SYSTEM AND METHOD FOR CROP HEALTH MONITORING

• US 20170131254A1
• Filed: 01/12/2017
• Published: 05/11/2017
• Est. Priority Date: 01/30/2015
• Status: Abandoned Application

• Current Assignee: AgriSight, Inc.
• Original Assignee: AgriSight, Inc.
• Inventors: Shriver, John, Agarwal, Mayank
• Application Number:
  US15/404,625
• Publication Number:
  US 20170131254A1
• Time in Patent Office: Days
• 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 of the geographic region captured at a first time;

generating a first performance value based on the first image;

determining a performance value change based on the first performance value and a second performance value, the second performance value associated with a second image of the geographic region captured at a second time;

determining an expected performance value change based on a third performance value associated with a third image of the geographic region captured at a third time; and

in response to the performance value change differing beyond a threshold from the expected performance value change, detecting a first crop health anomaly for the geographic region.

2. The method of claim 1, wherein determining the expected performance value change comprises determining the expected performance value based on the third performance value and a fourth performance value, the fourth performance value associated with a fourth image of the geographic region captured at a fourth time.

3. The method of claim 2, wherein the first and the third times are recurrences of a first recurring time unit, and wherein the second and the fourth times are recurrences of a second recurring time unit.

4. The method of claim 3, wherein the first and the second recurrent time units are different calendar months.

5. The method of claim 1, wherein generating the first performance value comprises normalizing the first performance value with remaining performance values sharing a crop type with the first performance value.

6. The method of claim 5, wherein normalizing the first performance value comprises determining a percentile rank of the first performance value relative to the remaining performance values.

7. The method of claim 1, further comprising:

updating the expected performance value change based on the actual performance value change;

detecting a second crop health anomaly for the geographic region based on the updated expected performance value change and a fourth performance value, the fourth performance value associated with a fourth image of the geographic region captured at a fourth time after the first, the second, and the third times.

8. The method of claim 1, further comprising:

generating applicator control instructions based on the first crop health anomaly; and

transmitting the applicator control instructions to a crop input applicator.

9. The method of claim 1, further comprising:

receiving a user input specifying a crop input applied to crops in the geographic region;

diagnosing a cause of the first crop health anomaly based on the crop input, the performance value change, and the expected performance value change; and

presenting the cause of the first crop health anomaly at a user device.

10. The method of claim 9, wherein the crop input is fertilizer type.

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

receiving a first image of the geographic region;

generating a first performance value based on the first image;

combining the first performance value with an additional performance value to generate a combined performance value associated with a first time;

determining a performance value change based on the combined performance value and a second performance value, the second performance value associated with a second time and a second image of the geographic region; and

identifying a crop health anomaly based on the performance value change and an expected performance value change.

12. The method of claim 11, wherein the additional performance value is generated by combining a third and a fourth performance value for a third and a fourth image, respectively.

13. The method of claim 11, further comprising:

generating a first historic performance value based on a first historic image; and

combining the first historic performance value and an additional historic performance value to generate a historic combined performance value;

wherein the expected performance value change is based on the historic combined performance value and a second historic performance value.

14. The method of claim 13, wherein the first historic combined performance value and the second historic performance value are associated with a first and a second historic time, respectively, wherein the first time and the first historic time are instances of a first recurrent time, and wherein the second time and the second historic time are instances of a second recurrent time unit.

15. The method of claim 11, wherein the geographic region comprises an anomalous sub-region associated with the crop health anomaly, the method further comprising:

generating a color-coded map of the geographic region, the color-coded map comprising a red-colored representation of the anomalous sub-region; and

presenting the color-coded map at a user device.

16. The method of claim 11, wherein the geographic region comprises a geographic sub-region associated with the crop health anomaly, the method further comprising:

receiving a user input identifying the geographic sub-region;

determining GPS coordinates corresponding to the geographic sub-region; and

directing a user to the geographic sub-region based on the GPS coordinates.

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

generating an expected region performance for the geographic region based on a historic combined value, wherein generating the expected region performance comprises;

determining a first performance value based on a first image associated with a first time;

determining a second performance value based on a second image associated with a second time;

generating the historic combined value based on the first and the second performance values;

generating an actual region performance for the geographic region based on a combined value, wherein generating the actual region performance comprises;

determining a third performance value based on a third image associated with a third time;

determining a fourth performance value based on a fourth image associated with a fourth time;

generating the combined value based on the third and the fourth performance values; and

identifying a crop health anomaly based on the actual region performance and the expected region performance.

18. The method of claim 17,

wherein the historic combined value is a historic change between the first and the second performance values,

wherein the combined value is an actual change between the third and the fourth performance values, and

wherein identifying the crop health anomaly is based on the actual change differing beyond a threshold from the historic change.

19. The method of claim 18, further comprising:

determining a historic weather change based on a first and a second weather parameter associated with the first and the second time, respectively; and

determining a weather change based on a third and a fourth weather parameter associated with the third and the fourth time, respectively, and

wherein identifying the crop health anomaly is further based on the weather change and the historic weather change.

20. The method of claim 17, wherein the first and the second times are within a historic calendar month, and wherein the third and the fourth times are within a current calendar month.