IP Library Granted Patent US 11,087,132
Granted Patent B2
US 11,087,132 · App. 16/331,010 · Granted Aug 10, 2021

Systems and methods for mapping emerged plants

Inventors: Jeremy Baynes (Raleigh, NC); Ali Punjani (Raleigh, NC); Edgar Lobaton (Raleigh, NC); Jason San Souci (Raleigh, NC); Thomas Haun (Raleigh, NC); Pat Lohman (Raleigh, NC); Andrew Slater (Raleigh, NC); Matt Mead (Raleigh, NC)
Assignee: Precision Hawk USA, Inc.
G06K9/00657A01B49/06A01B79/005A01C21/005A01G25/16G06T3/4038G05B15/02G06Q10/063G06Q50/02G06T2207/20221
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,087,132
App. No.
16/331,010
Granted
Aug 10, 2021
Kind
B2
Abstract

A system uses an optical sensor and an image processing apparatus to map emerged plants in a field. The optical sensor collects at least one image of a field of emerged plants. The image processing apparatus analyzes the image to detect areas of vegetation and creates a vegetation map indicative of the detected areas. The image processing element then analyzes the vegetation map to identify emerged plants within the image and creates at least map indicating locations of the emerged plants in the field. Such map may be used to make efficient crop management decisions based on the actual layout of emerged plants in the field.

Claims (70)

1. A method, comprising:

combining a plurality of images of a field to form a composite image of the field;

analyzing, by a processor device, the composite image to detect areas of vegetation within the composite image;

defining, by the processor device, a vegetation map based on the composite image, the vegetation map having a plurality of pixels corresponding to areas of the field, each of the pixels of the vegetation map indicating whether vegetation is detected by the processor device in a corresponding area of the field;

identifying, by the processor device, rows of vegetation within the vegetation map;

analyzing, by the processor device, each of the identified rows to identify emerged plants within the identified rows, by:

determining a seed spacing within the identified rows;

determining a size of a first plant based on the vegetation map;

based on the seed spacing and the size of the first plant, determining that the first plant is an emerged plant;

determining a size of a second plant based on the vegetation map; and

based on the seed spacing and the size of the second plant, determining that the second plant is not an emerged plant; and

defining, by the processor device, at least one map of the field based on analyzing each of the identified rows, the at least one map indicating locations of the identified emerged plants within the field.

2. The method of claim 1 , further comprising:

counting, by the processor device, a number of emerged plants within the identified rows; and

providing an output indicative of the counting.

3. The method of claim 1 , further comprising displaying the at least one map.

4. The method of claim 1 , further comprising controlling fertilization or watering of the field based on the at least one map.

5. The method of claim 1 , wherein analyzing the composite image comprises:

comparing a color value of at least one pixel of the composite image to a predefined threshold; and

determining whether the at least one pixel of the composite image corresponds to an area of vegetation based on the comparing.

6. The method of claim 1 , further comprising adjusting color values of the composite image thereby compensating for sun-angle variation.

7. The method of claim 1 , further comprising:

identifying, by the processor device, rows of vegetation within the composite image; and

analyzing, by the processor device, the identified rows of vegetation within the composite image to determine a row angle and a row spacing,

wherein identifying the rows of vegetation within the vegetation map is based on the row angle and the row spacing.

8. The method of claim 1 , further comprising receiving an input indicative of a seed spacing for emerged plants, wherein the analyzing each of the identified rows is based on the input.

9. The method of claim 8 , wherein analyzing each of the identified rows comprises:

identifying a plurality of contiguous vegetation pixels in the vegetation map; and

identifying a plurality of emerged plants within the contiguous vegetation pixels based on the input.

10. A system, comprising:

a memory; and

a processor device coupled to the memory, the processor device configured to:

detect areas of vegetation within image data comprising a composite image of a field;

define a vegetation map having a plurality of pixels corresponding to areas of the field, each of the pixels of the vegetation map indicating whether the processor device detected vegetation in a corresponding area of the field;

identify rows of vegetation within the vegetation map and identify emerged plants within the identified rows, by at least in part:

identifying, based on the image data, a plurality of sub-regions;

determining, based on the sub-regions, an average crop row angle, by:

determining crop row angles of the plurality of sub-regions; and

determining the average crop row angle based on an average of the crop row angles;

determining a primary crop row based in part on the average crop row angle, the primary crop row being a row of vegetation of the rows of vegetation having a crop row angle closest to the average crop row angle;

determining a next crop row that is adjacent the primary crop row; and

determining a crop row separation distance between the primary crop row and the next crop row; and

define at least one map of the field, wherein the at least one map indicates locations of the identified emerged plants within the field.

11. The system of claim 10 , wherein the at least one map is segmented into a plurality of cells, and wherein the at least one map indicates concentrations of the emerged plants within the cells.

12. The system of claim 10 , wherein the processor device is further configured to:

count a number of emerged plants within the identified rows; and

provide an output indicating a number of emerged plants within at least one area of the field.

13. The system of claim 10 , wherein the processor device is configured to compare a color value of at least one pixel of the composite image to a predefined threshold; and

determine whether the at least one pixel of the composite image corresponds to an area of vegetation based on a comparison of the color value to the predefined threshold.

14. The system of claim 10 , wherein the processor device is configured to:

receive an input indicative of seed spacing for the emerged plants; and

identify the emerged plants based on the input.

15. The system of claim 14 , wherein the processor device is configured to identify a plurality of contiguous vegetation pixels in the vegetation map and to identify a plurality of emerged plants within the contiguous vegetation pixels based on the input.

16. A method, comprising:

analyzing, by a processor device, color values of an image of a field;

detecting, by the processor device, areas of vegetation within the image based on the analyzing the color values;

defining, by the processor device, a vegetation map based on the detecting, the vegetation map having a plurality of pixels corresponding to areas of the field, each of the pixels of the vegetation map indicating whether vegetation is detected by the processor device in a corresponding area of the field, each pixel being identified as either a vegetation pixel or a non-vegetation pixel, each pixel identified as a vegetation pixel being assigned a same vegetation value, and each pixel identified as a non-vegetation pixel being assigned a same non-vegetation value;

identifying, by the processor device, emerged plants in the field based on the vegetation map; and

defining, by the processor device, at least one map of the field based on the identifying, the at least one map indicating a number of the identified emerged plants within a geographic region of the field.

17. The method of claim 16 , wherein analyzing the color values comprises comparing the color values to a predefined threshold.

18. The method of claim 16 , further comprising receiving an input indicative of a seed spacing for the emerged plants, wherein the identifying is based on the input.

19. The method of claim 16 , wherein the at least one map is segmented into a plurality of cells, and wherein the at least one map indicates a number of the identified emerged plants within at least one of the cells.

20. The method of claim 16 , further comprising:

identifying, by the processor device, rows of vegetation within the image; and

analyzing, by the processor device, the identified rows to determine a row angle of the rows and a row spacing between the rows.

21. The method of claim 20 , further comprising:

segmenting, by the processor device, the vegetation map into row segments based on the row angle and the row spacing; and

analyzing, by the processor device, the row segments,

wherein the identifying the rows of vegetation is based on analyzing the row segments.

22. The method of claim 21 , further comprising transforming, by the processor device, the image into Fourier Space, wherein identifying the rows of vegetation is based on the transforming.

Assignments (2)
SECURITY INTEREST Recorded Oct 4, 2019
From: PRECISIONHAWK, INC.; PRECISION HAWK USA, INC.
To: EASTWARD FUND MANAGEMENT, LLC
Reel/Frame 050628/0910 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 6, 2019
From: BAYNES, JEREMY; PUNJANI, ALI; LOBATON, EDGAR; SAN SOUCI, JASON; HAUN, THOMAS; LOHMAN, PAT; SLATER, ANDREW; MEAD, MATT
To: PRECISION HAWK USA, INC.
Reel/Frame 048519/0982 →
Continuity (1)
Related Publication 20190258859A1 · Aug 22, 2019
Cited By (1)
US 12,236,679