Process for normalizing images or other data layers

• US 8,135,178 B2
• Filed: 04/10/2007
• Issued: 03/13/2012
• Est. Priority Date: 04/10/2007
• Status: Active Grant

• Current Assignee: Deere & Company
• Original Assignee: Deere & Company
• Inventors: Hendrickson, Larry Lee, Clark, Rendell Bruce
• Primary Examiner(s): Bali, Vikkram
• Assistant Examiner(s): FUJITA, KATRINA R
• Application Number:
  US11/733,389
• Publication Number:
  US 20080253618A1
• Time in Patent Office: 1,799 Days
• Field of Search: 382/110, 702/2, 702/5, 47/581.R
• US Class Current: 382/110
• CPC Class Codes: G06V 20/13 Satellite images

Abstract

A method of processing vegetation data including the steps of identifying data relating to an agricultural field, segregating areas of predetermined development patterns and prescribing application rates of an agricultural compound. The identifying step includes identifying data relating to an agricultural field representative of areas of predetermined development patterns of vegetation in the field. The segregating step includes segregating the areas of the predetermined development patterns thereby defining segregated areas, other areas in the field being non-segregated areas. The prescribing step including prescribing application rates of an agricultural compound to the non-segregated areas dependent on at least one attribute determined from the data.

Claims

1. A method of processing image data on vegetation in an agricultural field, the method comprising:

identifying image data relating to an agricultural field representative of areas of predetermined development patterns of vegetation in the field, the predetermined development patterns comprising a higher vegetation area of weedy patches;

segregating said areas of the predetermined development patterns with said weedy patches thereby defining segregated areas by overlaying a Normalized Difference Vegetation Index (NDVI) with a color infrared layer to select pixels with a geometric pattern or spatial distribution indicative of the weedy patches, other areas in the field being non-segregated areas;

normalizing said image data within said non-segregated area using a best crop area as a reference crop area that has sufficient nitrogen to identify a reference pixel within the reference crop area such that the other pixel data in the non-segregated crop area has normalized pixel values with reference to the reference pixel; and

prescribing application rates of an agricultural compound to said non-segregated areas dependent on a crop canopy color determined from said normalized image data based on the NDVI.

2. The method of claim 1, wherein said segregated areas include excessive canopy areas.

3. The method of claim 1, wherein said reference crop area is a selected attribute of said pixel data defining a reference pixel value associated with some portion of the agricultural field with sufficient nitrogen.

4. The method of claim 1, wherein said normalizing step includes dividing pixel data in said non-segregated areas by said reference pixel value and multiplying by 100 to produce a normalized pixel value for each pixel as also defined by the equation:

Normalized pixel value=pixel value/reference pixel value×

100.

5. The method of claim 4, wherein said prescribing step uses said normalized pixel values to determine said application rates.

6. The method of claim 5, further comprising applying said agricultural compound to said non-segregated areas dependent on said application rates prescribed to said non-segregated areas.

7. The method of claim 6, further comprising assigning at least one application rate to said segregated areas.

8. The method of claim 7, further comprising applying said agricultural compound to said segregated areas dependent on said application rates assigned to said segregated areas.

9. The method of claim 8, further comprising masking selected pixels of said data from being used by said identifying step, said segregating step and said prescribing step.

10. The method of claim 1, further comprising prioritizing a plurality of fields after applying said steps of identifying, segregating and prescribing to each of said plurality of fields.

11. The method according to claim 1 wherein, in the segregating step, the geometric pattern or spatial distribution indicative of the weedy patches comprises a nonrectangular geometric pattern or nonrectangular spatial distribution.

12. A method of processing vegetation pixel data, the method comprising:

masking selected pixels from consideration;

identifying unselected pixels relating to an agricultural field representative of areas of predetermined development patterns of vegetation in the field, the predetermined development patterns comprising a higher vegetation area of weedy patches;

segregating said areas of predetermined development patterns with said weedy patches thereby defining segregated areas by overlaying a Normalized Difference Vegetation Index (NDVI) with a color infrared layer to select pixels with a geometric pattern or spatial distribution indicative of the weedy patches, other areas in the field being non-segregated areas;

normalizing said image data within said non-segregated area using a best crop area as a reference crop area that has sufficient nitrogen to identify a reference pixel within the reference crop area such that the other pixel data in the non-segregated crop area has normalized pixel values with reference to the reference pixel; and

prescribing application rates of an agricultural compound to said non-segregated areas dependent on a crop canopy color determined from said other pixels based on the NDVI.

13. The method of claim 12, wherein said segregated areas include excessive canopy areas.

14. The method of claim 12, further comprising selecting at least one reference crop pixel in the non-segregated area representative of the best crop area having sufficient nitrogen.

15. The method of claim 14, further comprising normalizing said data within said non-segregated area using said at least one reference crop pixel as a standard, where the at least one reference crop pixel is associated with some portion of the agricultural field with sufficient nitrogen.

16. The method of claim 15, wherein said normalizing step includes dividing pixel data in said non-segregated areas by said reference crop pixel and multiplying by 100 to produce a normalized pixel value for each of said other pixels as also defined by the equation:

Normalized pixel value=pixel/reference crop pixel×

100.

17. The method of claim 16, wherein said prescribing step uses said normalized pixel values to determine said application rates.

18. The method of claim 17, further comprising applying said agricultural compound to said non-segregated areas dependent on said application rates prescribed to said non-segregated areas.

19. The method of claim 18, further comprising assigning at least one application rate to said segregated areas.

20. The method of claim 19, further comprising applying said agricultural compound to said segregated areas dependent on said application rates assigned to said segregated areas.