System and method for automated odometry calibration for precision agriculture systems

Patent metadata

Field	Value
Publication number	US-9717171-B2
Application number	US-201514629361-A
Country	US
Kind code	B2
Filing date	Feb 23, 2015
Priority date	Mar 7, 2013
Publication date	Aug 1, 2017
Grant date	Aug 1, 2017

Abstract

A method including: recording a first image of a first field region; automatically treating a plant within the first region in-situ based on the first image; automatically verifying the plant treatment with a second image of the first region; and automatically treating a second region concurrently with treatment verification.

First claim

We claim:

1. A method for in-situ precision agriculture calibration of a device during operation of the device within a field, the method comprising:
capturing a first image of a first field region with a first camera of the device;
setting, by a computer of the device, a target treatment boundary location in the first field region based on the first image, the target treatment boundary location set in the first field region between a first treatment area and a second treatment area;
controlling, by the computer, a treatment mechanism of the device to apply the first treatment to the first treatment area;
controlling, by the computer, the treatment mechanism of the device to apply the second treatment to the second treatment area at a transition time, wherein the transition time is based on the target treatment boundary location;
capturing a second image of a second field region with a second camera of the device after the transition time, wherein the second field region overlaps with at least a portion of the first field region, the overlapped portion including the target treatment boundary location, and at least a portion of the first and second treatment areas, and the second camera being fixed on the device a predetermined separation distance away from the first camera along a traversal axis of the device;
determining, by the computer, an actual treatment boundary location based on the second image and a motion of the device, wherein the actual treatment boundary location is a location in the first field region where application of the second treatment begins; and
calibrating, by the computer, the device based on the target treatment boundary location and the actual treatment boundary location.

2. The method of claim 1 , wherein:
selecting the transition time comprises selecting, by the computer, the transition time based on a first set of values for a set of calibration parameters; and
calibrating the device comprises determining, by the computer, a second set of values for the set of calibration parameters.

3. The method of claim 2 , wherein the second set of values for the set of calibration parameters are determined from a pixel shift value between the first image and the second image, an estimated traversed distance between a first time when the first image is captured and a second time when the second image is captured, and a fixed distance between the first and second cameras.

4. The method of claim 3 , wherein determining the estimated traversed distance comprises determining, by the computer, a number of wheel rotations using a follow-on wheel of known radius and a rotary encoder coupled to the wheel.

5. The method of claim 3 , wherein the set of calibration parameters comprise a number of pixels corresponding to an actual unit of length, a position correction factor, a camera-to-treatment mechanism distance, and a timing delay.

6. The method of claim 3 , wherein determining the pixel shift value comprises:
identifying, by the computer, a set of common reference features between the first image and the second image; and
determining, by the computer, an amount of pixel shift between the first image and the second image based on positions of the common reference features within the first image and the second images.

7. The method of claim 6 , wherein the reference features comprise features of the field.

8. The method of claim 1 , further comprising:
identifying, by the computer, a first plant within the first region from the first image; and
determining, by the computer, the first treatment for the first plant before determining a target treatment boundary location.

9. The method of claim 8 , further comprising:
identifying, by the computer, a second plant proximal the first plant along a travel path of the device; and
determining, by the computer, the second treatment for the second plant different from the first treatment;
wherein the determined target treatment boundary location is located between the first plant and the second plant.

10. The method of claim 1 , further comprising monitoring, by the computer, the device based on data present in the second image.

11. The method of claim 10 , wherein monitoring the device with the second image comprises:
determining, by the computer, a set of camera-to-treatment mechanism distance values and a set of timing delay values based on previously recorded image pairs recorded by the device, wherein each of the previously recorded image pairs comprises an image from the first camera and an image from the second camera;
comparing, by the computer, a camera-to-treatment mechanism distance value and a timing delay value, determined based on the first image and the second image, to the set of prior camera-to-treatment mechanism distance values and the set of timing delay values; and
detecting, by the computer, a treatment mechanism failure in response to the camera-to-treatment mechanism distance value and a timing delay value deviating from the set of prior camera-to-treatment mechanism distance values and the set of timing delay values beyond a threshold deviation.

12. The method of claim 11 , wherein the treatment mechanism comprises a solenoid, wherein detecting the treatment mechanism failure comprises detecting solenoid sticking.

13. The method of claim 10 , wherein monitoring the precision agriculture system with the second image comprises detecting, by the computer, a system failure in response to a difference between the target treatment boundary location and the actual treatment boundary location exceeding a threshold difference.

14. The method of claim 13 , wherein the threshold difference is half an inch.

15. The method of claim 1 , wherein the second treatment comprises not applying a treatment material to the second treatment area.

16. A device for in-situ precision agriculture calibration during operation of the device within a field, the device comprising:
a first camera;
a second camera;
a treatment mechanism;
a processor; and
a non-transitory computer-readable storage medium comprising instructions that, when executed, cause the processor to:
capture a first image of a first field region with the first camera of the device;
set, by a computer of the device, a target treatment boundary location in the first field region based on the first image, the target treatment boundary location set in the first field region between a first treatment area and a second treatment area;
control, by the computer, a treatment mechanism of the device to apply the first treatment to the first treatment area;
control, by the computer, the treatment mechanism of the device to apply the second treatment to the second treatment area at a transition time, wherein the transition time is based on the target treatment boundary location;
capture a second image of a second field region with a second camera of the device after the transition time, wherein the second field region overlaps with at least a portion of the first field region, the overlapped portion including the target treatment boundary location, and at least a portion of the first and second treatment areas, and the second camera being fixed on the device a predetermined separation distance away from the first camera along a traversal axis of the device;
determine an actual treatment boundary location based on the second image and a motion of the device, wherein the actual treatment boundary location is a location in the first field region where application of the second treatment begins; and
calibrate the device based on the target treatment boundary location

Assignees

• Blue River Tech Inc

Inventors

• Redden Lee Kamp
• Anderson Kent
• Pell Edward William Jeffcott
• Ostrowski James Patrick

Classifications

• A01M21/02

  Apparatus for mechanical destruction {(hand-tools for uprooting weeds A01B1/16; machines for working soil and for weeding A01B39/18; harvesting machines A01D; cutting implements A01G3/00)} · CPC title

• A01B41/06 Primary

  with electric, e.g. photo-electric control of thinning operations · CPC title

• A01C21/00

  Methods of fertilising {, sowing or planting} · CPC title

• G01C11/00

  Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying · CPC title

• G01C11/06

  by comparison of two or more pictures of the same area · CPC title