System and method of in-season nitrogen measurement and fertilization of non-leguminous crops from digital image analysis

• US 9,117,140 B2
• Filed: 10/16/2012
• Issued: 08/25/2015
• Est. Priority Date: 05/24/2010
• Status: Expired due to Fees

• Current Assignee: The Board of Trustees of the University of Arkansas (University of Arkansas System)
• Original Assignee: The Board of Trustees of the University of Arkansas (University of Arkansas System)
• Inventors: Purcell, Larry C., Siddons, Upton G., Karcher, Douglas E., Rorie, Robert L.
• Primary Examiner(s): Nakhjavan, Shervin
• Application Number:
  US13/652,605
• Publication Number:
  US 20130044919A1
• Time in Patent Office: 1,043 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G01N 2021/8466 Investigation of vegetal material, e.g. leaves, plants, fruits
• CPC Class Codes: G01N 21/25 Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
• CPC Class Codes: G01N 21/84 Systems specially adapted for particular applications
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30128 Food products
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/56 relating to colour

Abstract

Systems and methods of determining nitrogen levels from a digital image and in-season nitrogen measurement and fertilization of non-leguminous crops from digital image analysis are disclosed herein. In particular, a method of determining leaf nitrogen concentration and yield from a digital photograph of a fully developed leaf (collared leaf) of a crop of non-legumes, such as corn, wheat, rice, cotton, potatoes sugarcane, turfgrass or forage grass species. The digital image is processed to determine a dark green color index (“DGCI”), which is closely related to leaf nitrogen concentration and yield. Standardized color disks having known DGCI values are included in the digital photograph and serve as an comparative standard. The comparative standard allows correction of DGCI of samples when using different cameras and/or when lighting conditions change. The DGCI values can then be used to determine the amount of nitrogen fertilizer that should be applied to recover crop yield potential.

Claims

1. A computer-implemented method of determining an in-season nitrogen fertilization rate for a non-legume crop using digital image analysis, said method comprising the steps of:

a. receiving a dark green color index obtained from analysis of a digital image of said crop, where said dark green color index is equal to DGCI=[(H−

60)/60+(1−

S)+(1−

B)]/3, where DGCI is equal to said dark green color index, H is equal to an average hue value, S is equal to an average saturation value, and B is equal to an average brightness value;

b. determining a corrected dark green color index from said dark green color index;

c. determining said nitrogen fertilization rate from said corrected dark green color index; and

d. providing said nitrogen fertilization rate to achieve a predetermined yield potential for said crop.

2. The method of claim 1 further comprising the steps of:

a. acquiring said image of a colored leaf from said crop of non-legume plants, said image comprising a comparative standard to account for differences in cameras or lighting conditions or both, said image further comprising a contrasting standard having a color in a portion of the visible spectrum away from the visible spectrum of the color of said leaf; and

b. performing an algorithm to determine said dark green color index of said leaf in said image.

3. The method of claim 2 further comprising the step of placing said comparative standard a distance away from said crop to minimize any shadows between said crop and said comparative standard.

4. The method of claim 2 wherein said comparative standard is a plurality of standardized color disks having a predetermined shape and a color representing a color value ranging from severely nitrogen deficient to nitrogen sufficient of said crop.

5. The method of claim 4 wherein said standardized color disks further comprise a first standardized color disk having a yellow color representing a severely nitrogen deficient leaf and a second standardized disk having a dark green color representing a nitrogen sufficient leaf.

6. The method of claim 4 wherein said algorithm recognizes said shape of said standardized color disks and uses said standardized color disks as said comparative standard to adjust for different cameras or lighting conditions or both.

7. The method of claim 2 wherein said color of said contrasting standard is pink.

8. The method of claim 2 wherein said algorithm further comprises the steps of:

a. calculating said dark green color index of said leaf in said image;

b. calculating said dark green color index of said comparative standard in said image; and

c. calculating said corrected dark green color index from said dark green color index of said leaf and said dark green color index of said comparative standard.

9. The method of claim 8 wherein said step of calculating said dark green color index of said leaf in said image further comprises the steps of:

a. obtaining absolute red, green and blue values of said leaf in said image;

b. converting said absolute red, green and blue values to percentage red, green and blue values of said leaf in said image;

c. converting said percentage red, green and blue values to absolute hue, saturation and brightness values of said leaf in said image;

d. calculating said average hue, saturation and brightness values from said absolute hue, saturation and brightness values of said leaf in said image; and

e. converting said average hue, saturation and brightness values to said dark green color index of said leaf in said image.

10. The method of claim 9 wherein said dark green color index of said leaf in said image encompasses a dark green color on a scale of zero (0) to one (1) with values closer to one (1) representing a darker green.

11. The method of claim 8 wherein said step of calculating said dark green color index of said comparative standard in said image further comprises the steps of:

a. obtaining absolute red, green and blue values of said comparative standard in said image;

b. converting said absolute red, green and blue values to percentage red, green and blue values of said comparative standard in said image;

c. converting said percentage red, green and blue values to absolute hue, saturation and brightness values of said comparative standard in said image;

d. calculating said average hue, saturation and brightness values from said absolute hue, saturation and brightness values of said comparative standard in said image; and

e. converting said average hue, saturation and brightness values to said dark green color index of said comparative standard in said image.

12. The method of claim 11 wherein said dark green color index of said comparative standard in said image encompasses a dark green color on a scale of zero (0) to one (1) with values closer to one (1) representing a darker green.

13. The method of claim 1 further comprising the step of determining nitrogen sufficiency or deficiency of said leaf in said image from said dark green color index.

14. The method of claim 13 wherein said leaf in said image is a corn leaf at tasseling.

15. The method of claim 13 further comprising transmitting said leaf nitrogen sufficiency or deficiency through a network connection.

16. The method of claim 13 further comprising the step of estimating yield of said crop from said image based on said leaf nitrogen sufficiency or deficiency.

17. The method of claim 16 wherein said crop is corn at V6 through V10 development stage.

18. The method of claim 1 wherein said non-legume plant is selected from the group consisting of corn, wheat, rice, cotton, potatoes sugarcane, turfgrass or forage grass species.

19. The method of claim 1 further comprising the step of estimating potential yield of said crop from said image as a function of said dark green color index.

20. The method of claim 1 further comprising the step of transmitting said dark green color index through a network connection.

21. The method of claim 1 further comprising the step of transmitting said nitrogen fertilization rate through a network connection.

22. The method of claim 1 further comprising the step of providing a recommended amount of nitrogen per unit area to be applied at in-season based on said nitrogen fertilization rate in order to maximize said predetermined yield potential for said crop.

23. The method of claim 1 further comprising the step of providing a recommended amount of nitrogen per unit area to be applied during mid-season at V6 through V10 development stage in order to maximize said predetermined yield potential for a corn crop based on said nitrogen fertilization rate.

24. The method of claim 1 wherein said step of determining said nitrogen fertilization rate further comprises the step of providing a mathematical model forming a yield potential response curve as a function of said nitrogen fertilization rate.

25. The method of claim 24 wherein said model of said yield potential response curve is a quadratic expression.

26. The method of claim 25 wherein said quadratic expression is a function of ƒ

(x)=ax²+bx+c, where ƒ

(x) is equal to said predetermined yield potential, x is equal to said nitrogen fertilization rate, a is equal to a quadratic coefficient to said nitrogen fertilization rate, b is equal to a linear coefficient to said nitrogen fertilization rate, and c is equal to said predetermined yield potential when said nitrogen fertilization rate is equal to 0.

27. The method of claim 1 wherein said step of determining said nitrogen fertilization rate further comprises the step of performing an algorithm providing said nitrogen fertilization rate as a function of said dark green color index.

28. The method of claim 27 wherein said algorithm is a quadratic relationship of said nitrogen fertilization rate with respect to said dark green color index.

29. A system, comprising:

a portable electronic device comprising a camera for taking a digital image of a vegetative plant; and

a processor in communication with said portable electronic device, said processor operable for calculating a nitrogen fertilization rate to achieve a predetermined yield potential for said plant as a function of a corrected dark green color index of said image, where said function is in the form of ƒ

(x)=ax²+bx+c, where ƒ

(x) is equal to said predetermined yield potential, x is equal to said nitrogen fertilization rate, a is equal to a quadratic coefficient to said nitrogen fertilization rate, b is equal to a linear coefficient to said nitrogen fertilization rate, and c is equal to said predetermined yield potential when said nitrogen fertilization rate is equal to 0.

30. The system of claim 29 further comprising a memory accessible by said processor for storing corrected dark green color indexes.

31. The system of claim 29 further comprising an application program loaded on said portable electronic device.

32. The system of claim 29 further comprising a central processing unit communicably attached to said electronic device via a network connection for performing an algorithm to estimate said nitrogen fertilization rate based on said corrected dark green color index.

33. The system of claim 29 further comprising a comparative standard to account for differences in cameras or lighting conditions or both and a contrasting standard having a color in a portion of the visible spectrum away from the visible spectrum of the color of said plant.

34. The system of claim 33 wherein said comparative standard has a predetermined shape and a color representing a color value ranging from severely nitrogen deficient to nitrogen sufficient of said plant.

35. The system of claim 34 wherein said comparative standard further comprises a first comparative standard having a yellow color representing a severely nitrogen deficient leaf and a second comparative standard having a dark green color representing a nitrogen sufficient leaf.

36. A process for providing an in-season nitrogen fertilization rate, said process comprising the steps of:

a. receiving a corrected dark green color index of a digital image of a crop;

b. determining said nitrogen fertilization rate for said crop from said corrected dark green color index of said image using a quadratic function in the form of ƒ

(x)=ax²+bx+c, where ƒ

(x) is equal to said predetermined yield potential, x is equal to said nitrogen fertilization rate, a is equal to a quadratic coefficient to said nitrogen fertilization rate, b is equal to a linear coefficient to said nitrogen fertilization rate, and c is equal to said predetermined yield potential when said nitrogen fertilization rate is equal to 0; and

c. providing said nitrogen fertilization rate to achieve said predetermined yield potential for said crop.

37. The process of claim 36 further comprising the step of acquiring said digital image of a colored leaf from said crop, a comparative standard to account for differences in cameras or lighting conditions or both, and a contrasting standard having a color in a portion of the visible spectrum away from the visible spectrum of the color of said leaf.

38. The process of claim 37 wherein said comparative standard is a plurality of standardized color disks having a predetermined shape and a color representing a color value ranging from severely nitrogen deficient to nitrogen sufficient of said crop.

39. The process of claim 38 wherein said standardized color disks further comprise a first standardized color disk having a yellow color representing a severely nitrogen deficient leaf and a second standardized disk having a dark green color representing a nitrogen sufficient leaf.

40. The process of claim 37 wherein said color of said contrasting standard is pink.

41. The process of claim 37 further comprising the steps of:

a. calculating a dark green color index of said leaf in said image;

b. calculating a dark green color index of said comparative standard in said image; and

c. calculating said corrected dark green color index from said dark green color index of said leaf and said dark green color index of said comparative standard.

42. The process of claim 41 wherein said step of calculating said dark green color index of said leaf in said image and/or said step of calculating said dark green color index of said comparative standard in said image further comprises the steps of:

a. obtaining absolute red, green and blue values in said image;

b. converting said absolute red, green and blue values to percentage red, green and blue values in said image;

c. converting said percentage red, green and blue values to absolute hue, saturation and brightness values in said image;

d. calculating average hue, saturation and brightness values from said absolute hue, saturation and brightness values in said image; and

e. converting said average hue, saturation and brightness values to said dark green color index in said image.

43. The process of claim 42 further comprising converting said average hue, saturation and brightness values to said dark green color index in said image using the following equation:

DGCI=[(H−

60)/60+(1−

S)+(1−

B)]/3

where DGCI is equal to dark green color index, H is equal to said average hue value, S is equal to said average saturation value, and B is equal to said average brightness value.

44. The process of claim 43 wherein said dark green color index in said image encompasses a dark green color on a scale of zero (0) to one (1) with values closer to one (1) representing a darker green.

45. The process of claim 37 further comprising the step of determining nitrogen sufficiency or deficiency of said leaf in said image from said dark green color index.

46. The process of claim 45 further comprising the step of estimating potential yield of said crop from said image based on said leaf nitrogen sufficiency or deficiency.