SYSTEM AND METHOD FOR CROP HEALTH MONITORING

• US 20160223506A1
• Filed: 02/01/2016
• Published: 08/04/2016
• Est. Priority Date: 01/30/2015
• Status: Active Grant

• Current Assignee: AgriSight, Inc.
• Original Assignee: AgriSight, Inc.
• Inventors: Agarwal, Mayank, Shriver, John
• Granted Patent: US 9,638,678 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A01C 21/007 Determining fertilization requirements
• CPC Class Codes: A01G 25/16 Control of watering
• CPC Class Codes: G01N 33/0098 Plants or trees wood G01N33/46
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06Q 10/06393 Score-carding, benchmarking or key performance indicator [KPI] analysis
• CPC Class Codes: G06Q 10/109 Time management, e.g. calendars, reminders, meetings or time accounting
• CPC Class Codes: G06Q 50/02 Agriculture; Fishing; Forestry; Mining
• CPC Class Codes: G06T 11/001 Texturing; Colouring; Generation of texture or colour inpainting G06T5/77
• CPC Class Codes: G06T 11/20 Drawing from basic elements, e.g. lines or circles
• CPC Class Codes: G06T 2207/30128 Food products
• CPC Class Codes: G06T 2207/30188 Vegetation; Agriculture
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06V 20/188 Vegetation
• CPC Class Codes: G06V 30/422 Technical drawings; Geographical maps

Abstract

A method for monitoring crop health of a geographic region includes receiving an image comprising a set of image elements, the image corresponding to a time unit, mapping an image element of the set of image elements to a geographic sub-region of the geographic region, determining a geographic region performance value for the image element, determining a geographic region performance value change, and identifying a crop health anomaly based on the geographic region performance change and an expected geographic region performance value change. Determining the geographic region performance value for the image element can include determining a vegetative performance value for the image element, mapping the image element to a crop type, and normalizing the vegetative performance value.

Claims

1. A method for monitoring crop health of a geographic region, the method comprising:

receiving a first image comprising a set of image elements, the first image corresponding to a first instance of a first recurrent time unit;

mapping a first image element of the set of image elements to a geographic sub-region of the geographic region;

generating a vegetative performance value for the first image element;

mapping the first image element to a crop type;

normalizing the vegetative performance value with respect to remaining vegetative performance values associated with a subset of the set of image elements, wherein the subset of image elements is mapped to the crop type;

generating a first geographic region performance value for the first image element based on the normalization of the vegetative performance value;

calculating an actual geographic region performance value change between the first geographic region performance value and a second geographic region performance value, the second geographic region performance value associated with a second image element of a second image, the second image corresponding to a first instance of a second recurrent time unit, wherein the second image element is mapped to the geographic sub-region; and

defining the geographic sub-region as an anomalous geographic sub-region of a set of anomalous geographic sub-regions, in response to the actual geographic region performance value change differing beyond a predetermined threshold from an expected geographic region performance value change for the geographic sub-region; and

identifying a crop health anomaly based on the set of anomalous geographic sub-regions.

2. The method of claim 1, wherein the first and the second recurrent time units are a first and a second month of a growing season, respectively.

3. The method of claim 1, further comprising determining the expected geographic region performance value change based on a third and a fourth geographic region performance value, wherein the third geographic performance value is associated with a third image corresponding to a second instance of the first recurrent time unit, and wherein the fourth geographic region is associated with a fourth image corresponding to a second instance of the second recurrent time unit.

4. The method of claim 3, wherein the first instances of the first and the second recurrent time units are within a first growing season, and wherein the second instances of the first and second recurrent time units are within a reference growing season representative of historic growing seasons.

5. The method of claim 4, wherein the first recurrent time unit corresponds to a first common calendar month, and wherein the second recurrent time unit corresponds to a second common calendar month.

6. The method of claim 1, further comprising notifying a user of the crop health anomaly in response to identification of the crop health anomaly.

7. The method of claim 6, wherein notifying the user comprises:

generating a color-coded map of the geographic region comprising a plurality of map elements, wherein each map element of the plurality corresponds to a geographic sub-region of the geographic region, wherein each map element is associated with a color indicative of a difference between the actual geographic region performance value change and an expected geographic region performance value change for the respective geographic sub-region;

displaying the color-coded map on a user device associated with the user.

8. The method of claim 6, wherein notifying the user comprises directing the user to the geographic sub-region.

9. The method of claim 1, further comprising updating the expected geographic region performance value change for the geographic sub-region based on the actual geographic region performance value change.

10. A method for monitoring crop health of a geographic region, the method comprising:

receiving a first image comprising a set of image elements, the first image corresponding to a first time unit;

mapping a first image element of the set of image elements to a geographic sub-region of the geographic region;

determining a first geographic region performance value for the geographic sub-region based on the first image element;

determining an actual geographic region performance value change between the first geographic region performance value and a prior geographic region performance value for the geographic sub-region; and

identifying a crop health anomaly based on the geographic region performance value change and an expected geographic region performance value change for the geographic sub-region.

11. A method of claim 10, wherein:

determining the actual geographic region performance value change comprises calculating a difference between the first geographic region performance value and the prior geographic region performance value, wherein the first and second geographic region performance values correspond to a first and second calendar month within a current growing season, respectively;

wherein the expected geographic region performance value change is based on a difference between a third geographic region performance value and a fourth geographic region performance value, the third and fourth geographic region performance values corresponding to the first and second calendar month within a historic growing season, respectively;

wherein identifying the crop health anomaly comprises defining the geographic sub-region as an anomalous geographic sub-region of a set of anomalous geographic sub-regions, in response to the actual geographic region performance value change differing beyond a predetermined threshold from an expected geographic region performance value change for the geographic sub-region, and

wherein identifying the crop health anomaly comprises identifying the crop health anomaly based on the set of anomalous geographic sub-regions.

12. The method of claim 10, wherein identifying the crop health anomaly comprises:

receiving a supplemental dataset associated with the actual geographic region performance value change, wherein the supplemental dataset comprises at least one of;

a soil characteristic, a weather characteristic, and a user input;

comparing the supplemental dataset to a historic supplemental dataset associated with the expected geographic region performance value change, wherein the historic supplemental dataset comprises at least one of;

a historic soil characteristic, a historic weather characteristic, and a historic user input; and

identifying the crop health anomaly based on comparing the supplemental dataset to the historic supplemental dataset.

13. The method of claim 10, the method further comprising:

generating a combined geographic region performance value, comprising combining the first geographic region performance value with a second geographic region performance value associated with a second image element of a second image corresponding to a second time unit;

wherein determining the actual geographic region performance value change comprises comparing the combined geographic region performance value and the prior geographic region performance value.

14. The method of claim 13, wherein the second geographic region performance value is determined by combining a third and a fourth geographic region performance value, wherein the third geographic region performance value is associated with a third image element of a third image corresponding to a third time unit, and wherein the fourth geographic region performance value is associated with a fourth image element of a fourth image corresponding to a fourth time unit.

15. The method of claim 14, wherein the first, the second, the third, and the fourth time units are within a shared growing season.

16. The method of claim 15, wherein the first and the second time units correspond to a first calendar month within the shared growing season, and wherein the third and the fourth time units correspond to a second calendar month within the shared growing season.

17. The method of claim 10, further comprising:

diagnosing the crop health anomaly; and

presenting a diagnosis of the crop health anomaly to a user at a user device.

18. The method of claim 17, wherein diagnosing the crop health anomaly comprises:

identifying anomalous geographic sub-regions with crop health anomalies within the geographic region;

selecting an anomaly diagnosis based on a pattern of anomalous geographic sub-regions with crop health anomalies within the geographic region.

19. The method of claim 10, further comprising, in response to identifying the crop health anomaly:

determining a crop treatment based on the crop health anomaly; and

presenting the crop treatment for the geographic sub-region to a user at a user device.

20. The method of claim 10, wherein generating the first geographic region performance value comprises:

generating a vegetative performance value for the first image element;

mapping the first image element to a crop type, wherein the first image element is one of a subset of the set of image elements, and wherein the subset of image elements is mapped to the crop type;

determining a percentile ranking of the vegetative performance value relative to remaining vegetative performance values associated with the subset of image elements; and

generating the first geographic region performance value based on the percentile ranking.