a set of vegetative performance values for the set of image elements, mapping the set of image elements to a set of crop types, defining a subset of image elements corresponding to a subset of vegetative performance values, comparing vegetative performance values of the subset of vegetative performance values, and generating geographic region performance values for the subset of image elements.

Claims

1. A method for measuring performance of a geographic region, the geographic region including a set of geographic sub-regions, the method comprising:

a) receiving a first image of a physical geographic region, the first image recorded during a recurrent time unit within a first time duration, the first image comprising an image element set;

b) for each image element of the image element set;

mapping the image element to a virtual representation of a geographic sub-region within the geographic region,

determining a vegetative performance value for the virtual representation of the geographic sub-region based on a spectral signal extracted from the respective image element, and

associating the virtual representation of the geographic sub-region with a crop type from a set of crop types;

c) identifying a first crop set comprising virtual representations of geographic sub-regions associated with a first crop type of the set of crop types;

d) determining a first normalized vegetative performance value set, comprising determining a normalized vegetative performance value for each virtual representation of a geographic sub-region within the first crop set;

e) generating a geographic region performance summary map for the geographic region for the recurrent time unit;

f) generating a crop treatment prescription based on the geographic region performance summary map; and

g) wirelessly sending the crop treatment prescription to a crop treatment system, wherein the crop treatment system is controlled based on the crop treatment prescription.

2. The method of claim 1, further comprising:

wherein generating the geographic region performance summary map for the geographic region for the recurrent time unit comprises generating the geographic region performance summary map based on the first normalized vegetative performance value set and a second normalized vegetative performance value set associated with the recurrent time unit within a second time duration.

3. The method of claim 2, wherein the second normalized vegetative performance value set comprises a second normalized vegetative performance value for each virtual representation of a geographic sub-region, wherein generating a geographic region performance summary map comprises, for each virtual representation of a geographic sub-region, combining the respective normalized vegetative performance value with the respective second normalized vegetative performance value.

4. The method of claim 3, wherein the second normalized vegetative performance set is determined by performing a) to d) for a second image recorded during the recurrent time unit within the second time duration.

5. The method of claim 3, wherein a virtual representation of a geographic sub-region of the first crop set is associated with a second crop type for the recurrent time unit within the second time duration, wherein the second crop type is different from the first crop type.

6. The method of claim 5, wherein determining the normalized vegetative performance value for each virtual representation of a geographic sub-region within the first crop set comprises normalizing the respective vegetative performance value against the vegetative performance values of remaining virtual representations of geographic sub-regions of the first crop set, wherein the second normalized vegetative performance value for each virtual representation of a geographic sub-region is determined by normalizing a second vegetative performance value for the respective virtual representation of the geographic sub-region against vegetative performance values of remaining virtual representations of geographic sub-regions of a second crop set, wherein virtual representations of geographic sub-regions within the second crop set are associated with the second crop type.

7. The method of claim 2, wherein the first and the second time durations are a first and a second growing season, respectively.

8. The method of claim 1, wherein determining a normalized vegetative performance value for each virtual representation of a geographic sub-region within the first crop set comprises:

normalizing the respective vegetative performance value against the vegetative performance values of remaining virtual representations of geographic sub-regions of the first crop set.

9. The method of claim 8, wherein normalizing the respective vegetative performance value comprises determining a percentile of the respective vegetative performance value relative to the vegetative performance values of remaining virtual representations of geographic sub-regions of the first crop set.

10. The method of claim 1, wherein the vegetative performance value comprises a wide dynamic range vegetation index (WDRVI) value.

11. The method of claim 1, wherein associating the virtual representation of the geographic sub-region with a crop type comprises associating the crop type with the virtual representation of the geographic sub-region based on a predetermined map of crop types for the geographic region.

12. The method of claim 11, wherein associating the virtual representation of the geographic sub-region with the crop type based on the predetermined map comprises:

receiving a crop type user input comprising the crop type associated with a geographic area encompassed by the geographic region, and

associating the crop type with virtual representations of the geographic sub-regions encompassed by the geographic area.

13. A method for measuring performance of a geographic region from a first image including an image element set, the method comprising:

receiving the first image corresponding to a first time unit;

generating a first geographic region performance map for the first image, comprising;

mapping the image element set to geographic sub-regions of the geographic region,

generating a set of vegetative performance values for the set of image elements,

determining a crop type for each image element of the image element set,

defining a first subset of the image element set, the image elements within the first subset sharing a common crop type,

generating geographic region performance values for each image element within the first image element subset, based on the vegetative performance values associated with the respective image element;

generating a first geographic region performance map based on the geographic region performance values;

generating a first geographic region performance summary map based on the first geographic region performance map and a second geographic region performance map corresponding to a second image of the geographic region, wherein the second image corresponds to a second time unit;

generating a crop treatment prescription based on the first geographic region performance summary map; and

wirelessly sending the crop treatment prescription to a crop treatment system, wherein the crop treatment system is controlled based on the crop treatment prescription.

14. The method of claim 13, wherein generating the first geographic region performance map comprises defining a second subset of the image element set based on the crop types, and wherein the first and the second image element subsets comprise different image elements, wherein the first and second image element subsets are associated with a first and second crop type, respectively.

15. The method of claim 13, wherein generating a first geographic region performance summary map comprises averaging a first geographic region performance value with a second geographic region performance value, wherein the first and the second geographic region performance value correspond to a first and a second image element, respectively, and wherein the first and the second image element both correspond to a first geographic sub-region of the geographic sub-regions.

16. The method of claim 13, wherein the first and the second time unit are within a first growing season.

17. The method of claim 16, further comprising combining the first geographic region performance summary map with a second geographic region performance summary map generated based on a third image and a fourth image, the third and the fourth images respectively corresponding to a third and a fourth time unit within a second growing season, wherein the first and the second time unit correspond to a first and a second recurring calendar month within the first growing season, and wherein the third and the fourth time unit correspond to the first and the second recurring calendar month within the second growing season.

18. The method of claim 13, further comprising:

receiving a new image corresponding to the geographic region;

generating a new geographic region performance map for the new image; and

generating an updated first geographic region performance summary map based on combining the first geographic region performance summary map with the new geographic region performance map.

19. The method of claim 13, wherein comparing the vegetative performance values comprises determining a percentile ranking of a first vegetative performance value relative to remaining vegetative performance values of the subset of vegetative performance values.