DETERMINING FIELD CHARACTERISTICS USING OPTICAL RECOGNITION

• US 20160029545A1
• Filed: 07/20/2015
• Published: 02/04/2016
• Est. Priority Date: 08/01/2014
• Status: Active Grant

• Current Assignee: AGCO Corporation
• Original Assignee: AGCO Corporation
• Inventors: Matthews, Paul Ross
• Granted Patent: US 10,390,472 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A01B 69/008 automatic
• CPC Class Codes: A01C 21/007 Determining fertilization requirements
• CPC Class Codes: G01C 21/005 with correlation of navigation data from several sources, e.g. map or contour matching G01C21/30 takes precedence
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06V 20/188 Vegetation
• CPC Class Codes: G06V 30/422 Technical drawings; Geographical maps

Abstract

In one embodiment, a method for automated guidance comprising receiving an image of a field; identifying one or more characteristics of the field in the image; determining one or more geographic locations corresponding to the one or more characteristics of the field in the image; determining a path to be followed in the field using the one or more geographic locations; and automatically guiding the machine to follow the path.

Claims

1. A non-transitory machine-readable storage medium having instructions stored therein which, when executed by one or more processors, cause the one or more processors to:

receive an image of a field;

identify one or more characteristics of the field in the image; and

use the one or more characteristics of the field to enable a machine to perform precision farming.

2. The non-transitory machine-readable storage medium of claim 1, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:

determine a location of the machine;

determine one or more geographic locations corresponding to the one or more characteristics of the field in the image;

identify one field among a plurality of fields in the image that corresponds to the location of the machine; and

determine the one or more geographic locations of the identified one field.

3. The non-transitory machine-readable storage medium of claim 1, wherein the one or more characteristics of the field include a center of the field, a boundary of the field, or a combination of the center of the field and the boundary of the field.

4. The non-transitory machine-readable storage medium of claim 3, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to identify the center by identifying a geometric center of a boundary defining the field in the image.

5. The non-transitory machine-readable storage medium of claim 4, wherein the image comprises pixel differences representing the field that indicate a fully-circular outline or a partially-circular outline.

6. The non-transitory machine-readable storage medium of claim 5, wherein responsive to identifying multiple boundaries, the instructions, when executed by the one or more processors, further cause the one or more processors to present an operator with selectable choices on a user interface corresponding to the multiple boundaries.

7. The non-transitory machine-readable storage medium of claim 3, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to identify the center by identifying pixel differences indicating a center of a center-pivot irrigation system in the field.

8. The non-transitory machine-readable storage medium of claim 7, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to identify the center of the center-pivot irrigation system by identifying from the pixel differences in the image a pivot arm and an end of the pivot arm corresponding to the center.

9. The non-transitory machine-readable storage medium of claim 1, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to determine one or more geographic locations by accessing coordinates from data associated with the image and corresponding to the identified one or more characteristics.

10. The non-transitory machine-readable storage medium of claim 9, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to determine a machine path by determining multiple concentric circles of the machine path centered at the coordinates and automatically guide the machine to follow the path.

11. The non-transitory machine-readable storage medium of claim 1, wherein the instructions, when executed by the one or more processors, further cause the one or more processors to identify the one or more characteristics of the field in the image based on user input.

12. The non-transitory machine-readable storage medium of claim 1, wherein the one or more characteristics of the field in the image are identified based on optical recognition.

13. A method for automated guidance, the method comprising:

receiving an image of a field;

identifying one or more characteristics of the field in the image;

determining one or more geographic locations corresponding to the one or more characteristics of the field in the image;

determining a path to be followed in the field using the one or more geographic locations; and

automatically guiding the machine to follow the path.

14. The method of claim 13, further comprising:

determining a location of the machine;

identifying one field among a plurality of fields in the image that corresponds to the location of the machine; and

determining the one or more geographic locations of the identified one field.

15. The method of claim 13, wherein identifying the one or more characteristics of the field include identifying pixel differences indicating a center pivot irrigation system, the center pivot irrigation system comprising a pivot arm and an end of the pivot arm corresponding to the center.

16. The method of claim 13, wherein identifying the one or more characteristics of the field include identifying pixel differences indicating a geometric center of a boundary defining the field in the image, wherein the image comprises a fully-circular outline or a partially-circular outline.

17. The method of claim 13, wherein determining the one or more geographic locations comprises determining coordinates of the identified one or more characteristics based on data associated with the image.

18. A system, comprising:

a machine comprising a drive system;

a position determining device configured to detect a geographic location of the machine; and

a

one or more computing devices configured to;

access an aerial or satellite image of one or more fields;

identify from pixel differences in the image a center of a center pivot irrigation system that is closest to the machine;

determine coordinates for the identified center; and

cause the drive system to automatically navigate the machine according to a center pivot wayline that is based on the determined coordinates.

19. The system of claim 18, further comprising a user interface, wherein the one or more computing devices are configured to access, identify, determine, and cause based on receiving user input corresponding to selection of a center pivot wayline option among a plurality of wayline type options.

20. The system of claim 18, wherein responsive to detecting a field boundary, the one or more computing devices are configured to access, identify, determine, and cause based on automatic selection of a center pivot wayline option among a plurality of wayline type options.