Crop stand analysis

• US 9,489,576 B2
• Filed: 03/25/2015
• Issued: 11/08/2016
• Est. Priority Date: 03/26/2014
• Status: Active Grant

• Current Assignee: Aglytix Inc.
• Original Assignee: F12 Solutions LLC
• Inventors: Johnson, Jerome D., Nigon, Tyler John, Abouali, Mohammad
• Primary Examiner(s): NAKHJAVAN, SHERVIN K
• Application Number:
  US14/668,249
• Publication Number:
  US 20150278640A1
• Time in Patent Office: 594 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: A01B 79/005 Precision agriculture
• CPC Class Codes: A01C 21/005 Following a specific plan, e.g. pattern
• CPC Class Codes: G01C 11/04 Interpretation of pictures
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 2207/30128 Food products
• CPC Class Codes: G06T 2207/30188 Vegetation; Agriculture
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 20/188 Vegetation

Abstract

In one example, a method includes receiving, by a computing device, data for a region of interest that includes growing crops. The received data for the region of interest can include image data for the region of interest. The method further includes identifying, by the computing device based on the received image data, rows of crops within the region of interest. The method further includes determining, by the computing device based on the received data for the region of interest associated with portions of the region of interest included in the identified rows of crops and excluding portions of the region of interest outside the identified rows of crops, a stand status of the growing crops within the region of interest. The stand status includes a quantity status corresponding to a population of crops within the region of interest.

Claims

1. A method comprising:

receiving, by a computing device, data for a region of interest that includes growing crops, wherein the received data for the region of interest comprises image data for the region of interest;

determining a crop mask for the region of interest, the crop mask comprising a plurality of elements, each of the plurality of elements corresponding to a pixel of the image data for the region of interest and categorized as one of a vegetation element indicating that a corresponding pixel of the received image data is associated with vegetation within the region of interest and a non-vegetation element indicating that a corresponding pixel of the received image data is associated with an absence of vegetation within the region of interest; and

determining the rows of crops within the region of interest based on the determined crop mask; and

determining, by the computing device based on the received data for the region of interest associated with portions of the region of interest included in the identified rows of crops and excluding portions of the region of interest outside the identified rows of crops, a stand status of the growing crops within the region of interest, the stand status comprising a quantity status corresponding to a population of crops within the region of interest.

2. The method of claim 1,

wherein a color of each of the pixels of the received image data for the region of interest is represented by a red value indicating an intensity of a contribution of a red color to the color of the respective pixel, a green value indicating an intensity of a contribution of a green color to the color of the respective pixel, and a blue value indicating an intensity of contribution of a blue color to the color of the respective pixel;

and

wherein determining the crop mask for the region of interest comprises determining the crop mask, based on the green value and excluding the red value and the blue value, of each of the pixels of the received image data.

3. The method of claim 2, wherein determining the crop mask for the region of interest based on the green value of each of the pixels of the received image data comprises:

comparing the green value of each of the pixels to a threshold value;

determining that the respective pixel corresponds to vegetation within the region of interest based on determining that the green value of the respective pixel exceeds the threshold value; and

determining that the respective pixel corresponds to an absence of vegetation within the region of interest based on determining that the green value of the respective pixel does not exceed the threshold value.

4. The method of claim 3, wherein determining the threshold value comprises determining, via Otsu'"'"'s method, the threshold value so as to minimize a variance between the threshold value and the green values of each of the pixels of the received image data for the region of interest.

5. The method of claim 1, wherein determining the rows of crops within the region of interest based on the determined crop mask comprises:

determining a plurality of starting locations of the rows of crops within the region of interest, each of the plurality of starting locations corresponding to at least one vegetation element of the crop mask;

determining a row angle of the rows of crops within the region of interest, the row angle measured relative to an orientation direction of the received image data for the region of interest; and

determining the rows of crops as extending from each of the plurality of starting locations in a direction of the row angle.

6. The method of claim 5, wherein determining the row angle of the rows of crops within the region of interest comprises:

determining a number of vegetation elements of the crop mask corresponding to each of a plurality of candidate row angles;

determining a dominant row angle as one of the plurality of candidate row angles corresponding to a greatest number of vegetation elements of the crop mask; and

determining the row angle of the rows of crops within the region of interest as the dominant row angle.

7. The method of claim 6, wherein determining the number of vegetation elements of the crop mask corresponding to each of the plurality of candidate row angles comprises determining the number of vegetation elements of the crop mask corresponding to each of the plurality of candidate row angles via a Hough transform of the crop mask.

8. The method of claim 1, further comprising:

segregating, by the computing device, data representative of the growing crops into a plurality of groups based on one or more parameters of a category of the received data for the region of interest;

wherein determining the stand status of the growing crops within the region of interest comprises determining the stand status for each of the plurality of groups; and

wherein the method further comprises;

comparing, by the computing device, the stand status of each of the plurality of groups to at least one benchmark criterion; and

outputting, by the computing device, an indication of the comparison.

9. The method of claim 8,

wherein the quantity status indicates an expected yield of the growing crops within each respective group;

wherein the at least one benchmark criterion includes a benchmark yield criterion; and

wherein comparing the stand status of each of the plurality of groups to at least one benchmark criterion comprises comparing the expected yield of the growing crops within each respective group to the benchmark yield criterion to determine an expected yield loss of the growing crops within each respective group.

10. The method of claim 9, wherein receiving the data for the region of interest comprises receiving first data for the region of interest, the method further comprising:

receiving, by the computing device, second data for the region of interest, the second data including data representative of a harvested yield of the growing crops;

comparing, by the computing device, the data representative of the harvested yield to the benchmark yield criterion to determine a calculated yield loss of the growing crops within each respective group; and

outputting, by the computing device, an indication of the comparison of the calculated yield loss of the growing crops within each respective group.

11. The method of claim 8,

wherein the category of received data comprises a seed treatment category;

wherein the one or more parameters of the seed treatment category identify a type of treatment associated with the growing crops; and

wherein segregating the data representative of the growing crops into the plurality of groups comprises segregating the data representative of the growing crops into the plurality of groups according to a seed treatment associated with each of the growing crops.

12. The method of claim 8,

wherein the category of received data comprises a soil compaction category;

wherein the one or more parameters of the soil compaction category indicate proximity of the growing crops to a path of a support structure of equipment used to plant the growing crops; and

wherein segregating the data representative of the growing crops into the plurality of groups comprises segregating the data representative of the growing crops into the plurality of groups according to a proximity of each of the growing crops to the path of the support structure of the equipment used to plant the growing crops.

13. The method of claim 8,

wherein the category of received data comprises a soil type category;

wherein the one or more parameters of the soil type category indicate a type of soil associated with the growing crops; and

wherein segregating the data representative of the growing crops into the plurality of groups comprises segregating the data representative of the growing crops into the plurality of groups according to a soil type associated with each of the growing crops.

14. The method of claim 8,

wherein the category of received data comprises a seed type category;

wherein the one or more parameters of the seed type category indicate a type of seed associated with the growing crops; and

wherein segregating the data representative of the growing crops into the plurality of groups comprises segregating the data representative of the growing crops into the plurality of groups according to a seed type associated with each of the growing crops.

15. The method of claim 8,

wherein the category of received data comprises a drain tile category;

wherein the one or more parameters of the drain tile category indicate proximity of the growing crops to drain tail; and

wherein segregating the data representative of the growing crops into the plurality of groups comprises segregating the data representative of the growing crops into the plurality of groups according to a proximity of each of the growing crops to drain tile.

16. The method of claim 8,

wherein the category of received data comprises a ground surface residue category;

wherein the one or more parameters of the ground surface residue category indicate an amount of ground surface residue associated with the growing crops; and

wherein segregating the data representative of the growing crops into the plurality of groups comprises segregating the data representative of the growing crops into the plurality of groups according to an amount of ground surface residue associated with each of the growing crops.

17. The method of claim 8,

wherein the category of received data comprises a planter equipment speed category;

wherein the one or more parameters of the planter equipment speed category indicate a planter equipment speed associated with the growing crops; and

wherein segregating the data representative of the growing crops into the plurality of groups comprises segregating the data representative of the growing crops into the plurality of groups according to a speed associated with each of the growing crops of the planter equipment used to plant the growing crops.

18. A system comprising:

a computing device comprising at least one processor; and

computer-readable memory encoded with instructions that, when executed by the at least one processor, cause the computing device to;

receive data for a region of interest that includes growing crops, wherein the received data for the region of interest comprises image data for the region of interest;

determine a crop mask for the region of interest, the crop mask comprising a plurality of elements, each of the plurality of elements corresponding to a pixel of the image data for the region of interest and categorized as one of a vegetation element indicating that a corresponding pixel of the received image data is associated with vegetation within the region of interest and a non-vegetation element indicating that a corresponding pixel of the received image data is associated with an absence of vegetation within the region of interest; and

determine the rows of crops within the region of interest based on the determined crop mask; and

determine, based on the received data for the region of interest associated with portions of the region of interest included in the identified rows of crops and excluding portions of the region of interest outside the rows of crops, a stand status of the growing crops within the region of interest, the stand status comprising a quantity status corresponding to a population of crops within the region of interest.

19. A method comprising:

receiving, by a computing device, data for a region of interest that includes growing crops, wherein the received data for the region of interest comprises image data for the region of interest;

segregating, by the computing device, the image data for the region of interest into a plurality of tiles, each tile from the plurality of tiles including image data corresponding to a different geographical portion of the region of interest;

determining, by the computing device, a plurality of crop masks, each of the plurality of crop masks corresponding to one of the plurality of tiles and including a plurality of elements, each of the plurality of elements corresponding to a pixel of image data included in the respective tile and categorized as one of a vegetation element indicating that the respective pixel is associated with vegetation within the respective tile and a non-vegetation element indicating that the respective pixel is associated with an absence of vegetation within the respective tile;

determining, by the computing device for each of the plurality of crop masks, a number of vegetation elements of the respective crop mask corresponding to each of a plurality of candidate row angles;

determining, by the computing device for each of the plurality of crop masks, a dominant row angle as one of the plurality of candidate row angles for the respective crop mask corresponding to a greatest number of vegetation elements;

identifying, by the computing device for each of the plurality of tiles, rows of crops within the geographical portion of the region of interest corresponding to the respective tile based on the determined dominant row angle of the crop mask corresponding to the respective tile; and

determining, by the computing device, a stand status of the growing crops within the region of interest based on the received data for the region of interest associated with geographical portions of the region of interest included in the identified rows of crops within each of the plurality of tiles and excluding geographical portions of the region of interest outside the identified rows of crops.